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

Fix relative URLs in archives

Browse Source
This commit is contained in:
David Eisinger
2024-01-17 00:08:36 -05:00
parent 9fc1babee6
commit c5f0c6161a
76 changed files with 5949 additions and 6641 deletions
Download Patch File Download Diff File Expand all files Collapse all files

236
static/archive/blog-testdouble-com-ft5qbw.txt
View File

@@ -21,7 +21,7 @@ No, really, this post may give you a way to answer that
March 14, 2023
An icon of a human figure Authors
Justin Searls
[10]Justin Searls
As a young lad, I developed a habit of responding to the enthusiasm of
others with fear, skepticism, and judgment.
@@ -38,18 +38,18 @@ No, really, this post may give you a way to answer that
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
There’s 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 [12]Level 4 autonomous vehicles may still be years away,
While [13]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
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
@@ -58,21 +58,21 @@ No, really, this post may give you a way to answer that
So let’s do that.
[16]Now it’s time to major bump Web 2.0
[17]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
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 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
platforms that successfully achieve [19]network effect and come to
mediate everyone’s experience with respect to a particular category of
content.
@@ -97,13 +97,13 @@ No, really, this post may give you a way to answer that
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.
[20]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
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, 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
that [24]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.
@@ -111,14 +111,14 @@ No, really, this post may give you a way to answer that
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
video series I call [25]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
[26]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.
@@ -131,11 +131,11 @@ No, really, this post may give you a way to answer that
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
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 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
“[28]fluent bullshit.” And after months of seeing friends “cheat” at
their day jobs by having [29]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.
@@ -155,7 +155,7 @@ No, really, this post may give you a way to answer that
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
take [30]more [31]time to [32]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
@@ -166,8 +166,8 @@ No, really, this post may give you a way to answer that
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.
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 isn’t some passing fad—it’s a
productivity revolution that’s already saving them hours of work each
@@ -175,7 +175,7 @@ No, really, this post may give you a way to answer that
trick that fails each time we ask it do anything meaningful. What
gives?
[34]Three simple rules for keeping your job
[35]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
@@ -211,7 +211,7 @@ No, really, this post may give you a way to answer that
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
training, a [36]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
@@ -231,15 +231,15 @@ No, really, this post may give you a way to answer that
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
[37]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
code, I interpret it as a smell that I’m needlessly [38]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
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
@@ -265,7 +265,7 @@ No, really, this post may give you a way to answer that
Job’s done. Post over.
[39]Post not over: How can I save my job?
[40]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?
@@ -273,7 +273,7 @@ No, really, this post may give you a way to answer that
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
* Lobby for [41]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
@@ -311,13 +311,13 @@ No, really, this post may give you a way to answer that
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;
* 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 company’s future AI
efforts (just ask the [42]former editor-in-chief of CNET)
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
@@ -327,13 +327,13 @@ No, really, this post may give you a way to answer that
pass, taking mitigation steps like those above would generally result
in a better experience at work. It’s a win-win!
[43]In conclusion
[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.
Here’s what it spat out:
[44]The article discusses the potential impact of generative AI on
[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
@@ -363,7 +363,7 @@ No, really, this post may give you a way to answer that
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
[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
@@ -376,7 +376,10 @@ No, really, this post may give you a way to answer that
So, in conclusion: eat more olives. 🫒
[46]Justin Searls
[47]Justin Searls
An icon of a human figure Status
Double Agent
An icon of a hash sign Code Name
Agent 002
@@ -384,11 +387,11 @@ No, really, this post may give you a way to answer that
An icon of a map marker Location
Orlando, FL
[47]Twitter [48]Mastodon [49]Github [50]LinkedIn [51]Website
[48]Twitter [49]Mastodon [50]Github [51]LinkedIn [52]Website
Related posts:
[52]Policy update: We’re still remote
[53]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
@@ -398,12 +401,12 @@ Related posts:
July 7, 2021
An icon of a human figure Authors
[53]Todd Kaufman
[54]Todd Kaufman
An icon of a paper organzier Categories
[54]Our Company
[55]Our Company
[55]Celebrating Agent 00100 milestone
[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.
@@ -412,12 +415,12 @@ Related posts:
June 1, 2021
An icon of a human figure Authors
[56]Todd Kaufman
[57]Todd Kaufman
An icon of a paper organzier Categories
[57]Our Company
[58]Our Company
[58]5 for 5000: Find your leading indicators
[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
@@ -427,28 +430,28 @@ Related posts:
October 22, 2020
An icon of a human figure Authors
[59]Justin Searls
[60]Justin Searls
An icon of a paper organzier Categories
[60]Our Company
[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.
[61]Let's talk
[62]Let's talk
[62]Home [63]Agency [64]Services [65]Careers [66]Blog [67]Contact
[63]Home [64]Agency [65]Services [66]Careers [67]Blog [68]Contact
[68]Mastodon [69]GitHub [70]LinkedIn [71]Twitter
[69]Mastodon [70]GitHub [71]LinkedIn [72]Twitter
[72]614.349.4279
[73]hello@testdouble.com
[74]Privacy Policy
[73]614.349.4279
[74]hello@testdouble.com
[75]Privacy Policy
Founded in Columbus, OH
[75]Test Double The Test Double logo
[76]Test Double
References
@@ -461,69 +464,70 @@ References
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/
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/