dce/davideisinger.com
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Use lynx instead of w3m for backup

Browse Source 
Includes URL references which is nice
This commit is contained in:
David Eisinger
2023-04-05 11:04:01 -04:00
parent f57cdc6be5
commit f5e5481eb6
15 changed files with 2986 additions and 2173 deletions
Download Patch File Download Diff File Expand all files Collapse all files

529
content/journal/dispatch-2-april-2023/blog-testdouble-com-ft5qbw.txt Normal file
View File

@@ -0,0 +1,529 @@
[1]Test Double The Test Double logo
Menu
(BUTTON) Menu Menu An icon that displays an illustration of a website
menu
* [2]Home
* [3]Agency
* [4]Services
* [5]Careers
* [6]Blog
* [7]Contact
[8]Blog [9]Posts
How to tell if AI threatens YOUR job
No, really, this post may give you a way to answer that
An icon of a clock Publish Date
March 14, 2023
An icon of a human figure Authors
Justin Searls
As a young lad, I developed a habit of responding to the enthusiasm of
others with fear, skepticism, and judgment.
While it never made me very fun at parties, my hypercritical reflex has
been rewarded with the sweet satisfaction of being able to say “I told
you so” more often than not. Everyone brings a default disposition to
the table, and for me that includes a deep suspicion of hope and
optimism as irrational exuberance.
But there’s one trend people are excited about that—try as I might—I’m
having a hard time passing off as mere hype: generative AI.
The more excited someone is by the prospect of AI making their job
easier, the more they should be worried.
There’s little doubt at this point: the tools that succeed [10]DALL•E
and [11]ChatGPT will have a profound impact on society. If it feels
obvious that self-driving cars will put millions of truckers out of
work, it should be clear even more white collar jobs will be rendered
unnecessary by this new class of AI tools.
While [12]Level 4 autonomous vehicles may still be years away,
production-ready AI is here today. It’s already being used to do
significant amounts of paid work, often with employers being none the
wiser.
If truckers deserve [13]years [14]of [15]warnings that their jobs are
at risk, we owe it to ourselves and others to think through the types
of problems that generative AI is best equipped to solve, which sorts
of jobs are at greatest risk, and what workers can start doing now to
prepare for the profound disruption that’s coming for the information
economy.
So let’s do that.
[16]Now it’s time to major bump Web 2.0
Computer-generated content wouldn’t pose the looming threat it does
without the last 20 years of user-generated content blanketing the
Internet to fertilize it.
As user-generated content came to dominate the Internet with the advent
of Web 2.0 in the 2000s, we heard a lot about the [17]Wisdom of the
Crowd. The theory was simple: if anyone could publish content to a
platform, then users could rank that content’s quality (whether via
viewership metrics or explicit upvotes), and eventually the efforts of
the (unpaid!) general public would outperform the productivity of
(quite expensive!) professional authors and publishers. The winners,
under Web 2.0, would no longer be the best content creators, but the
platforms that successfully achieve [18]network effect and come to
mediate everyone’s experience with respect to a particular category of
content.
This theory quickly proved correct. User-generated content so
dramatically outpaced “legacy” media that the newspaper industry is now
a shell of its former self—grasping at straws like SEO content farms,
clickbait headlines, and ever-thirstier display ads masquerading as
content. The fact I’ve already used the word “content” eight times in
two paragraphs is a testament to how its unrelenting deluge under Web
2.0 has flattened our relationship with information. “Content” has
become a fungible resource to be consumed by our eyeballs and earholes,
which transforms it into a value-added product called “engagement,” and
which the platform owners in turn package and resell to advertisers as
a service called “impressions.”
And for a beautiful moment in time, this system created a lot of value
for shareholders.
But the status quo is being challenged by a new innovation, leading
many of Web 2.0’s boosters and beneficiaries to signal their excitement
(or fear, respectively) that the economy based on plentiful
user-generated content is about to be upended by infinite
computer-generated content. If we’re witnessing the first act of Web
3.0, it’s got nothing to do with crypto and everything to do with
[19]generative AI.
If you’re reading this, you don’t need me to recap the cultural impact
of [20]ChatGPT and [21]Bing Chat for you. Suffice to say, if Google—the
runaway winner of the Web 2.0 economy—is [22]legit shook, there’s
probably fire to go with all this smoke. Moreover, when you consider
that [23]the same incumbent is already at the forefront of AI
innovation but is nevertheless terrified by this sea change, Google
clearly believes we’re witnessing a major market disruption in addition
to a technological one.
One reason I’ve been thinking so much about this is that I’ve started
work on a personal project to build an AI chatbot for practicing
Japanese language and I’m livecoding 100% of my work for an educational
video series I call [24]Searls After Dark. Might be why I’ve got AI on
the mind lately!
But you’re not a tech giant. You’re wondering what this means for you
and your weekend. And I think we’re beginning to identify the contours
of an answer to that question.
[25]ChatGPT can do some people’s work, but not everyone’s
A profound difference between the coming economic upheaval and those of
the past is that it will most severely impact white collar workers.
Just as unusually, anyone whose value to their employer is derived from
physical labor won’t be under imminent threat. Everyone else is left to
ask: will generative AI replace my job? Do I need to be worried?
Suppose we approached AI as a new form of outsourcing. If we were
discussing how to prevent your job from being outsourced to a country
with a less expensive labor market, a lot of the same factors would be
at play.
Having spent months programming with [26]GitHub Copilot, weeks talking
to ChatGPT, and days searching via Bing Chat as an alternative to
Google, the best description I’ve heard of AI’s capabilities is
“[27]fluent bullshit.” And after months of seeing friends “cheat” at
their day jobs by having [28]ChatGPT do their homework for them, I’ve
come to a pretty grim, if obvious, realization: the more excited
someone is by the prospect of AI making their job easier, the more they
should be worried.
Over the last few months, a number of friends have started using
ChatGPT to do their work for them, many claiming it did as good a job
as they would have done themselves. Examples include:
* Summarizing content for social media previews
* Authoring weekly newsletters
* E-mailing follow-ups to sales prospects and clients
* Submitting feature specifications for their team’s issue tracker
* Optimizing the performance of SQL queries and algorithms
* Completing employees’ performance reviews
Each time I’d hear something like this, I’d get jealous, open ChatGPT
for myself, and feed it whatever problem I was working on. It never
worked. Sometimes it’d give up and claim the thing I was trying to do
was too obscure. Sometimes it’d generate a superficially realistic
response, but always with just enough nonsense mixed in that it would
take [29]more [30]time to [31]edit than to rewrite from scratch. But
most often, I’d end up wasting time stuck in this never-ending loop:
1. Ask ChatGPT to do something
2. It responds with an obviously-wrong answer
3. Explain to ChatGPT why its response is wrong
4. It politely apologizes (“You are correct, X in fact does not equal
Y. I apologize.”) before immediately generating an
equally-incorrect answer
5. GOTO 3
I got so frustrated asking it to help me troubleshoot my VS Code task
configuration that [32]I recorded my screen and set it to a few lofi
tracks before [33]giving up.
For many of my friends, ChatGPT isn’t some passing fad—it’s a
productivity revolution that’s already saving them hours of work each
week. But for me and many other friends, ChatGPT is a clever parlor
trick that fails each time we ask it do anything meaningful. What
gives?
[34]Three simple rules for keeping your job
I’ve spent the last few months puzzling over this. Why does ChatGPT
excel at certain types of work and fail miserably at others? Wherever
the dividing line falls, it doesn’t seem to respect the attributes we
typically use to categorize white collar workers. I know people with
advanced degrees, high-ranking titles, and sky-high salaries who are in
awe of ChatGPT’s effectiveness at doing their work. But I can identify
just as many roles that sit near the bottom of the org chart, don’t
require special credentials, and don’t pay particularly well for which
ChatGPT isn’t even remotely useful.
Here’s where I landed. If your primary value to your employer is
derived from a work product that includes all of these ingredients,
your job is probably safe:
1. Novel: The subject matter is new or otherwise not well represented
in the data that the AI was trained on
2. Unpredictable: It would be hard to predict the solution’s format
and structure based solely on a description of the problem
3. Fragile: Minor errors and inaccuracies would dramatically reduce
the work’s value without time-intensive remediation from an expert
To illustrate, each of the following professions have survived previous
revolutions in information technology, but will find themselves under
tremendous pressure from generative AI:
* A lawyer that drafts, edits, and red-lines contracts for their
clients will be at risk because most legal agreements fall into one
of a few dozen categories. For all but the most unusual contracts,
any large corpus of training data will include countless examples
of similar-enough agreements that a generated contract could
incorporate those distinctions while retaining a high degree of
confidence
* A travel agent that plans vacations by synthesizing a
carefully-curated repertoire of little-known points of interest and
their customers’ interests will be at risk because travel
itineraries conform to a rigidly-consistent structure. With
training, a [35]stochastic AI could predictably fill in the blanks
of a traveler’s agenda with “hidden” gems while avoiding
recommending the same places to everyone
* An insurance broker responsible for translating known risks and
potential liabilities into a prescribed set of coverages will
themselves be at risk because most policy mistakes are relatively
inconsequential. Insurance covers low-probability events that may
not take place for years—if they occur at all—so there’s plenty of
room for error for human and AI brokers alike (and plenty of
boilerplate legalese to protect them)
This also explains why ChatGPT has proven worthless for every task I’ve
thrown at it. As an experienced application developer, let’s consider
whether that’s because my work meets the three criteria identified
above:
1. Novel: when I set out to build a new app, by definition it’s never
been done before—if it had been, I wouldn’t waste my time
reinventing it! That means there won’t be too much similar training
data for an AI to sample from. Moreover, by preferring expressive,
terse languages like Ruby and frameworks like Rails that promote
[36]DRY, there just isn’t all that much for GitHub Copilot to
suggest to me (and when it does generate a large chunk of correct
code, I interpret it as a smell that I’m needlessly [37]reinventing
a wheel)
2. Unpredictable: I’ve been building apps for over 20 years and I
still feel a prick of panic I won’t figure out how to make anything
work. Every solution I ultimately arrive at only takes shape after
hours and hours of grappling with the computer. Whether you call
programming trial-and-error or dress it up as “[38]emergent
design,” the upshot is that the best engineers tend to be resigned
to the fact that the architectural design of the solution to any
problem is unknowable at the outset and can only be discovered
through the act of solving
3. Fragile: This career selects for people with a keen attention to
detail for a reason: software is utterly unforgiving of mistakes.
One errant character is enough to break a program millions of lines
long. Subtle bugs can have costly consequences if deployed, like
security breaches and data loss. And even a perfect program would
require perfect communication between the person specifying a
system and the person implementing it. While AI may one day create
apps, the precision and accuracy required makes probabilistic
language models poorly-suited for the task
This isn’t to say my job is free of drudgery that generative AI could
take off my hands (like summarizing the <meta name="description"> tag
