davideisinger.com/static/archive/www-citationneeded-news-4myqvd.txt

[1] [citation needed]
a newsletter by Molly White

  • [4]Archive
  • [5]Recap issues
  • [6]Podcast feed
  • [7]Follow the Crypto
  • [8]About
  • [9]RSS
  • [10]Tip jar
  • [11]Privacy policy

[13]Sign in [14]Subscribe

Sidenotes

[16][ ] Show footnotes
[17][ ] Show references
[18]( ) [19]( ) [20]( )
[21]( ) [22]( ) [23]( )
[24]Newsletter

AI isn't useless. But is it worth it?

AI can be kind of useful, but I'm not sure that a "kind of useful" tool
justifies the harm.

[25] Molly White

[26]Molly White

Apr 17, 2024 — 15 min read
AI isn't useless. But is it worth it?
audio-thumbnail
AI isn't useless. But is it worth it?
0:00
/1311.164082
[29][0                   ]1×[33][100                 ]
Listen to a voiceover of this post, [34]download the recording for later, or 
[35]subscribe to the feed in your podcast app.

As someone known for my criticism of the previous deeply flawed technology to
become the subject of the tech world's overinflated aspirations, I have had
people express surprise when I've remarked that generative artificial
intelligence tools^[36]a can be useful. In fact, I was a little surprised
myself.

But there is a yawning gap between "AI tools can be handy for some things" and
the kinds of stories AI companies are telling (and the media is uncritically
reprinting). And when it comes to the massively harmful ways in which large
language models (LLMs) are being developed and trained, the feeble argument
that "well, they can sometimes be handy..." doesn't offer much of a
justification.

Some are surprised when they discover I don't think blockchains are useless,
either. Like so many technologies, blockchains are designed to prioritize a few
specific characteristics (coordination among parties who don't trust one
another, censorship-resistance, etc.) at the expense of many others (speed,
cost, etc.). And as they became trendy, people often used them for purposes
where their characteristics weren't necessary — or were sometimes even unwanted
— and so they got all of the flaws with none of the benefits. The thing with
blockchains is that the things they are suited for are not things I personally
find to be terribly desirable, such as the massive casinos that have emerged
around gambling on token prices, or financial transactions that cannot be
reversed.

When I boil it down, I find my feelings about AI are actually pretty similar to
my feelings about blockchains: they do a poor job of much of what people try to
do with them, they can't do the things their creators claim they one day might,
and many of the things they are well suited to do may not be altogether that
beneficial. And while I do think that AI tools are more broadly useful than
blockchains, they also come with similarly monstrous costs.

[37]Subscribe

I've been slow to get around to writing about artificial intelligence in any
depth, mostly because I've been trying to take the time to interrogate my own
knee-jerk response to a clearly overhyped technology. After spending so much
time writing about a niche that's practically all hype with little practical
functionality, it's all too easy to look at such a frothy mania around a
different type of technology and assume it's all the same.

In the earliest months of the LLM mania, my ethical concerns about the tools
made me hesitant to try them at all. When my early tests were met with mediocre
to outright unhelpful results, I'll admit I was quick to internally dismiss the
technology as more or less useless. It takes time to experiment with these
models and learn how to prompt them to produce useful outputs,^[38]b and I just
didn't have that time then.^[39]c But as the hype around AI has grown, and with
it my desire to understand the space in more depth, I wanted to really
understand what these tools can do, to develop as strong an understanding as
possible of their potential capabilities as well as their limitations and
tradeoffs, to ensure my opinions are well-formed.

I, like many others who have experimented with or adopted these products, have
found that these tools actually can be pretty useful for some tasks. Though AI
companies are prone to making overblown promises that the tools will shortly be
able to replace your content writing team or generate feature-length films or
develop a video game from scratch, the reality is far more mundane: they are
handy in the same way that it might occasionally be useful to delegate some
tasks to an inexperienced and sometimes sloppy intern.

Still, I do think acknowledging the usefulness is important, while also holding
companies to account for their false or impossible promises, abusive labor
practices, and myriad other issues. When critics dismiss AI outright, I think
in many cases this weakens the criticism, as readers who have used and
benefited from AI tools think "wait, that's not been my experience at all".

Use cases

I've found AI tools to be useful to my writing, though not for the actual
writing bit. When I'm writing, I often find myself with a word on the "tip of
my tongue" (so to speak), and I've had more success with ChatGPT than with
Google for these circumstances — although I can usually find the word with
Google if I try hard enough.

