Files
davideisinger.com/static/archive/blog-testdouble-com-ft5qbw.txt
2024-01-17 00:10:00 -05:00

534 lines
27 KiB
Plaintext
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
[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
[10]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 theres one trend people are excited about that—try as I might—Im
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.
Theres little doubt at this point: the tools that succeed [11]DALL•E
and [12]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 [13]Level 4 autonomous vehicles may still be years away,
production-ready AI is here today. Its already being used to do
significant amounts of paid work, often with employers being none the
wiser.
If truckers deserve [14]years [15]of [16]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 thats coming for the information
economy.
So lets do that.
[17]Now its time to major bump Web 2.0
Computer-generated content wouldnt 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 [18]Wisdom of the
Crowd. The theory was simple: if anyone could publish content to a
platform, then users could rank that contents 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 [19]network effect and come to
mediate everyones 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 Ive 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 2.0s 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 were witnessing the first act of Web
3.0, its got nothing to do with crypto and everything to do with
[20]generative AI.
If youre reading this, you dont need me to recap the cultural impact
of [21]ChatGPT and [22]Bing Chat for you. Suffice to say, if Google—the
runaway winner of the Web 2.0 economy—is [23]legit shook, theres
probably fire to go with all this smoke. Moreover, when you consider
that [24]the same incumbent is already at the forefront of AI
innovation but is nevertheless terrified by this sea change, Google
clearly believes were witnessing a major market disruption in addition
to a technological one.
One reason Ive been thinking so much about this is that Ive started
work on a personal project to build an AI chatbot for practicing
Japanese language and Im livecoding 100% of my work for an educational
video series I call [25]Searls After Dark. Might be why Ive got AI on
the mind lately!
But youre not a tech giant. Youre wondering what this means for you
and your weekend. And I think were beginning to identify the contours
of an answer to that question.
[26]ChatGPT can do some peoples work, but not everyones
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 wont 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 [27]GitHub Copilot, weeks talking
to ChatGPT, and days searching via Bing Chat as an alternative to
Google, the best description Ive heard of AIs capabilities is
“[28]fluent bullshit.” And after months of seeing friends “cheat” at
their day jobs by having [29]ChatGPT do their homework for them, Ive
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 teams issue tracker
* Optimizing the performance of SQL queries and algorithms
* Completing employees performance reviews
Each time Id hear something like this, Id get jealous, open ChatGPT
for myself, and feed it whatever problem I was working on. It never
worked. Sometimes itd give up and claim the thing I was trying to do
was too obscure. Sometimes itd generate a superficially realistic
response, but always with just enough nonsense mixed in that it would
take [30]more [31]time to [32]edit than to rewrite from scratch. But
most often, Id 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 [33]I recorded my screen and set it to a few lofi
tracks before [34]giving up.
For many of my friends, ChatGPT isnt some passing fad—its a
productivity revolution thats 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?
[35]Three simple rules for keeping your job
Ive 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 doesnt 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 ChatGPTs effectiveness at doing their work. But I can identify
just as many roles that sit near the bottom of the org chart, dont
require special credentials, and dont pay particularly well for which
ChatGPT isnt even remotely useful.
Heres 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 solutions format
and structure based solely on a description of the problem
3. Fragile: Minor errors and inaccuracies would dramatically reduce
the works 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 [36]stochastic AI could predictably fill in the blanks
of a travelers 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 theres 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 Ive
thrown at it. As an experienced application developer, lets consider
whether thats because my work meets the three criteria identified
above:
1. Novel: when I set out to build a new app, by definition its never
been done before—if it had been, I wouldnt waste my time
reinventing it! That means there wont 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
[37]DRY, there just isnt 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 Im needlessly [38]reinventing
a wheel)
2. Unpredictable: Ive been building apps for over 20 years and I
still feel a prick of panic I wont 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 “[39]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 isnt 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
cant do (yet).
So if youre a programmer like me, youre probably safe!
Jobs done. Post over.
[40]Post not over: How can I save my job?
So what can someone do if their primary role doesnt produce work that
checks the three boxes of novelty, unpredictability, and fragility?
Here are a few ideas that probably wont work:
* Ask major tech companies to kindly put this genie back into the
bottle
* Lobby for [41]humane policies to prepare for a world that doesnt
need every humans labor
* Embrace return-to-office mandates by doing stuff software cant 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 its 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, heres
what Id 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 isnt very good at. The robots
probably arent 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 weve 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 [42]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 companys future AI
efforts (just ask the [43]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. Its a win-win!
[44]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.
Heres what it spat out:
[45]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 cant 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:
[46]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. 🫒
[47]Justin Searls
An icon of a human figure Status
Double Agent
An icon of a hash sign Code Name
Agent 002
An icon of a map marker Location
Orlando, FL
[48]Twitter [49]Mastodon [50]Github [51]LinkedIn [52]Website
Related posts:
[53]Policy update: Were still remote
Dont 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
[54]Todd Kaufman
An icon of a paper organzier Categories
[55]Our Company
[56]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
[57]Todd Kaufman
An icon of a paper organzier Categories
[58]Our Company
[59]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
[60]Justin Searls
An icon of a paper organzier Categories
[61]Our Company
Looking for developers? Work with people who care about what you care about.
We level up teams striving to ship great code.