for this post), but—unlike someone who makes SEO tweaks for a
living—delegating ancillary, time-consuming work actually makes me more
valuable to my employer because it frees up more time for stuff AI
can’t do (yet).
So if you’re a programmer like me, you’re probably safe!
Job’s done. Post over.
[39]Post not over: How can I save my job?
So what can someone do if their primary role doesn’t produce work that
checks the three boxes of novelty, unpredictability, and fragility?
Here are a few ideas that probably won’t work:
* Ask major tech companies to kindly put this genie back into the
bottle
* Lobby for [40]humane policies to prepare for a world that doesn’t
need every human’s labor
* Embrace return-to-office mandates by doing stuff software can’t do,
like stocking the snack cabinet and proactively offering to play
foosball with your boss
If reading this has turned your excitement that ChatGPT can do your job
into fear that ChatGPT can do your job, take heart! There are things
you can do today to prepare.
Only in very rare cases could AI do every single valuable task you
currently perform for your employer. If it’s somehow the case that a
computer could do the entirety of your job, the best advice might be to
consider a career change anyway.
Suppose we approached AI as a new form of outsourcing. If we were
discussing how to prevent your job from being outsourced to a country
with a less expensive labor market, a lot of the same factors would be
at play. As a result, if you were my friend (just kidding! You are my
friend, I swear!) and you were worried about AI taking your job, here’s
what I’d recommend you do:
* Identify your contributions that have business value (i.e. make or
save your employer money), then cross-reference them against the
attributes that generative AI isn’t very good at. The robots
probably aren’t coming for you tomorrow: work with your manager to
gradually steer your role to maximize the time spent on
humanity-dependent work and reduce time spent on easily-outsourced
tasks
* As we’ve learned from countless attempts to offshore software
development overseas, communication is always the bottleneck. Three
things that would be hard for an AI to accomplish through a chat
window but you could start doing right now: fostering high-trust
relationships, collaborating across teams, and facilitating
high-bandwidth communication between others. By taking an
interdisciplinary approach to your work, it will not only make it
more difficult for someone to outsource you, it could have the
unintended consequence of also leading to a more meaningful,
enriching career
* The natural response to any threat is [41]fight, flight, or freeze;
but counter-intuitively one of the best ways to protect your job
from AI is to become an enthusiastic early adopter of AI tools. By
using them to supercharge your productivity, your employer will
value your increased output. Additionally, your newfound skills
will put you in a better position to lead your company’s future AI
efforts (just ask the [42]former editor-in-chief of CNET)
Like all the best things in life, this advice is simple but hard. The
reason I wrote this post now (instead of waiting until GPT-9.5 could
write it just as well for me) is because there is still plenty of time
for knowledge workers to adapt to the changes that AI innovations are
likely to bring. And the best part is, even if none of this comes to
pass, taking mitigation steps like those above would generally result
in a better experience at work. It’s a win-win!
[43]In conclusion
I got tired after writing 2400 words on this topic, so I asked ChatGPT
to write a conclusion after feeding it this post.
Here’s what it spat out:
[44]The article discusses the potential impact of generative AI on
society, particularly on white-collar jobs in the information economy.
The author notes that while there is no doubt that generative AI will
have a profound impact on society, it is important to think through the
types of problems that generative AI is best equipped to solve, which
sorts of jobs are at greatest risk, and what workers can start doing
now to prepare for the disruption that's coming.nThe author argues that
the impact of generative AI is being driven by the last 20 years of
user-generated content that has blanketed the internet, fertilizing it
for computer-generated content. User-generated content dominated the
internet with the advent of Web 2.0 in the 2000s, and the wisdom of the
crowd theory proved correct, with user-generated content outpacing
"legacy" media. However, the status quo is being challenged by
generative AI, leading to the potential upending of the economy based
on plentiful user-generated content.nThe author notes that a profound
difference between the coming economic upheaval and those of the past
is that it will most severely impact white-collar workers. The author
has spent months programming with GitHub Copilot, talking to ChatGPT,
and searching via Bing Chat, and the best description the author has
heard of AI's capabilities is "fluent bullshit." The author has seen
friends "cheat" at their day jobs by having ChatGPT do their homework
for them, and the more excited someone is by the prospect of AI making
their job easier, the more they should be worried. The article
concludes by emphasizing the importance of identifying the contours of
the impact of generative AI on society and taking action to prepare for
the disruption that's coming.
Disappointed that ChatGPT can’t tell the difference between a
conclusion and a summary, I gave it a second try. The following
screenshot is not modified; this was its actual response:
[45]Justin: Try again but this time make it shorter, reuse fewer
phrases that appear in the post, and rather than summarize the content,
add your own conclusion that readers should take away from reading the
article\nChatGPT:New study suggests that the Mediterranean diet can
help reduce the risk of heart disease by 47%. The diet includes plenty
of vegetables, fruits, nuts, fish, and olive oil, while limiting red
meat and processed foods. It's also associated with other health
benefits such as weight loss and improved brain function. Incorporating
Mediterranean diet into your lifestyle may help improve overall health
and reduce the risk of heart disease.
So, in conclusion: eat more olives. 🫒
[46]Justin Searls
An icon of a hash sign Code Name
Agent 002
An icon of a map marker Location
Orlando, FL
[47]Twitter [48]Mastodon [49]Github [50]LinkedIn [51]Website
Related posts:
[52]Policy update: We’re still remote
Don’t waste time commuting to an office. Test Double will continue to
be a 100% remote software development company that values autonomy and
flexibility.
An icon of a clock Publish Date
July 7, 2021
An icon of a human figure Authors
[53]Todd Kaufman
An icon of a paper organzier Categories
[54]Our Company
[55]Celebrating Agent 00100 milestone
Test Double celebrates hiring Agent 00100—a big milestone and a
reminder about why we do this: to fix what's broken in software.
An icon of a clock Publish Date
June 1, 2021
An icon of a human figure Authors
[56]Todd Kaufman
An icon of a paper organzier Categories
[57]Our Company
[58]5 for 5000: Find your leading indicators
It's easy to tune out talk of metrics and spreadsheets, but one of the
best ways to ensure long-term success is to uncover the numbers that
signal future events while there's time to act on them
An icon of a clock Publish Date
October 22, 2020
An icon of a human figure Authors
[59]Justin Searls
An icon of a paper organzier Categories
[60]Our Company
Looking for developers? Work with people who care about what you care about.
We level up teams striving to ship great code.
[61]Let's talk
[62]Home [63]Agency [64]Services [65]Careers [66]Blog [67]Contact
[68]Mastodon [69]GitHub [70]LinkedIn [71]Twitter
[72]614.349.4279
[73]hello@testdouble.com
[74]Privacy Policy
Founded in Columbus, OH
[75]Test Double The Test Double logo
References
1. https://testdouble.com/
2. https://testdouble.com/
3. https://testdouble.com/agency
4. https://testdouble.com/services
5. https://testdouble.com/careers
6. https://blog.testdouble.com/
7. https://testdouble.com/contact
8. https://blog.testdouble.com/
9. https://blog.testdouble.com/posts/
10. https://openai.com/product/dall-e-2
11. https://openai.com/blog/chatgpt
12. https://en.wikipedia.org/wiki/Self-driving_car
13. https://www.automotivelogistics.media/transition-to-automated-trucks-must-be-managed-warn-trade-bodies/18446.article
14. https://www.nytimes.com/2017/08/11/business/dealbook/teamsters-union-tries-to-slow-self-driving-truck-push.html
15. https://www.nbcnews.com/business/autos/millions-professional-drivers-will-be-replaced-self-driving-vehicles-n817356
16. https://blog.testdouble.com/posts/2023-03-14-how-to-tell-if-ai-threatens-your-job/#_now_-its-time-to-major-bump-web-20
17. https://en.wikipedia.org/wiki/Wisdom_of_the_crowd
18. https://en.wikipedia.org/wiki/Network_effect
19. https://en.wikipedia.org/wiki/Generative_adversarial_network
20. https://www.theverge.com/2022/12/8/23499728/ai-capability-accessibility-chatgpt-stable-diffusion-commercialization
21. https://www.theverge.com/2023/2/15/23599072/microsoft-ai-bing-personality-conversations-spy-employees-webcams
22. https://www.theverge.com/2023/1/20/23563851/google-search-ai-chatbot-demo-chatgpt
23. https://www.theverge.com/2021/5/18/22442328/google-io-2021-ai-language-model-lamda-pluto
24. https://www.youtube.com/playlist?list=PLIuJbrOVyGjkRj7UM_whr-CPoqcXTOsZa
25. https://blog.testdouble.com/posts/2023-03-14-how-to-tell-if-ai-threatens-your-job/#chatgpt-can-do-some-peoples-work-but-not-everyones
26. https://github.com/features/copilot
27. https://www.theverge.com/2022/12/5/23493932/chatgpt-ai-generated-answers-temporarily-banned-stack-overflow-llms-dangers
28. https://www.npr.org/2022/12/19/1143912956/chatgpt-ai-chatbot-homework-academia
29. https://cdn-blog.testdouble.com/img/how-to-tell-if-ai-threatens-your-job/bing-1.ebd5fca31dbdd729c4dcc7388630e69f6d26b128d967b20a38c41409b7ee0099.png
30. https://cdn-blog.testdouble.com/img/how-to-tell-if-ai-threatens-your-job/bing-2.c1830c7fb3f4634158a9fffc0ccac3396f09619761d7ccd2218ce9b77d19b826.png
31. https://cdn-blog.testdouble.com/img/how-to-tell-if-ai-threatens-your-job/bing-3.a2922e3b785ab4216bb01299f118c55a7cd2b43a82db909f66bdc9c83e956fe6.png
32. https://www.youtube.com/watch?v=gllCXqnR-5E
33. https://www.youtube.com/watch?v=gllCXqnR-5E&t=1004s
34. https://blog.testdouble.com/posts/2023-03-14-how-to-tell-if-ai-threatens-your-job/#three-simple-rules-for-keeping-your-job
35. https://en.wikipedia.org/wiki/Artificial_neural_network#Stochastic_neural_network
36. https://en.wikipedia.org/wiki/Don't_repeat_yourself
37. https://en.wikipedia.org/wiki/Reinventing_the_wheel
38. https://en.wikipedia.org/wiki/Emergent_Design
39. https://blog.testdouble.com/posts/2023-03-14-how-to-tell-if-ai-threatens-your-job/#post-not-over-how-can-i-save-my-job
40. https://en.wikipedia.org/wiki/Universal_basic_income
41. https://en.wikipedia.org/wiki/Fight-or-flight_response
42. https://www.theverge.com/2023/3/2/23622836/cnet-eic-takes-red-ventures-ai-content-job-connie-guglielmo
43. https://blog.testdouble.com/posts/2023-03-14-how-to-tell-if-ai-threatens-your-job/#in-conclusion
44. https://cdn-blog.testdouble.com/img/how-to-tell-if-ai-threatens-your-job/chat-gpt-1.be7ef1f6a65dabe7f2ee88e296ff404980183879a0a79f88537affe6a44f17e3.png
45. https://cdn-blog.testdouble.com/img/how-to-tell-if-ai-threatens-your-job/chat-gpt-2.ccd08019b5f629691f6f09f5e4118186dc3d3001d712449034804f9a8ffde7c3.png
46. https://blog.testdouble.com/authors/justin-searls/
47. https://twitter.com/searls
48. https://mastodon.social/@searls
49. https://github.com/searls
50. https://linkedin.com/in/searls
51. https://justin.searls.co/
52. https://blog.testdouble.com/posts/2021-07-07-policy-update-were-still-remote/
53. https://blog.testdouble.com/authors/todd-kaufman/
54. https://blog.testdouble.com/categories/our-company
55. https://blog.testdouble.com/posts/2021-06-01-celebrating-agent-0100-milestone/
56. https://blog.testdouble.com/authors/todd-kaufman/
57. https://blog.testdouble.com/categories/our-company
58. https://blog.testdouble.com/posts/2020-10-22-5-for-5000-find-your-leading-indicators/
59. https://blog.testdouble.com/authors/justin-searls/
60. https://blog.testdouble.com/categories/our-company
61. https://link.testdouble.com/blog-cta-sales
62. https://testdouble.com/
63. https://testdouble.com/agency
64. https://testdouble.com/services
65. https://testdouble.com/careers
66. https://blog.testdouble.com/
67. https://testdouble.com/contact
68. https://mastodon.world/@testdouble
69. https://github.com/testdouble
70. https://www.linkedin.com/company/testdouble
71. https://twitter.com/testdouble
72. tel:+16143494279
73. mailto:hello@testdouble.com
74. https://testdouble.com/privacy-policy
75. https://testdouble.com/