[Screenshot-2024-04-16-at-4]User: What's a word for something that will not
affect the final outcome Assistant: Inconsequential

Like many people, I also find it challenging to proofread my own writing, and I
sometimes miss typos or weird grammar accidentally left in from changing a
sentence halfway through.

USER Please proofread the following text and point out any spelling or grammar
problems, typos, and other such issues. Do not change the tone of the writing
or try to adjust the reading level. Do not repeat the entire corrected text
back to me, simply identify with brief quotes of the flawed text where changes
need to be made. <document> Bitcoiners are all aflutter as the halving date
approaches in about a week. This is very exciting for them, because the past
three halvings look like they've precipitated major price increases
(particularly if you use a log scale, which bitcoiners love). Bitcoin prices in
linear scale (blue) and log scale (black) since 2010, with halvings marked by
the red lines (chart via Bitbo) The "halving" is the moment when bitcoin block
rewards that is, the amount of bitcoin issued as a reward to the miner for
successfully mining a block are reduced by half. This is a strategy to ensure
the total supply of bitcoin gradually tapers... RESPONSE Here are the spelling,
grammar, and typo issues I found in the text: 1. "kind of the thought process"
should be "kind of thought process" 2. "beliefs of guaranteed double-your-money
returns" should be "belief of guaranteed double-your-money returns" 3. "2024"
is used instead of "2023" in several places, likely typos: • "Notice of appeal
filed on April 11, 2024." • "Letter motion filed on April 8, 2024." • "Tweet by
Inner City Press, April 9, 2024." • "Tweet by Inner City Press, April 12,
2024." • "Order filed on April 8, 2024." 4. "Committee on Committee on Banking"
should be "Committee on Banking" 5. "consider proposals" should be "considers
proposals" 6. "BitBoy" Armstrong's name is inconsistently capitalized as
"Bitboy" in one instance 7. "coinflips" should be "coin flips" 8. There is an
inconsistency in the number of Web3 is Going Just Great entries between April 1
and April 12. The text states "11 entries" but only 7 are listed.Proofreading a
newsletter post with Anthropic's Claude model

LLMs are pretty decent at proofreading, and although they sometimes spit out a
few false positives, this example from proofreading my most recent recap issue
shows where it caught several mistakes (points 1, 2, 4, and 8; point 5 was also
a genuine error, but it was within a quote).

However, I don't think I need generative AI to do this, either. There are a lot
of proofreading tools^[40]d that work quite well, and, helpfully, don't invent
errors that weren't in the original text (as I've found the ChatGPT models are
particularly wont to do).

Coding has been the far more compelling use case for me. Copilot, Github's AI
coding assistant, integrates directly into VSCode and other [41]IDEs. I've also
played with using the more general models, like ChatGPT, for coding tasks. They
are certainly flawed — Copilot has an annoying habit of "hallucinating"
(fabricating) imports instead of deferring to VSCode's perfectly good non-AI
auto-import, for example — but in other cases they are genuinely helpful.

I've found these tools to be particularly good at simple tasks that would
normally pull me out of my workflow to consult documentation or StackOverflow,
like generating finicky CSS selectors or helping me craft database aggregation
operations. On at least one occasion, they've pointed me towards useful
functionality I never knew about and wouldn't even think to look up. They're
also great at saving you some typing by spitting out the kind of boilerplate-y
code you have to write for things like new unit tests.

The tools can also do the kind of simple, repetitive tasks I'd previously write
a quick script to do for me — or they can generate that quick script. For
example, here's me asking ChatGPT to write a quick Python script to turn my
blogroll OPML file into the JSON file I wanted while I was adding a [42]
blogroll page to my website:

Suggest some python code to turn an OPML file like this into a JSON file with
fields for "text", "xmlUrl", and "htmlUrl": <opml version="1.0"> <head> <title>
Feeds of molly.white5 tagged as Blogroll from Inoreader [https://
www.inoreader.com]</title> </head> <body> <outline text="Blogroll" title=
"Blogroll"> <outline text="Adactio" title="Adactio" type="rss" xmlUrl="https://
adactio.com/rss/" htmlUrl="https://adactio.com/"/> <outline text="Anil Dash"
title="Anil Dash" type="rss" xmlUrl="https://feeds.dashes.com/AnilDash" htmlUrl
="https://dashes.com/anil/"/> <outline text="Ben Werdmüller" title="Ben
Werdmüller" type="rss" xmlUrl="https://werd.io/?_t=rss" htmlUrl="https://
werd.io/"/> <outline text="Birch Tree" title="Birch Tree" type="rss" xmlUrl=
"https://birchtree.me/rss/" htmlUrl="https://birchtree.me/"/> <outline text=
"cabel.com" title="cabel.com" type="rss" xmlUrl="https://cabel.com/feed/"
htmlUrl="https://cabel.com"/>