[62]Let's talk
[63]Home [64]Agency [65]Services [66]Careers [67]Blog [68]Contact
[69]Mastodon [70]GitHub [71]LinkedIn [72]Twitter
[73]614.349.4279
[74]hello@testdouble.com
[75]Privacy Policy
Founded in Columbus, OH
[76]Test Double
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://blog.testdouble.com/authors/justin-searls/
11. https://openai.com/product/dall-e-2
12. https://openai.com/blog/chatgpt
13. https://en.wikipedia.org/wiki/Self-driving_car
14. https://www.automotivelogistics.media/transition-to-automated-trucks-must-be-managed-warn-trade-bodies/18446.article
15. https://www.nytimes.com/2017/08/11/business/dealbook/teamsters-union-tries-to-slow-self-driving-truck-push.html
16. https://www.nbcnews.com/business/autos/millions-professional-drivers-will-be-replaced-self-driving-vehicles-n817356
17. https://blog.testdouble.com/posts/2023-03-14-how-to-tell-if-ai-threatens-your-job/#_now_-its-time-to-major-bump-web-20
18. https://en.wikipedia.org/wiki/Wisdom_of_the_crowd
19. https://en.wikipedia.org/wiki/Network_effect
20. https://en.wikipedia.org/wiki/Generative_adversarial_network
21. https://www.theverge.com/2022/12/8/23499728/ai-capability-accessibility-chatgpt-stable-diffusion-commercialization
22. https://www.theverge.com/2023/2/15/23599072/microsoft-ai-bing-personality-conversations-spy-employees-webcams
23. https://www.theverge.com/2023/1/20/23563851/google-search-ai-chatbot-demo-chatgpt
24. https://www.theverge.com/2021/5/18/22442328/google-io-2021-ai-language-model-lamda-pluto
25. https://www.youtube.com/playlist?list=PLIuJbrOVyGjkRj7UM_whr-CPoqcXTOsZa
26. 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
27. https://github.com/features/copilot
28. https://www.theverge.com/2022/12/5/23493932/chatgpt-ai-generated-answers-temporarily-banned-stack-overflow-llms-dangers
29. https://www.npr.org/2022/12/19/1143912956/chatgpt-ai-chatbot-homework-academia
30. https://cdn-blog.testdouble.com/img/how-to-tell-if-ai-threatens-your-job/bing-1.ebd5fca31dbdd729c4dcc7388630e69f6d26b128d967b20a38c41409b7ee0099.png
31. https://cdn-blog.testdouble.com/img/how-to-tell-if-ai-threatens-your-job/bing-2.c1830c7fb3f4634158a9fffc0ccac3396f09619761d7ccd2218ce9b77d19b826.png
32. https://cdn-blog.testdouble.com/img/how-to-tell-if-ai-threatens-your-job/bing-3.a2922e3b785ab4216bb01299f118c55a7cd2b43a82db909f66bdc9c83e956fe6.png
33. https://www.youtube.com/watch?v=gllCXqnR-5E
34. https://www.youtube.com/watch?v=gllCXqnR-5E&t=1004s
35. https://blog.testdouble.com/posts/2023-03-14-how-to-tell-if-ai-threatens-your-job/#three-simple-rules-for-keeping-your-job
36. https://en.wikipedia.org/wiki/Artificial_neural_network#Stochastic_neural_network
37. https://en.wikipedia.org/wiki/Don't_repeat_yourself
38. https://en.wikipedia.org/wiki/Reinventing_the_wheel
39. https://en.wikipedia.org/wiki/Emergent_Design
40. 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
41. https://en.wikipedia.org/wiki/Universal_basic_income
42. https://en.wikipedia.org/wiki/Fight-or-flight_response
43. https://www.theverge.com/2023/3/2/23622836/cnet-eic-takes-red-ventures-ai-content-job-connie-guglielmo
44. https://blog.testdouble.com/posts/2023-03-14-how-to-tell-if-ai-threatens-your-job/#in-conclusion
45. https://cdn-blog.testdouble.com/img/how-to-tell-if-ai-threatens-your-job/chat-gpt-1.be7ef1f6a65dabe7f2ee88e296ff404980183879a0a79f88537affe6a44f17e3.png
46. https://cdn-blog.testdouble.com/img/how-to-tell-if-ai-threatens-your-job/chat-gpt-2.ccd08019b5f629691f6f09f5e4118186dc3d3001d712449034804f9a8ffde7c3.png
47. https://blog.testdouble.com/authors/justin-searls/
48. https://twitter.com/searls
49. https://mastodon.social/@searls
50. https://github.com/searls
51. https://linkedin.com/in/searls
52. https://justin.searls.co/
53. https://blog.testdouble.com/posts/2021-07-07-policy-update-were-still-remote/
54. https://blog.testdouble.com/authors/todd-kaufman/
55. https://blog.testdouble.com/categories/our-company
56. https://blog.testdouble.com/posts/2021-06-01-celebrating-agent-0100-milestone/
57. https://blog.testdouble.com/authors/todd-kaufman/
58. https://blog.testdouble.com/categories/our-company
59. https://blog.testdouble.com/posts/2020-10-22-5-for-5000-find-your-leading-indicators/
60. https://blog.testdouble.com/authors/justin-searls/
61. https://blog.testdouble.com/categories/our-company
62. https://link.testdouble.com/blog-cta-sales
63. https://testdouble.com/
64. https://testdouble.com/agency
65. https://testdouble.com/services
66. https://testdouble.com/careers
67. https://blog.testdouble.com/
68. https://testdouble.com/contact
69. https://mastodon.social/@testdouble
70. https://github.com/testdouble
71. https://www.linkedin.com/company/testdouble
72. https://twitter.com/testdouble
73. tel:+16143494279
74. mailto:hello@testdouble.com
75. https://testdouble.com/privacy-policy
76. https://testdouble.com/