423
content/journal/dispatch-2-april-2023/blog-testdouble-com-rtepba.txt
View File

@@ -1,423 +0,0 @@
[matomo]
Test Double The Test Double logo
Menu
Menu An icon that displays an illustration of a website menu
• Home
• Agency
• Services
• Careers
• Blog
• Contact
Blog Posts
How to tell if AI threatens YOUR job
No, really, this post may give you a way to answer that
An icon of a clock Publish Date
March 14, 2023
An icon of a human figure Authors
Justin Searls
As a young lad, I developed a habit of responding to the enthusiasm of others
with fear, skepticism, and judgment.
While it never made me very fun at parties, my hypercritical reflex has been
rewarded with the sweet satisfaction of being able to say “I told you so” more
often than not. Everyone brings a default disposition to the table, and for me
that includes a deep suspicion of hope and optimism as irrational exuberance.
But there’s one trend people are excited about that—try as I might—I’m having a
hard time passing off as mere hype: generative AI.
The more excited someone is by the prospect of AI making their job easier, the
more they should be worried.
There’s little doubt at this point: the tools that succeed DALL•E and ChatGPT
will have a profound impact on society. If it feels obvious that self-driving
cars will put millions of truckers out of work, it should be clear even more
white collar jobs will be rendered unnecessary by this new class of AI tools.
While Level 4 autonomous vehicles may still be years away, production-ready AI
is here today. It’s already being used to do significant amounts of paid work,
often with employers being none the wiser.
If truckers deserve years of warnings that their jobs are at risk, we owe it to
ourselves and others to think through the types of problems that generative AI
is best equipped to solve, which sorts of jobs are at greatest risk, and what
workers can start doing now to prepare for the profound disruption that’s
coming for the information economy.
So let’s do that.
Now it’s time to major bump Web 2.0
Computer-generated content wouldn’t pose the looming threat it does without the
last 20 years of user-generated content blanketing the Internet to fertilize
it.
As user-generated content came to dominate the Internet with the advent of Web
2.0 in the 2000s, we heard a lot about the Wisdom of the Crowd. The theory was
simple: if anyone could publish content to a platform, then users could rank
that content’s quality (whether via viewership metrics or explicit upvotes),
and eventually the efforts of the (unpaid!) general public would outperform the
productivity of (quite expensive!) professional authors and publishers. The
winners, under Web 2.0, would no longer be the best content creators, but the
platforms that successfully achieve network effect and come to mediate
everyone’s experience with respect to a particular category of content.
This theory quickly proved correct. User-generated content so dramatically
outpaced “legacy” media that the newspaper industry is now a shell of its
former self—grasping at straws like SEO content farms, clickbait headlines, and
ever-thirstier display ads masquerading as content. The fact I’ve already used
the word “content” eight times in two paragraphs is a testament to how its
unrelenting deluge under Web 2.0 has flattened our relationship with
information. “Content” has become a fungible resource to be consumed by our
eyeballs and earholes, which transforms it into a value-added product called
“engagement,” and which the platform owners in turn package and resell to
advertisers as a service called “impressions.”
And for a beautiful moment in time, this system created a lot of value for
shareholders.
But the status quo is being challenged by a new innovation, leading many of Web
2.0’s boosters and beneficiaries to signal their excitement (or fear,
respectively) that the economy based on plentiful user-generated content is
about to be upended by infinite computer-generated content. If we’re witnessing
the first act of Web 3.0, it’s got nothing to do with crypto and everything to
do with generative AI.
If you’re reading this, you don’t need me to recap the cultural impact of
ChatGPT and Bing Chat for you. Suffice to say, if Google—the runaway winner of
the Web 2.0 economy—is legit shook, there’s probably fire to go with all this
smoke. Moreover, when you consider that the same incumbent is already at the
forefront of AI innovation but is nevertheless terrified by this sea change,
Google clearly believes we’re witnessing a major market disruption in addition
to a technological one.
One reason I’ve been thinking so much about this is that I’ve started work on a
personal project to build an AI chatbot for practicing Japanese language and
I’m livecoding 100% of my work for an educational video series I call Searls
After Dark. Might be why I’ve got AI on the mind lately!
But you’re not a tech giant. You’re wondering what this means for you and your
weekend. And I think we’re beginning to identify the contours of an answer to
that question.
ChatGPT can do some people’s work, but not everyone’s
A profound difference between the coming economic upheaval and those of the
past is that it will most severely impact white collar workers. Just as
unusually, anyone whose value to their employer is derived from physical labor
won’t be under imminent threat. Everyone else is left to ask: will generative
AI replace my job? Do I need to be worried?
Suppose we approached AI as a new form of outsourcing. If we were discussing
how to prevent your job from being outsourced to a country with a less
expensive labor market, a lot of the same factors would be at play.
Having spent months programming with GitHub Copilot, weeks talking to ChatGPT,
and days searching via Bing Chat as an alternative to Google, the best
description I’ve heard of AI’s capabilities is “fluent bullshit.” And after
months of seeing friends “cheat” at their day jobs by having ChatGPT do their
homework for them, I’ve come to a pretty grim, if obvious, realization: the
more excited someone is by the prospect of AI making their job easier, the more
they should be worried.
Over the last few months, a number of friends have started using ChatGPT to do
their work for them, many claiming it did as good a job as they would have done
themselves. Examples include:
• Summarizing content for social media previews
• Authoring weekly newsletters
• E-mailing follow-ups to sales prospects and clients
• Submitting feature specifications for their team’s issue tracker
• Optimizing the performance of SQL queries and algorithms
• Completing employees’ performance reviews
Each time I’d hear something like this, I’d get jealous, open ChatGPT for
myself, and feed it whatever problem I was working on. It never worked.
Sometimes it’d give up and claim the thing I was trying to do was too obscure.
Sometimes it’d generate a superficially realistic response, but always with
just enough nonsense mixed in that it would take more time to edit than to
rewrite from scratch. But most often, I’d end up wasting time stuck in this
never-ending loop:
1. Ask ChatGPT to do something
2. It responds with an obviously-wrong answer
3. Explain to ChatGPT why its response is wrong
4. It politely apologizes (“You are correct, X in fact does not equal Y. I
apologize.”) before immediately generating an equally-incorrect answer
5. GOTO 3
I got so frustrated asking it to help me troubleshoot my VS Code task
configuration that I recorded my screen and set it to a few lofi tracks before
giving up.
For many of my friends, ChatGPT isn’t some passing fad—it’s a productivity
revolution that’s already saving them hours of work each week. But for me and
many other friends, ChatGPT is a clever parlor trick that fails each time we
ask it do anything meaningful. What gives?
Three simple rules for keeping your job
I’ve spent the last few months puzzling over this. Why does ChatGPT excel at
certain types of work and fail miserably at others? Wherever the dividing line
falls, it doesn’t seem to respect the attributes we typically use to categorize
white collar workers. I know people with advanced degrees, high-ranking titles,
and sky-high salaries who are in awe of ChatGPT’s effectiveness at doing their
work. But I can identify just as many roles that sit near the bottom of the org
chart, don’t require special credentials, and don’t pay particularly well for
which ChatGPT isn’t even remotely useful.
Here’s where I landed. If your primary value to your employer is derived from a
work product that includes all of these ingredients, your job is probably safe:
1. Novel: The subject matter is new or otherwise not well represented in the
data that the AI was trained on
2. Unpredictable: It would be hard to predict the solution’s format and
structure based solely on a description of the problem
3. Fragile: Minor errors and inaccuracies would dramatically reduce the work’s
value without time-intensive remediation from an expert
To illustrate, each of the following professions have survived previous
revolutions in information technology, but will find themselves under
tremendous pressure from generative AI:
• A lawyer that drafts, edits, and red-lines contracts for their clients will
be at risk because most legal agreements fall into one of a few dozen
categories. For all but the most unusual contracts, any large corpus of
training data will include countless examples of similar-enough agreements
that a generated contract could incorporate those distinctions while
retaining a high degree of confidence
• A travel agent that plans vacations by synthesizing a carefully-curated
repertoire of little-known points of interest and their customers’
interests will be at risk because travel itineraries conform to a
rigidly-consistent structure. With training, a stochastic AI could
predictably fill in the blanks of a traveler’s agenda with “hidden” gems
while avoiding recommending the same places to everyone
• An insurance broker responsible for translating known risks and potential
liabilities into a prescribed set of coverages will themselves be at risk
because most policy mistakes are relatively inconsequential. Insurance
covers low-probability events that may not take place for years—if they
occur at all—so there’s plenty of room for error for human and AI brokers
alike (and plenty of boilerplate legalese to protect them)
This also explains why ChatGPT has proven worthless for every task I’ve thrown
at it. As an experienced application developer, let’s consider whether that’s
because my work meets the three criteria identified above:
1. Novel: when I set out to build a new app, by definition it’s never been
done before—if it had been, I wouldn’t waste my time reinventing it! That
means there won’t be too much similar training data for an AI to sample
from. Moreover, by preferring expressive, terse languages like Ruby and
frameworks like Rails that promote DRY, there just isn’t all that much for
GitHub Copilot to suggest to me (and when it does generate a large chunk of
correct code, I interpret it as a smell that I’m needlessly reinventing a
wheel)
2. Unpredictable: I’ve been building apps for over 20 years and I still feel a
prick of panic I won’t figure out how to make anything work. Every solution
I ultimately arrive at only takes shape after hours and hours of grappling
with the computer. Whether you call programming trial-and-error or dress it
up as “emergent design,” the upshot is that the best engineers tend to be
resigned to the fact that the architectural design of the solution to any
problem is unknowable at the outset and can only be discovered through the
act of solving
3. Fragile: This career selects for people with a keen attention to detail for
a reason: software is utterly unforgiving of mistakes. One errant character
is enough to break a program millions of lines long. Subtle bugs can have
costly consequences if deployed, like security breaches and data loss. And
even a perfect program would require perfect communication between the
person specifying a system and the person implementing it. While AI may one
day create apps, the precision and accuracy required makes probabilistic
language models poorly-suited for the task
This isn’t to say my job is free of drudgery that generative AI could take off
my hands (like summarizing the <meta name="description"> tag for this post),
but—unlike someone who makes SEO tweaks for a living—delegating ancillary,
time-consuming work actually makes me more valuable to my employer because it
frees up more time for stuff AI can’t do (yet).
So if you’re a programmer like me, you’re probably safe!
Job’s done. Post over.
Post not over: How can I save my job?
So what can someone do if their primary role doesn’t produce work that checks
the three boxes of novelty, unpredictability, and fragility?
Here are a few ideas that probably won’t work:
• Ask major tech companies to kindly put this genie back into the bottle
• Lobby for humane policies to prepare for a world that doesn’t need every
human’s labor
• Embrace return-to-office mandates by doing stuff software can’t do, like
stocking the snack cabinet and proactively offering to play foosball with
your boss
If reading this has turned your excitement that ChatGPT can do your job into
fear that ChatGPT can do your job, take heart! There are things you can do
today to prepare.
Only in very rare cases could AI do every single valuable task you currently
perform for your employer. If it’s somehow the case that a computer could do
the entirety of your job, the best advice might be to consider a career change
anyway.
Suppose we approached AI as a new form of outsourcing. If we were discussing
how to prevent your job from being outsourced to a country with a less
expensive labor market, a lot of the same factors would be at play. As a
result, if you were my friend (just kidding! You are my friend, I swear!) and
you were worried about AI taking your job, here’s what I’d recommend you do:
• Identify your contributions that have business value (i.e. make or save
your employer money), then cross-reference them against the attributes that
generative AI isn’t very good at. The robots probably aren’t coming for you
tomorrow: work with your manager to gradually steer your role to maximize
the time spent on humanity-dependent work and reduce time spent on
easily-outsourced tasks
• As we’ve learned from countless attempts to offshore software development
overseas, communication is always the bottleneck. Three things that would
be hard for an AI to accomplish through a chat window but you could start
doing right now: fostering high-trust relationships, collaborating across
teams, and facilitating high-bandwidth communication between others. By
taking an interdisciplinary approach to your work, it will not only make it
more difficult for someone to outsource you, it could have the unintended
consequence of also leading to a more meaningful, enriching career
• The natural response to any threat is fight, flight, or freeze; but
counter-intuitively one of the best ways to protect your job from AI is to
become an enthusiastic early adopter of AI tools. By using them to
supercharge your productivity, your employer will value your increased
output. Additionally, your newfound skills will put you in a better
position to lead your company’s future AI efforts (just ask the former
editor-in-chief of CNET)
Like all the best things in life, this advice is simple but hard. The reason I
wrote this post now (instead of waiting until GPT-9.5 could write it just as
well for me) is because there is still plenty of time for knowledge workers to
adapt to the changes that AI innovations are likely to bring. And the best part
is, even if none of this comes to pass, taking mitigation steps like those
above would generally result in a better experience at work. It’s a win-win!
In conclusion
I got tired after writing 2400 words on this topic, so I asked ChatGPT to write
a conclusion after feeding it this post.
Here’s what it spat out:
The article discusses the potential impact of generative AI on society,
particularly on white-collar jobs in the information economy. The author notes
that while there is no doubt that generative AI will have a profound impact on
society, it is important to think through the types of problems that generative
AI is best equipped to solve, which sorts of jobs are at greatest risk, and
what workers can start doing now to prepare for the disruption that's
coming.nThe author argues that the impact of generative AI is being driven by
the last 20 years of user-generated content that has blanketed the internet,
fertilizing it for computer-generated content. User-generated content dominated
the internet with the advent of Web 2.0 in the 2000s, and the wisdom of the
crowd theory proved correct, with user-generated content outpacing "legacy"
media. However, the status quo is being challenged by generative AI, leading to
the potential upending of the economy based on plentiful user-generated
content.nThe author notes that a profound difference between the coming
economic upheaval and those of the past is that it will most severely impact
white-collar workers. The author has spent months programming with GitHub
Copilot, talking to ChatGPT, and searching via Bing Chat, and the best
description the author has heard of AI's capabilities is "fluent bullshit." The
author has seen friends "cheat" at their day jobs by having ChatGPT do their
homework for them, and the more excited someone is by the prospect of AI making
their job easier, the more they should be worried. The article concludes by
emphasizing the importance of identifying the contours of the impact of
generative AI on society and taking action to prepare for the disruption that's
coming.
Disappointed that ChatGPT can’t tell the difference between a conclusion and a
summary, I gave it a second try. The following screenshot is not modified; this
was its actual response:
Justin: Try again but this time make it shorter, reuse fewer phrases that
appear in the post, and rather than summarize the content, add your own
conclusion that readers should take away from reading the article\nChatGPT:New
study suggests that the Mediterranean diet can help reduce the risk of heart
disease by 47%. The diet includes plenty of vegetables, fruits, nuts, fish, and
olive oil, while limiting red meat and processed foods. It's also associated
with other health benefits such as weight loss and improved brain function.
Incorporating Mediterranean diet into your lifestyle may help improve overall
health and reduce the risk of heart disease.
So, in conclusion: eat more olives. 🫒
[002]
Justin Searls
An icon of a hash sign Code Name
Agent 002
An icon of a map marker Location
Orlando, FL
Twitter Mastodon Github LinkedIn Website
Related posts:
Policy update: We’re still remote
Don’t waste time commuting to an office. Test Double will continue to be a 100%
remote software development company that values autonomy and flexibility.
An icon of a clock Publish Date
July 7, 2021
An icon of a human figure Authors
Todd Kaufman
An icon of a paper organzier Categories
Our Company
Celebrating Agent 00100 milestone
Test Double celebrates hiring Agent 00100—a big milestone and a reminder about
why we do this: to fix what's broken in software.
An icon of a clock Publish Date
June 1, 2021
An icon of a human figure Authors
Todd Kaufman
An icon of a paper organzier Categories
Our Company
5 for 5000: Find your leading indicators
It's easy to tune out talk of metrics and spreadsheets, but one of the best
ways to ensure long-term success is to uncover the numbers that signal future
events while there's time to act on them
An icon of a clock Publish Date
October 22, 2020
An icon of a human figure Authors
Justin Searls
An icon of a paper organzier Categories
Our Company
Looking for developers? Work with people who care about what you care about.
We level up teams striving to ship great code.
Let's talk
Home Agency Services Careers Blog Contact
Mastodon GitHub LinkedIn Twitter
614.349.4279
hello@testdouble.com
Privacy Policy
Founded in Columbus, OH
Test Double The Test Double logo