After changing the feeds.opml file path to the location of the file on my
computer, the code it suggested worked without any modification:

ASSISTANT python import xml.etree.Element Tree as ET import json tree =
ET.parse('feeds.opml') root = tree.getroot() feeds = for outline in
root.findall('.//outline'): feed = { 'text': outline.attrib.get('text'),
'xmlUrl': outline.attrib.get('xmlUrl"), 'htmlUrl': outline.attrib.get
('htmlUrl') } feeds.append(feed) json_data = json.dumps(feeds, indent=4) with
open('feeds.json', 'w') as f: f.write(json_data) This code will read the OPML
file 'feeds.opml', extract the 'text', 'xmlUrl', and 'htmlUrl' attributes from
each outline element, and save the data into a JSON file 'feeds.json' with
proper indentation.

Besides my own experimentation, others are using these tools in ways that are
really hard to argue aren't useful. Someone I know in real life has told me
about creating a custom model based on their own emails, which they then query
as needed, or use to create some fairly boilerplate documents they previously
had to spend hours on. Open source developer Simon Willison has been
documenting his own AI coding experiments on his blog, and has described how
LLMs have [43]made him more ambitious with his projects and more likely to
embark on what he calls "[44]sidequests".^[45]e Sumana Harihareswara [46]uses
OpenAI's speech recognition tools to create subtitles for her videos and
recorded talks, or to "mine" them for material she can later reuse. Elsewhere
on the internet, those who speak English as a second language have spoken of
LLMs' usefulness in revising their professional communications. Others use it
to summarize meeting notes. Some use it as a starting point for documentation.

Reality check

Despite some unarguably useful features, the limitations of these tools make
themselves readily apparent.

When it comes to coding, while it can make for a handy assistant to an
experienced developer, it can't replace an experienced developer. Microsoft's 
[47]Super Bowl commercial, which shows a person prompting Copilot to "Write
code for my 3D open world game", is pure fantasy.

molly Write code for my 3D open world game GitHub Copilot Used 1 reference >
Sorry, but writing code for a 3D open world game is a complex task that
requires a lot of time and effort. It's not something that can be done in a
single response. However, I can help you get started by creating a basic
structure for a game using a game development framework like Unity or Unreal
Engine. Here's a simple example of a Unity script in C# that moves a game
object: using System.Collections; using System.Collections.Generic; using
UnityEngine; public class PlayerMovement: MonoBehaviour { public float speed =
10.0f; void Update() { float moveHorizontal = Input.GetAxis ("Horizontal");
float moveVertical = Input.GetAxis ("Vertical"); Vector3 movement = new Vector3
(moveHorizontal, 0.0f, moveVertical); transform.position = transform.position +
movement * speed * Time.de } } This script should be attached to the player
object. It takes input from the keyboard and moves the player object
accordingly. The speed variable can be adjusted to control how fast the player
moves.

And in my experience, it sometimes gets in the way more than it helps, as when
I experimented with it while working on a [48]Chrome extension I was writing
recently and ultimately had to turn it off. It constantly suggested plausible
but completely non-functional code, scaffolded the project in an outdated
format, and autogenerated CSS classes that looked like they could be Bootstrap
classes, but weren't. It's good at short functions and common boilerplate, but
it's not going to architect a project for you, and, as with writing, it's not
going to "think" of novel ideas. I like it for getting annoying, repetitive
tasks out of my way; I don't worry it's going to take my job.

Arguably the most widely-described use case for generative AI is writing.
Indeed, as media companies lay off journalists in droves, [49]some [50]outlets
are replacing their work with shoddy, AI-generated approximations. Freelance
writers are reporting challenges in finding work as their former clients decide
that ChatGPT can do a good enough job. But what these companies and clients
fail to recognize is that ChatGPT does not write, it generates text, and anyone
who's spotted obviously LLM-generated content in the wild immediately knows the
difference.