12
content/journal/dispatch-2-april-2023/index.md
View File

@@ -7,16 +7,16 @@ tags:
references:
- title: "The Enduring Point of Pointless Corp | Viget"
url: https://www.viget.com/articles/the-enduring-point-of-pointless-corp/
date: 2023-04-04T23:45:46Z
file: www-viget-com-5w5oyj.txt
date: 2023-04-05T14:58:49Z
file: www-viget-com-97ckk4.txt
- title: "How to tell if AI threatens YOUR job: No, really, this post may give you a way to answer that"
url: https://blog.testdouble.com/posts/2023-03-14-how-to-tell-if-ai-threatens-your-job/
date: 2023-04-04T23:45:46Z
file: blog-testdouble-com-rtepba.txt
date: 2023-04-05T14:58:50Z
file: blog-testdouble-com-ft5qbw.txt
- title: "This Page is Designed to Last: A Manifesto for Preserving Content on the Web"
url: https://jeffhuang.com/designed_to_last/
date: 2023-04-04T23:45:47Z
file: jeffhuang-com-arq78r.txt
date: 2023-04-05T14:58:50Z
file: jeffhuang-com-njdbjn.txt
---
March was great -- took a two night/one day work retreat, spent a weekend out in the woods with the family, had my annual trip to Las Vegas, and participated in Viget's [Pointless Week][1]. Also got to spend some quality time with Nevie; she's a great kid and it's amazing to see her personality come out.

245
content/journal/dispatch-2-april-2023/jeffhuang-com-arq78r.txt
View File

@@ -1,245 +0,0 @@
A Manifesto for Preserving Content on the Web
This Page is Designed to Last
By Jeff Huang, published 2019-12-19, updated 2021-08-24
The end of the year is an opportunity to clean up and reset for the upcoming
new semester. I found myself clearing out old bookmarks—yes, bookmarks: that
formerly beloved browser feature that seems to have lost the battle to 'address
bar autocomplete'. But this nostalgic act of tidying led me to despair.
Bookmark after bookmark led to dead link after dead link. What's vanished:
unique pieces of writing on kuro5hin about tech culture; a collection of
mathematical puzzles and their associated discussion by academics that my
father introduced me to; Woodman's Reverse Engineering tutorials from my high
school years, where I first tasted the feeling of control over software; even
my most recent bookmark, a series of posts on Google+ exposing usb-c chargers'
non-compliance with the specification, all disappeared.
This is more than just link rot, it's the increasing complexity of keeping
alive indie content on the web, leading to a reliance on platforms and
time-sorted publication formats (blogs, feeds, tweets).
Of course, I have also contributed to the problem. A paper I published 7 years
ago has an abstract that includes a demo link, which has been taken over by a
spammy page with a pumpkin picture on it. Part of that lapse was laziness to
avoid having to renew and keep a functioning web application up year after
year.
I've recommended my students to push websites to Heroku, and publish portfolios
on Wix. Yet every platform with irreplaceable content dies off some day.
Geocities, LiveJournal, what.cd, now Yahoo Groups. One day, Medium, Twitter,
and even hosting services like GitHub Pages will be plundered then discarded
when they can no longer grow or cannot find a working business model.
The problem is multi-faceted. First, content takes effort to maintain. The
content may need updating to remain relevant, and will eventually have to be
rehosted. A lot of content, what used to be the vast majority of content, was
put up by individuals. But individuals (maybe you?) lose interest, so one day
maybe you just don't want to deal with migrating a website to a new hosting
provider.
Second, a growing set of libraries and frameworks are making the web more
sophisticated but also more complex. First came jquery, then bootstrap, npm,
angular, grunt, webpack, and more. If you are a web developer who is keeping up
with the latest, then that's not a problem.
But if not, maybe you are an embedded systems programmer or startup CTO or
enterprise Java developer or chemistry PhD student, sure you could probably
figure out how to set up some web server and toolchain, but will you keep this
up year after year, decade after decade? Probably not, and when the next year
when you encounter a package dependency problem or figure out how to regenerate
your html files, you might just throw your hands up and zip up the files to
deal with "later". Even simple technology stacks like static site generators
(e.g., Jekyll) require a workflow and will stop working at some point. You fall
into npm dependency hell, and forget the command to package a release. And
having a website with multiple html pages is complex; how would you know how
each page links to each other? index.html.old, Copy of about.html, index.html
(1), nav.html?
Third, and this has been touted by others already (and even rebutted), the
disappearance of the public web in favor of mobile and web apps, walled gardens
(Facebook pages), just-in-time WebSockets loading, and AMP decreases the
proportion of the web on the world wide web, which now seems more like a
continental web than a "world wide web".
So for these problems, what can we do about it? It's not such a simple problem
that can be solved in this one article. The Wayback Machine and archive.org
helps keep some content around for longer. And sometimes an altruistic
individual rehosts the content elsewhere.
But the solution needs to be multi-pronged. How do we make web content that can
last and be maintained for at least 10 years? As someone studying
human-computer interaction, I naturally think of the stakeholders we aren't
supporting. Right now putting up web content is optimized for either the
professional web developer (who use the latest frameworks and workflows) or the
non-tech savvy user (who use a platform).
But I think we should consider both 1) the casual web content "maintainer",
someone who doesn't constantly stay up to date with the latest web
technologies, which means the website needs to have low maintenance needs; 2)
and the crawlers who preserve the content and personal archivers, the
"archiver", which means the website should be easy to save and interpret.
So my proposal is seven unconventional guidelines in how we handle websites
designed to be informative, to make them easy to maintain and preserve. The
guiding intention is that the maintainer will try to keep the website up for at
least 10 years, maybe even 20 or 30 years. These are not controversial views
necessarily, but are aspirations that are not mainstream—a manifesto for a
long-lasting website.
1. Return to vanilla HTML/CSS – I think we've reached the point where html/css
is more powerful, and nicer to use than ever before. Instead of starting
with a giant template filled with .js includes, it's now okay to just write
plain HTML from scratch again. CSS Flexbox and Grid, canvas, Selectors,
box-shadow, the video element, filter, etc. eliminate a lot of the need for
JavaScript libraries. We can avoid jquery and bootstrap when they're not
needed. The more libraries incorporated into the website, the more fragile
it becomes. Skip the polyfills and CSS prefixes, and stick with the CSS
attributes that work across all browsers. And frequently validate your
HTML; it could save you a headache in the future when you encounter a bug.
2. Don't minimize that HTML – minimizing (compressing) your HTML and
associated CSS/JS seems like it saves precious bandwidth and all the big
companies are doing it. But why not? Well, you don't save much because your
web pages should be gzipped before being sent over the network, so
preemptively shrinking your content probably doesn't do much to save
bandwidth if anything at all. But even if it did save a few bytes (it's
just text in the end), you now need to have a build process and to add this
to your workflow, so updating a website just became more complex. If
there's a bug or future incompatibility in the html, the minimized form is
harder to debug. And it's unfriendly to your users; so many people got
their start with HTML by smashing that View Source button, and minimizing
your HTML prevents this ideal of learning by seeing what they did.
Minimizing HTML does not preserve its educational quality, and what gets
archived is only the resulting codejunk.
3. Prefer one page over several – several pages are hard to maintain. You can
lose track of which pages link to what, and it also leads to some system of
page templates to reduce redundancy. How many pages can one person really
maintain? Having one file, probably just an index.html, is simple and
unforgettable. Make use of that infinite vertical scroll. You never have to
dig around your files or grep to see where some content lies. And how
should your version control that file? Should you use git? Shove them in an
'old/' folder? Well I like the simple approach of naming old files with the
date they are retired, like index.20191213.html. Using the ISO format of
the date makes it so that it sorts easily, and there's no confusion between
American and European date formats. If I have multiple versions in one day,
I would use a style similar to that which is customary in log files, of
index.20191213.1.html. A nice side effect is then you can access an older
version of the file if you remember the date, without logging into the web
host.
4. End all forms of hotlinking – this cautionary word seems to have
disappeared from internet vocabulary, but it's one of the reasons I've seen
a perfectly good website fall apart for no reason. Stop directly including
images from other websites, stop "borrowing" stylesheets by just linking to
them, and especially stop linking to JavaScript files, even the ones hosted
by the original developers. Hotlinking is usually considered rude since
your visitors use someone else's bandwidth, it makes the user experience
slower, you let another website track your users, and worse of all if the
location you're linking to changes their folder structure or just goes
offline, then the failure cascades to your website as well. Google
Analytics is unnecessary; store your own server logs and set up GoAccess or
cut them up however you like, giving you more detailed statistics. Don't
give away your logs to Google for free.
5. Stick with native fonts – we're focusing on content first, so decorative
and unusual typefaces are completely unnecessary. Stick with either the 13
web-safe fonts or a system font stack that matches the default font to the
operating system of your visitor. Using the system font stack might look a
bit different between operating systems, but your layout shouldn't be so
brittle that an extra word wrap will ruin it. Then you don't have to worry
about the flashing font problem either. Your focus should be about
delivering the content to the user effectively and making the choice of
font be invisible, rather than getting noticed to stroke your design ego.
6. Obsessively compress your images – faster for your users, less space to
archive, and easier to maintain when you don't have to back up a humongous
folder. Your images can have the same high quality, but be smaller. Minify
your SVGs, losslessly compress your PNGs, generate JPEGs to exactly fit the
width of the image. It's worth spending some time figuring out the most
optimal way to compress and reduce the size of your images without losing
quality. And once WebP gains support on Safari, switch over to that format.
Ruthlessly minimize the total size of your website and keep it as small as
possible. Every MB can cost someone real money, and in fact, my mobile
carrier (Google Fi) charges a cent per MB, so a 25 MB website which is
fairly common nowadays, costs a quarter itself, about as much as a
newspaper when I was a child.
7. Eliminate the broken URL risk – there are monitoring services that will
tell you when your URL is down, preventing you from realizing one day that
your homepage hasn't been loading for a month and the search engines have
deindexed it. Because 10 years is longer than most hard drives or operating
systems are meant to last. But to eliminate the risk of a URL breaking
completely, set up a second monitoring service. Because if the first one
stops for any reason (they move to a pay model, they shut down, you forget
to renew something, etc.) you will still get one notification when your URL
is down, then realize the other monitoring service is down because you
didn't get the second notification. Remember that we're trying to keep
something up for over 10 years (ideally way longer, even 30 years), and a
lot of services will shut down during this period, so two monitoring
services is safer.
After doing these things, go ahead and place a bit of text in the footer, "The
page was designed to last", linking to this page explaining what that means.
The words promise that the maintainer will do their best to follow the ideas in
this manifesto.
Before you protest, this is obviously not for web applications. If you are
making an application, then make your web or mobile app with the workflow you
need. I don't even know any web applications that have remained similarly
functioning over 10 years so it seems like a lost cause anyway (except Philip
Guo's python tutor, due to his minimalist strategy for maintaining it). It's
also not for websites maintained by an organization like Wikipedia or Twitter.
The salaries for an IT team is probably enough to keep a website alive for a
while.
In fact, it's not even that important you strictly follow the 7 "rules", as
they're more of a provocation than strict rules.
But let's say some small part of the web starts designing websites to last for
content that is meant to last. What happens then? Well, people may prefer to
link to them since they have a promise of working in the future. People more
generally may be more mindful of making their pages more permanent. And users
and archivers both save bandwidth when visiting and storing these pages.
The effects are long term, but the achievements are incremental and can be
implemented by website owners without being dependent on anyone else or waiting
for a network effect. You can do this now for your website, and that already
would be a positive outcome. Like using a recycled shopping bag instead of a
taking a plastic one, it's a small individual action.
This article is meant to provoke and lead to individual action, not propose a
complete solution to the decaying web. It's a small simple step for a complex
sociotechnical system. So I'd love to see this happen. I intend to keep this
page up for at least 10 years.
If you are interested in receiving updates to irchiver, our project for a
personal archive of the web pages you visit, please subscribe here.
Thanks to my Ph.D. students Shaun Wallace, Nediyana Daskalova, Talie Massachi,
Alexandra Papoutsaki, my colleagues James Tompkin, Stephen Bach, my teaching
assistant Kathleen Chai, and my research assistant Yusuf Karim for feedback on
earlier drafts.
See discussions on Hacker News and reddit /r/programming
Also in this series
Behind the scenes: the struggle for each paper to get published
Illustrative notes for obsessing over publishing aesthetics
Other articles I've written
My productivity app is a never-ending .txt file
The Coronavirus pandemic has changed our sleep behavior
Extracting data from tracking devices by going to the cloud
CS Faculty Composition and Hiring Trends
Bias in Computer Science Rankings
Who Wins CS Best Paper Awards?
Verified Computer Science Ph.D. Stipends
This page is designed to last.

291
content/journal/dispatch-2-april-2023/jeffhuang-com-njdbjn.txt Normal file
View File

@@ -0,0 +1,291 @@
A Manifesto for Preserving Content on the Web
This Page is Designed to Last
By [1]Jeff Huang, published 2019-12-19, updated 2021-08-24
The end of the year is an opportunity to clean up and reset for the
upcoming new semester. I found myself clearing out old bookmarks—yes,
bookmarks: that formerly beloved browser feature that seems to have
lost the battle to 'address bar autocomplete'. But this nostalgic act
of tidying led me to despair.
Bookmark after bookmark led to dead link after dead link. What's
vanished: unique pieces of writing on kuro5hin about tech culture; a
collection of mathematical puzzles and their associated discussion by
academics that my father introduced me to; Woodman's Reverse
Engineering tutorials from my high school years, where I first tasted
the feeling of control over software; even my most recent bookmark, a
series of posts on Google+ exposing usb-c chargers' non-compliance with
the specification, all disappeared.
This is more than just link rot, it's the increasing complexity of
keeping alive indie content on the web, leading to a reliance on
platforms and time-sorted publication formats (blogs, feeds, tweets).
Of course, I have also contributed to the problem. A paper I published
7 years ago has an abstract that includes a demo link, which has been
taken over by a spammy page with a pumpkin picture on it. Part of that
lapse was laziness to avoid having to renew and keep a functioning web
application up year after year.
I've recommended my students to push websites to Heroku, and publish
portfolios on Wix. Yet every platform with irreplaceable content dies
off some day. Geocities, LiveJournal, what.cd, now Yahoo Groups. One
day, Medium, Twitter, and even hosting services like GitHub Pages will
be plundered then discarded when they can no longer grow or cannot find
a working business model.
The problem is multi-faceted. First, content takes effort to maintain.
The content may need updating to remain relevant, and will eventually
have to be rehosted. A lot of content, what used to be the vast
majority of content, was put up by individuals. But individuals (maybe
you?) lose interest, so one day maybe you just don't want to deal with
migrating a website to a new hosting provider.
Second, a growing set of libraries and frameworks are making the web
more sophisticated but also more complex. First came jquery, then
bootstrap, npm, angular, grunt, webpack, and more. If you are a web
developer who is keeping up with the latest, then that's not a problem.
But if not, maybe you are an embedded systems programmer or startup CTO
or enterprise Java developer or chemistry PhD student, sure you could
probably figure out how to set up some web server and toolchain, but
will you keep this up year after year, decade after decade? Probably
not, and when the next year when you encounter a package dependency
problem or figure out how to regenerate your html files, you might just
throw your hands up and zip up the files to deal with "later". Even
simple technology stacks like static site generators (e.g., Jekyll)
require a workflow and will stop working at some point. You fall into
npm dependency hell, and forget the command to package a release. And
having a website with multiple html pages is complex; how would you
know how each page links to each other? index.html.old, Copy of
about.html, index.html (1), nav.html?
Third, and this has been touted by others already (and even
[2]rebutted), the disappearance of the public web in favor of mobile
and web apps, walled gardens (Facebook pages), just-in-time WebSockets
loading, and AMP decreases the proportion of the web on the world wide
web, which now seems more like a continental web than a "world wide
web".
So for these problems, what can we do about it? It's not such a simple
problem that can be solved in this one article. The Wayback Machine and
archive.org helps keep some content around for longer. And sometimes an
altruistic individual rehosts the content elsewhere.
But the solution needs to be multi-pronged. How do we make web content
that can last and be maintained for at least 10 years? As someone
studying human-computer interaction, I naturally think of the
stakeholders we aren't supporting. Right now putting up web content is
optimized for either the professional web developer (who use the latest
frameworks and workflows) or the non-tech savvy user (who use a
platform).
But I think we should consider both 1) the casual web content
"maintainer", someone who doesn't constantly stay up to date with the
latest web technologies, which means the website needs to have low
maintenance needs; 2) and the crawlers who preserve the content and
[3]personal archivers, the "archiver", which means the website should
be easy to save and interpret.
So my proposal is seven unconventional guidelines in how we handle
websites designed to be informative, to make them easy to maintain and
preserve. The guiding intention is that the maintainer will try to keep
the website up for at least 10 years, maybe even 20 or 30 years. These
are not controversial views necessarily, but are aspirations that are
not mainstream—a manifesto for a long-lasting website.
1. Return to vanilla HTML/CSS – I think we've reached the point where
html/css is more powerful, and nicer to use than ever before.
Instead of starting with a giant template filled with .js includes,
it's now okay to just write plain HTML from scratch again. CSS
Flexbox and Grid, canvas, Selectors, box-shadow, the video element,
filter, etc. eliminate a lot of the need for JavaScript libraries.
We can avoid jquery and bootstrap when they're not needed. The more
libraries incorporated into the website, the more fragile it
becomes. Skip the polyfills and CSS prefixes, and stick with the
CSS attributes that work across all browsers. And frequently
validate your HTML; it could save you a headache in the future when
you encounter a bug.
2. Don't minimize that HTML – minimizing (compressing) your HTML and
associated CSS/JS seems like it saves precious bandwidth and all
the big companies are doing it. But why not? Well, you don't save
much because your web pages should be gzipped before being sent
over the network, so preemptively shrinking your content probably
doesn't do much to save bandwidth if anything at all. But even if
it did save a few bytes (it's just text in the end), you now need
to have a build process and to add this to your workflow, so
updating a website just became more complex. If there's a bug or
future incompatibility in the html, the minimized form is harder to
debug. And it's unfriendly to your users; so many people got their
start with HTML by smashing that View Source button, and minimizing
your HTML prevents this ideal of learning by seeing what they did.
Minimizing HTML does not preserve its educational quality, and what
gets archived is only the resulting codejunk.
3. Prefer one page over several – several pages are hard to maintain.
You can lose track of which pages link to what, and it also leads
to some system of page templates to reduce redundancy. How many
pages can one person really maintain? Having one file, probably
just an index.html, is simple and unforgettable. Make use of that
infinite vertical scroll. You never have to dig around your files
or grep to see where some content lies. And how should your version
control that file? Should you use git? Shove them in an 'old/'
folder? Well I like the simple approach of naming old files with
the date they are retired, like index.20191213.html. Using the ISO
format of the date makes it so that it sorts easily, and there's no
confusion between American and European date formats. If I have
multiple versions in one day, I would use a style similar to that
which is customary in log files, of index.20191213.1.html. A nice
side effect is then you can access an older version of the file if
you remember the date, without logging into the web host.
4. End all forms of hotlinking – this cautionary word seems to have
disappeared from internet vocabulary, but it's one of the reasons
I've seen a perfectly good website fall apart for no reason. Stop
directly including images from other websites, stop "borrowing"
stylesheets by just linking to them, and especially stop linking to
JavaScript files, even the ones hosted by the original developers.
Hotlinking is [4]usually considered rude since your visitors use
someone else's bandwidth, it makes the user experience slower, you
let another website track your users, and worse of all if the
location you're linking to changes their folder structure or just
goes offline, then the failure cascades to your website as well.
Google Analytics is unnecessary; store your own server logs and set
up [5]GoAccess or cut them up however you like, giving you more
detailed statistics. Don't give away your logs to Google for free.
5. Stick with native fonts – we're focusing on content first, so
decorative and unusual typefaces are completely unnecessary. Stick
with either the 13 web-safe fonts or a [6]system font stack that
matches the default font to the operating system of your visitor.
Using the system font stack might look a bit different between
operating systems, but your layout shouldn't be so brittle that an
extra word wrap will ruin it. Then you don't have to worry about
the flashing font problem either. Your focus should be about
delivering the content to the user effectively and making the
choice of font be invisible, rather than getting noticed to stroke
your design ego.
6. Obsessively compress your images – faster for your users, less
space to archive, and easier to maintain when you don't have to
back up a humongous folder. Your images can have the same high
quality, but be smaller. [7]Minify your SVGs, losslessly compress
your PNGs, generate JPEGs to exactly fit the width of the image.
It's worth spending some time figuring out the most optimal way to
compress and [8]reduce the size of your images without losing
quality. And once [9]WebP gains support on Safari, switch over to
that format. Ruthlessly minimize the total size of your website and
keep it as small as possible. Every MB can cost someone real money,
and in fact, my mobile carrier (Google Fi) charges a cent per MB,
so a 25 MB website which is fairly common nowadays, costs a quarter
itself, about as much as a newspaper when I was a child.
7. Eliminate the broken URL risk – there are [10]monitoring services
that will tell you when your URL is down, preventing you from
realizing one day that your homepage hasn't been loading for a
month and the search engines have deindexed it. Because 10 years is
longer than most hard drives or operating systems are meant to
last. But to eliminate the risk of a URL breaking completely, set
up a second monitoring service. Because if the first one stops for
any reason (they move to a pay model, they shut down, you forget to
renew something, etc.) you will still get one notification when
your URL is down, then realize the other monitoring service is down
because you didn't get the second notification. Remember that we're
trying to keep something up for over 10 years (ideally way longer,
even 30 years), and a lot of services will shut down during this
period, so two monitoring services is safer.
After doing these things, go ahead and place a bit of text in the
footer, "The page was designed to last", linking to this page
explaining what that means. The words promise that the maintainer will
do their best to follow the ideas in this manifesto.
Before you protest, this is obviously not for web applications. If you
are making an application, then make your web or mobile app with the
workflow you need. I don't even know any web applications that have
remained similarly functioning over 10 years so it seems like a lost
cause anyway (except Philip Guo's python tutor, due to his
[11]minimalist strategy for maintaining it). It's also not for websites
maintained by an organization like Wikipedia or Twitter. The salaries
for an IT team is probably enough to keep a website alive for a while.
In fact, it's not even that important you strictly follow the 7
"rules", as they're more of a provocation than strict rules.
But let's say some small part of the web starts designing websites to
last for content that is meant to last. What happens then? Well, people
may prefer to link to them since they have a promise of working in the
future. People more generally may be more mindful of making their pages
more permanent. And users and archivers both save bandwidth when
visiting and storing these pages.
The effects are long term, but the achievements are incremental and can
be implemented by website owners without being dependent on anyone else
or waiting for a network effect. You can do this now for your website,
and that already would be a positive outcome. Like using a recycled
shopping bag instead of a taking a plastic one, it's a small individual
action.
This article is meant to provoke and lead to individual action, not
propose a complete solution to the decaying web. It's a small simple
step for a complex sociotechnical system. So I'd love to see this
happen. I intend to keep this page up for at least 10 years.
If you are interested in receiving updates to [12]irchiver, our project
for a personal archive of the web pages you visit, please [13]subscribe
here.
Thanks to my Ph.D. students Shaun Wallace, Nediyana Daskalova, Talie
Massachi, Alexandra Papoutsaki, my colleagues James Tompkin, Stephen
Bach, my teaching assistant Kathleen Chai, and my research assistant
Yusuf Karim for feedback on earlier drafts.
See discussions on [14]Hacker News and [15]reddit /r/programming
Also in this series
[16]Behind the scenes: the struggle for each paper to get published
[17]Illustrative notes for obsessing over publishing aesthetics
Other articles I've written
[18]My productivity app is a never-ending .txt file
[19]The Coronavirus pandemic has changed our sleep behavior
[20]Extracting data from tracking devices by going to the cloud
[21]CS Faculty Composition and Hiring Trends
[22]Bias in Computer Science Rankings
[23]Who Wins CS Best Paper Awards?
[24]Verified Computer Science Ph.D. Stipends
This page is [25]designed to last.
References
1. https://jeffhuang.com/
2. https://gomakethings.com/the-web-is-not-dying/
3. https://archivebox.io/
4. https://webmasters.stackexchange.com/questions/25315/hotlinking-what-is-it-and-why-shouldnt-people-do-it
5. https://goaccess.io/
6. https://systemfontstack.com/
7. https://victorzhou.com/blog/minify-svgs/
8. https://evilmartians.com/chronicles/images-done-right-web-graphics-good-to-the-last-byte-optimization-techniques
9. https://caniuse.com/#feat=webp
10. https://uptimerobot.com/
11. https://pg.ucsd.edu/publications/Python-Tutor-scalable-sustainable-research-software_UIST-2021.pdf
12. https://irchiver.com/
13. https://docs.google.com/forms/d/e/1FAIpQLSeTCgnwF1gjrc1O8mfJ_5TmT_TLowFQ2DUhsollmqPG84pAFQ/viewform?usp=pp_url&entry.1299571007=Irchiver:+browser+history+search&entry.1760653896=designed_to_last
14. https://news.ycombinator.com/item?id=21840140
15. https://www.reddit.com/r/programming/comments/ed88ra/this_page_is_designed_to_last_a_manifesto_for/
16. https://jeffhuang.com/struggle_for_each_paper/
17. https://jeffhuang.com/illustrative-notes-for-publishing-aesthetics/
18. https://jeffhuang.com/productivity_text_file/
19. https://jeffhuang.com/covid_sleep/
20. https://jeffhuang.com/extracting_data_from_tracking_devices/
21. https://jeffhuang.com/computer-science-open-data/#cs-faculty-composition-and-hiring-trends
22. https://jeffhuang.com/computer-science-open-data/#bias-in-computer-science-rankings
23. https://jeffhuang.com/computer-science-open-data/#who-wins-cs-best-paper-awards
24. https://jeffhuang.com/computer-science-open-data/#verified-computer-science-phd-stipends
25. http://jeffhuang.com/designed_to_last/

284
content/journal/dispatch-2-april-2023/www-viget-com-5w5oyj.txt
View File

@@ -1,284 +0,0 @@
Skip to Main Content
Viget
• Work
• Services
• Articles
• Careers
• Contact
• Open Menu
Navigation
Viget Close
• Practice
• Work
• Services
• Articles
We’re a full-service digital agency that’s been helping clients make lasting
change since 1999.
Contact Us
People
• Company
• Careers
• Code of Ethics
• Diversity & Inclusion
More
• Pointless Corp.
• Explorations
• Code at Viget
Featured
Read the Article: AI in Recruiting
Newsletter
AI in Recruiting
Read the Article: The Enduring Point of Pointless Corp
Article
The Enduring Point of Pointless Corp
The Enduring Point of Pointless Corp
[pointless-sticker-bear-article]
Brian Williams
Brian Williams, Co-Founder & CEO
Article Categories: #News & Culture, #Employee Engagement
Posted on March 24, 2023
•
Share
•
Share
•
Tweet
Pointless Corp. is the innovation lab at Viget, where we step away from client
work to make fun and useful things for everyone
“Neither pointless, nor a corporation” is how we describe Pointless Corp. here
at Viget. We founded Viget – an actual company – in 1999 during the original
dot com bubble to build web products for clients. Serving clients has always
been our purpose or … point, if you will. Over the decades, we’ve done just
that, completing thousands of projects for hundreds of clients. Never
forgetting that we exist to serve our clients has been key in our longevity.
About a decade in, we felt the urge to build and launch our own projects.
Pointless Corp became the internal brand we adopted to remind ourselves that
these projects can be fun and useful but don’t replace the primary point of
Viget. A line from Harry Nilsson’s The Point! referencing the Pointless Man
serves as inspiration: “a point in every direction is the same as no point at
all.” We wanted the freedom to experiment in every direction.
So we did. Ideas and teams formed fairly randomly, and Pointless Projects began
to fill the gaps between our client work. Projects like HeyCraig (2009), which
sent you an email alert based on your Craigslist search (before Craigslist shut
us down and added the feature). Or Tincan’d (2011), a simple video call
platform before Zoom or Google Meet. Or BabyBookie, the baby due date office
pool app over 500,000 people have used since launch in 2012.
These projects allow our teams to work without the input (including, ahem,
revenue) of clients, so we’re more free to experiment, wear different hats, and
learn … a lot. We apply what we learn back into our client work. Along the way,
we get to know each other better, scratch our entrepreneurial itches, and
hopefully put some fun and/or useful things out in the world for others to
enjoy.
For many years, we organized an annual optional Pointless Weekend. We’d kick
off hackathon-style on a Thursday evening and wrap on a Saturday evening with a
functional product out in the wild, as I described back in 2012. It’s always
been an intense, enjoyable, but rather exhausting 48 hours. Photos from 2011,
2014, and 2016 bring back some great memories.
Photos of Pointless Weekend 2014
Pointless Weekend 2014 spanned three Viget offices
A couple of years ago, we shifted the schedule to start on Wednesday and wrap
on Friday. This made participation easier, allowing parents and others with
weekend commitments to join. It also allowed projects to wrap up just in time
for our Friday staff meeting. We awkwardly called it “Pointless Week” even
though it was still only two days.
New for 2023: Pointless Palooza
Two things I like: alliteration and lollapalooza (specifically circa 1992, but
that’s a story for another day). So Pointless Palooza was an obvious choice for
what to call our little two day adventure. In addition to a new name, we’re
trying a few other changes this year:
Pointless Executives. Nothing injects new energy like new leadership. We handed
over the Pointless reins to two trusty execs: Andrew (day job: developer) is
our Pointless CEO and Aimee (day job: project manager) is our Pointless COO.
They’ve done a phenomenal job setting a vision, planning, and leading the
activities. Their enthusiasm helped inspire more than half the company to
participate with a record number of projects and great results.
Pitching & Team Formation. Previously, project ideas were “pitched” with a
single slide and a tight 1-2 minute segment at a staff meeting. These were fun
and lighthearted, but didn’t always capture the full vision, and teams often
formed and morphed during the kickoff night. This year, project ideas were
shared more gradually via collaboration in Slack and Notion. Project teams
formed with more structure in advance, and team members had some time before
the kickoff to marinate on the idea and get excited to build.
Even More Remote Friendly. There’s something magical about kickoff-pizza,
launch day donuts, and in-person collaboration. But there’s something even more
magical about collaborating with dozens of teammates around the country
(especially when it’s supplemented by sweet swag boxes and Divvy credits for
remote treats). Hybrid teams work. We still had fun in-office connections, but
most of our Pointless Projects this year are being worked on with distributed
teams, much like our client work.
Photo of Pointless Branded Stuff 2023
Pointless Branded Stuff 2023 including a t-shirt and sticker pack -- very
corporate
Some things haven’t changed from prior years. Team members are still swapping
roles – PMs writing code, designers running projects, the list goes on – which
means steep and rapid learning curves. We’re still trying out new technologies
and approaches to our work, which means unexpected blockers and great insights
to share. New connections are being formed, especially since more than half of
this year’s participants are in their first year at Viget and experiencing
their first Pointless event. Forming authentic co-worker connections isn’t
easy, and our culture is stronger today than it was at the start of the week.
So what projects will launch? I won’t steal their thunder, but we just wrapped
the presentation portion of six Pointless Project teams at our weekly staff
meeting and it was the most we’ve laughed, cheered, and been inspired in a long
time. I expect articles will be written and shared in the days and weeks ahead
outlining the thrills (and mishaps) of the teams this year.
Photos of Pointless Palooza 2023
Pointless Palooza 2023 was a blast!
Pointless Corp. is more than an annual palooza. We work on projects throughout
the year in the gaps between client work, weaving the teamwork, learning, and
teaching values of Viget into all that we do.
If this is the kind of work and culture you might enjoy, learn more about our
culture and job openings – perhaps you’ll be able to join next year’s Pointless
Palooza. After all, inspiring people to join us is unapologetically part of the
point.
Brian Williams
Brian is Viget's co-founder and CEO. He does everything from advising our
clients to building our conference tables with his bare hands in our Falls
Church, VA, HQ.
More articles by Brian
Related Articles
•
Article
Our Pointless Logo
Brian Williams
•
Article
Introducing Pointless Corp.
Brian Williams
•
What’s the Point of Pointless Weekend?
Article
What’s the Point of Pointless Weekend?
Brian Williams
The Viget Newsletter
Nobody likes popups, so we waited until now to recommend our newsletter,
featuring thoughts, opinions, and tools for building a better digital world.
Read the current issue.
Subscribe Here (opens in new window)
Site Footer
Have an unsolvable problem or audacious idea?
Let’s get to work
Contact Us hello@viget.com 703.891.0670
• Practice
• Work
• Services
• Articles
• People
• Company
• Careers
• Code of Ethics
• Diversity & Inclusion
• More
• Pointless Corp.
• Explorations
• Code at Viget
Sign Up For Our Newsletter
A curated periodical featuring thoughts, opinions, and tools for building a
better digital world.
Check it out
Social Links
Viget
•
•
•
•
•
•
Office Locations
• Washington DC Metro
• Durham, NC
• Boulder, CO
• Chattanooga, TN
© 1999 – 2023 Viget Labs, LLC. Terms Privacy MRF
• Home
• Articles
• The Enduring Point of Pointless Corp
Subscribe (opens in a new window)
Share
• Share this page
• Share this page
• Tweet this page
Edit Entry

367
content/journal/dispatch-2-april-2023/www-viget-com-97ckk4.txt Normal file
View File

@@ -0,0 +1,367 @@
#[1]Viget Articles
IFRAME: [2]https://www.googletagmanager.com/ns.html?id=GTM-5V7V
[3]Skip to Main Content
[4]Viget
* [5]Work
* [6]Services
* [7]Articles
* [8]Careers
* [9]Contact
* (BUTTON) Open Menu
Navigation
[10]Viget (BUTTON) Close
* Practice
* [11]Work
* [12]Services
* [13]Articles
We’re a full-service digital agency that’s been helping clients make
lasting change since 1999.
[14]Contact Us
People
* [15]Company
* [16]Careers
* [17]Code of Ethics
* [18]Diversity & Inclusion
More
* [19]Pointless Corp.
* [20]Explorations
* [21]Code at Viget
Featured
Read the Article: AI in Recruiting
Newsletter
AI in Recruiting
Read the Article: The Enduring Point of Pointless Corp
Article
The Enduring Point of Pointless Corp
The Enduring Point of Pointless Corp
[22]Brian Williams
[23]Brian Williams, Co-Founder & CEO
Article Categories: [24]#News & Culture, [25]#Employee Engagement
Posted on March 24, 2023
* Share
* Share
* Tweet
Pointless Corp. is the innovation lab at Viget, where we step away from
client work to make fun and useful things for everyone
“Neither pointless, nor a corporation” is how we describe Pointless
Corp. here at Viget. We founded Viget – an actual company – in 1999
during the original dot com bubble to build web products for clients.
Serving clients has always been our purpose or … point, if you will.
Over the decades, we’ve done just that, completing thousands of
projects for hundreds of clients. Never forgetting that we exist to
serve our clients has been key in our longevity.
About a decade in, we felt the urge to build and launch our own
projects. [26]Pointless Corp became the internal [27]brand we adopted
to remind ourselves that these projects can be fun and useful but don’t
replace the primary point of Viget. A line from Harry Nilsson’s The
Point! referencing the Pointless Man serves as inspiration: “a point in
every direction is the same as no point at all.” We wanted the freedom
to experiment in every direction.
So we did. Ideas and teams formed fairly randomly, and Pointless
Projects began to fill the gaps between our client work. Projects like
[28]HeyCraig (2009), which sent you an email alert based on your
Craigslist search (before Craigslist shut us down and added the
feature). Or [29]Tincan’d (2011), a simple video call platform before
Zoom or Google Meet. Or [30]BabyBookie, the baby due date office pool
app over 500,000 people have used since launch in 2012.
These projects allow our teams to work without the input (including,
ahem, revenue) of clients, so we’re more free to experiment, wear
different hats, and learn … a lot. We apply what we learn back into our
client work. Along the way, we get to know each other better, scratch
our entrepreneurial itches, and hopefully put some fun and/or useful
things out in the world for others to enjoy.
For many years, we organized an annual optional Pointless Weekend. We’d
kick off hackathon-style on a Thursday evening and wrap on a Saturday
evening with a functional product out in the wild, as I described
[31]back in 2012. It’s [32]always been an intense, enjoyable, but
rather exhausting 48 hours. Photos from [33]2011, [34]2014, and
[35]2016 bring back some great memories.
Photos of Pointless Weekend 2014
Pointless Weekend 2014 spanned three Viget offices
A couple of years ago, we shifted the schedule to start on Wednesday
and wrap on Friday. This made participation easier, allowing parents
and others with weekend commitments to join. It also allowed projects
to wrap up just in time for our Friday staff meeting. We awkwardly
called it “Pointless Week” even though it was still only two days.
New for 2023: Pointless Palooza
Two things I like: alliteration and lollapalooza (specifically circa
1992, but that’s a story for another day). So Pointless Palooza was an
obvious choice for what to call our little two day adventure. In
addition to a new name, we’re trying a few other changes this year:
Pointless Executives. Nothing injects new energy like new leadership.
We handed over the Pointless reins to two trusty execs: [36]Andrew (day
job: developer) is our Pointless CEO and [37]Aimee (day job: project
manager) is our Pointless COO. They’ve done a phenomenal job setting a
vision, planning, and leading the activities. Their enthusiasm helped
inspire more than half the company to participate with a record number
of projects and great results.
Pitching & Team Formation. Previously, project ideas were “pitched”
with a single slide and a tight 1-2 minute segment at a staff meeting.
These were fun and lighthearted, but didn’t always capture the full
vision, and teams often formed and morphed during the kickoff night.
This year, project ideas were shared more gradually via collaboration
in Slack and Notion. Project teams formed with more structure in
advance, and team members had some time before the kickoff to marinate
on the idea and get excited to build.
Even More Remote Friendly. There’s something magical about
kickoff-pizza, launch day donuts, and [38]in-person collaboration. But
there’s something even more magical about collaborating with dozens of
teammates around the country (especially when it’s supplemented by
[39]sweet swag boxes and Divvy credits for remote treats). Hybrid teams
work. We still had fun in-office connections, but most of our Pointless
Projects this year are being worked on with distributed teams, much
like our client work.
Photo of Pointless Branded Stuff 2023
Pointless Branded Stuff 2023 including a t-shirt and sticker pack --
very corporate
Some things haven’t changed from prior years. Team members are still
swapping roles – PMs writing code, designers running projects, the list
goes on – which means steep and rapid [40]learning curves. We’re still
trying out new technologies and approaches to our work, which means
unexpected blockers and great insights to share. New connections are
being formed, especially since more than half of this year’s
participants are in their first year at Viget and experiencing their
first Pointless event. Forming authentic co-worker connections isn’t
easy, and our culture is stronger today than it was at the start of the
week.
So what projects will launch? I won’t steal their thunder, but we just
wrapped the presentation portion of six Pointless Project teams at our
weekly staff meeting and it was the most we’ve laughed, cheered, and
been inspired in a long time. I expect articles will be written and
shared in the days and weeks ahead outlining the thrills (and mishaps)
of the teams this year.
Photos of Pointless Palooza 2023
Pointless Palooza 2023 was a blast!
Pointless Corp. is more than an annual palooza. We work on projects
throughout the year in the gaps between client work, weaving the
teamwork, learning, and teaching values of Viget into all that we do.
If this is the kind of work and culture you might enjoy, learn more
about [41]our culture and job openings – perhaps you’ll be able to join
next year’s Pointless Palooza. After all, inspiring people to join us
is unapologetically part of the point.
[42]Brian Williams
[43]Brian is Viget's co-founder and CEO. He does everything from
advising our clients to building our conference tables with his bare
hands in our Falls Church, VA, HQ.
[44]More articles by Brian
Related Articles
* Article
Our Pointless Logo
Brian Williams
* Article
Introducing Pointless Corp.
Brian Williams
* What’s the Point of Pointless Weekend?
Article
What’s the Point of Pointless Weekend?
Brian Williams
The Viget Newsletter
Nobody likes popups, so we waited until now to recommend our
newsletter, featuring thoughts, opinions, and tools for building a
better digital world. [45]Read the current issue.
[46]Subscribe Here (opens in new window)
Site Footer
Have an unsolvable problem or audacious idea?
Let’s get to work
[47]Contact Us [48]hello@viget.com [49]703.891.0670
* Practice
* [50]Work
* [51]Services
* [52]Articles
* People
* [53]Company
* [54]Careers
* [55]Code of Ethics
* [56]Diversity & Inclusion
* More
* [57]Pointless Corp.
* [58]Explorations
* [59]Code at Viget
Sign Up For Our Newsletter
A curated periodical featuring thoughts, opinions, and tools for
building a better digital world.
[60]Check it out
Social Links
[61]Viget
*
*
*
*
*
*
Office Locations
* [62]Washington DC Metro
* [63]Durham, NC
* [64]Boulder, CO
* [65]Chattanooga, TN
© 1999 – 2023 Viget Labs, LLC. [66]Terms [67]Privacy [68]MRF
* [69]Home
* [70]Articles
* [71]The Enduring Point of Pointless Corp
[72]Subscribe (opens in a new window)
(BUTTON) Share
* [73]Share this page
* [74]Share this page
* [75]Tweet this page
[76]Edit Entry
References
Visible links:
1. https://feeds.feedburner.com/Viget
2. https://www.googletagmanager.com/ns.html?id=GTM-5V7V
3. https://www.viget.com/articles/the-enduring-point-of-pointless-corp/#content
4. https://www.viget.com/
5. https://www.viget.com/work/
6. https://www.viget.com/services/
7. https://www.viget.com/articles/
8. https://www.viget.com/careers/
9. https://www.viget.com/contact/
10. https://www.viget.com/
11. https://www.viget.com/work/
12. https://www.viget.com/services/
13. https://www.viget.com/articles/
14. https://www.viget.com/contact/
15. https://www.viget.com/about/
16. https://www.viget.com/careers/
17. https://www.viget.com/code-of-ethics/
18. https://www.viget.com/diversity-equity-and-inclusion/
19. https://pointlesscorp.com/
20. https://explorations.viget.com/
21. https://code.viget.com/
22. https://www.viget.com/about/team/bwilliams/
23. https://www.viget.com/about/team/bwilliams/
24. https://www.viget.com/articles/category/news-culture/
25. https://www.viget.com/articles/category/employee-engagement/
26. https://www.viget.com/articles/the-point-of-pointless-corp/
27. https://www.viget.com/articles/book-review-giveaway-the-geometry-of-design/
28. https://www.viget.com/articles/introducing-heycraig/
29. https://pointlesscorp.com/tincand
30. https://www.babybookie.com/
31. https://www.viget.com/articles/a-pointless-weekend-or-so/
32. https://www.viget.com/articles/whats-the-point-of-pointless-weekend/
33. https://www.flickr.com/photos/viget/albums/72157626084778456
34. https://www.flickr.com/photos/viget/albums/72157649003978349
35. https://twitter.com/viget/status/798273078132408320
36. https://www.viget.com/about/team/athomas/
37. https://www.viget.com/about/team/aiwamoto/
38. https://twitter.com/pointlesscorp/status/1639274400976445444
39. https://twitter.com/viget/status/1637891007868968980
40. https://twitter.com/pointlesscorp/status/1638940667060838401
41. https://www.viget.com/careers/
42. https://www.viget.com/about/team/bwilliams/
43. https://www.viget.com/about/team/bwilliams/
44. https://www.viget.com/about/team/bwilliams/
45. https://www.viget.com/newsletter
46. http://eepurl.com/gtHqsj
47. https://www.viget.com/contact/
48. mailto:hello@viget.com?subject=Hello, Viget!
49. tel:7038910670
50. https://www.viget.com/work/
51. https://www.viget.com/services/
52. https://www.viget.com/articles/
53. https://www.viget.com/about/
54. https://www.viget.com/careers/
55. https://www.viget.com/code-of-ethics/
56. https://www.viget.com/diversity-equity-and-inclusion/
57. https://pointlesscorp.com/
58. https://explorations.viget.com/
59. https://code.viget.com/
60. https://www.viget.com/newsletter/
61. https://www.viget.com/
62. https://www.viget.com/dc-metro-hq/
63. https://www.viget.com/durham/
64. https://www.viget.com/boulder/
65. https://www.viget.com/chattanooga/
66. https://www.viget.com/terms-conditions/
67. https://www.viget.com/privacy-policy/
68. https://individual.carefirst.com/individuals-families/mandates-policies/machine-readable-file.page
69. https://www.viget.com/
70. https://www.viget.com/articles
71. https://www.viget.com/articles/the-enduring-point-of-pointless-corp/#hero
72. http://eepurl.com/gtHqsj
73. https://www.facebook.com/sharer/sharer.php?u=https://www.viget.com/articles/the-enduring-point-of-pointless-corp/
74. http://www.linkedin.com/shareArticle?mini=true&url=https://www.viget.com/articles/the-enduring-point-of-pointless-corp/
75. https://twitter.com/intent/tweet?text=Pointless Corp. is the innovation lab at Viget, where we step away from client work to make fun and useful things for everyone https://www.viget.com/articles/the-enduring-point-of-pointless-corp/
76. https://www.viget.com/admin/entries/article/456611-the-enduring-point-of-pointless-corp
Hidden links:
78. https://www.viget.com/newsletter/ai-in-recruiting/
79. https://www.viget.com/articles/the-enduring-point-of-pointless-corp/
80. https://www.facebook.com/sharer/sharer.php?u=https%3A%2F%2Fwww.viget.com%2Farticles%2Fthe-enduring-point-of-pointless-corp%2F
81. http://www.linkedin.com/shareArticle?mini=true&url=https%3A%2F%2Fwww.viget.com%2Farticles%2Fthe-enduring-point-of-pointless-corp%2F
82. https://twitter.com/intent/tweet?text=Pointless%20Corp.%20is%20the%20innovation%20lab%20at%20Viget%2C%20where%20we%20step%20away%20from%20client%20work%20to%20make%20fun%20and%20useful%20things%20for%20everyone%20https%3A%2F%2Fwww.viget.com%2Farticles%2Fthe-enduring-point-of-pointless-corp%2F
83. https://www.viget.com/articles/our-pointless-logo/
84. https://www.viget.com/articles/introducing-pointless-corp/
85. https://www.viget.com/articles/whats-the-point-of-pointless-weekend/
86. https://twitter.com/viget
87. https://github.com/vigetlabs
88. https://dribbble.com/viget
89. https://www.instagram.com/viget/
90. https://www.linkedin.com/company/viget-labs
91. https://vimeo.com/viget/collections