You've gotten this far into my article, so you're recently familiar with a
couple dozen paragraphs of purely human writing. Contrast that with LLMs'
attempts, from prompts with varying degrees of detail, with my very best
efforts put into trying to get it to sound halfway normal:

A table with a range of LLM prompts provided to three models: ChatGPT, Claude,
and Gemini([51]spreadsheet)

Yikes. I particularly like how, when I ask them to try to sound like me, or to
at least sound less like a chatbot, they adopt a sort of "cool teacher"
persona, as if they're sitting backwards on a chair to have a heart-to-heart.
Back when I used to wait tables, the other waitresses and I would joke to each
other about our "waitress voice", which were the personas we all subconsciously
seemed to slip into when talking to customers. They varied somewhat, but they
were all uniformly saccharine, with slightly higher-pitched voices, and with
the general demeanor as though you were talking to someone you didn't think was
very bright. Every LLM's writing "voice" reminds me of that.

Even if the telltale tone is surmountable, LLMs are good at generating text but
not at generating novel ideas. This is, of course, an inherent feature of
technology that's designed to generate plausible mathematical approximations of
what you've asked it for based on its large corpus of training data; it doesn't
think, and so the best you're ever going to get from it is some mashup of other
peoples' thinking.^[52]f

LLM-generated text is good enough for some use cases, which I'll return to in a
moment. But I think most people, myself certainly included, would be mortified
to replace any of our writing with this kind of stuff.^[53]g

Furthermore, LLMs' "hallucination" problem means that everything it does must
be carefully combed over for errors, which can sometimes be hard to spot.
Because of this, while it's handy for proofreading newsletters or helping me
quickly add a fun feature to my website, I wouldn't trust LLMs to do anything
of real import. And the tendency for people to put too much trust into these
tools^[54]h is among their most serious problems: no amount of warning labels
and disclaimers seem to be sufficient to stop people from trying to use them to
provide legal advice or sell AI "therapy" services.

Finally, advertisements that LLMs might someday generate feature-length films
or replace artists seem neither feasible nor desirable. AI-generated images
tend to suffer from a similar bland "tone" as its writing, and their
proliferation only makes me desire real human artwork more. With generated
video, they inevitably trend towards the uncanny, and the technology's inherent
limitations — as a tool that is probabilistically generating "likely" images
rather than ones based on some kind of understanding — seem unlikely to ever
overcome that. And the idea that we all should be striving to "replace artists"
— or any kind of labor — is deeply concerning, and I think incredibly
illustrative of the true desires of these companies: to increase corporate
profits at any cost.

When LLMs are good enough

As I mentioned before, there are some circumstances in which LLMs are good
enough. There are some types of writing where LLMs are already being widely
used: for example, by businesspeople who use them to generate meeting notes,
fluff up their outgoing emails or summarize their incoming ones, or spit out
lengthy, largely identical reports that they're required to write regularly.

You can also spot LLMs in all sorts of places on the internet, where they're
being used to try to boost websites' search engine rankings. That weird, bubbly
GPT voice is well suited to marketing copy and social media posts, too. Any
place on the web that incentivizes high-volume, low effort text is being
inundated by generated text, like e-book stores, online marketplaces, and
practically any review or comment section.

But I find one common thread among the things AI tools are particularly suited
to doing: do we even want to be doing these things? If all you want out of a
meeting is the AI-generated summary, maybe that meeting could've been an email.
If you're using AI to write your emails, and your recipient is using AI to read
them, could you maybe cut out the whole thing entirely? If mediocre,
auto-generated reports are passing muster, is anyone actually reading them? Or
is it just middle-management busywork?

As for the AI [55]enshittification of the internet, we all seem to agree
already that we don't want this, and yet here it is. No one wants to open up
Etsy to look for a thoughtful birthday gift, only to give up after scrolling
through pages of low-quality print-on-demand items or resold Aliexpress items
that have flooded the site.

[Screenshot-2024-04-13-at-5]
[Screenshot-2024-04-13-at-5]

Your AI model is showing

No one wants to Google search a question only to end up on several pages of
keyword-spam vomit before finding an authoritative answer.

But the incentives at play on these platforms, mean that AI junk is inevitable.
In fact, the LLMs may be new, but the behavior is not; just like [56]keyword
stuffing and [57]content farms and the myriad ways people used software to
generate reams upon reams of low-quality text before ChatGPT ever came on the
scene, if the incentive is there, the behavior will follow. If the internet's
enshittification feels worse post-ChatGPT, it's because of the quantity and
speed at which this junk is being produced, not because the junk is new.

Costs and benefits

Throughout all this exploration and experimentation I've felt a lingering
guilt, and a question: is this even worth it? And is it ethical for me to be
using these tools, even just to learn more about them in hopes of later
criticizing them more effectively?

The costs of these AI models are huge, and not just in terms of the billions of
dollars of VC funds they're burning through at incredible speed. These models
are well known to require far more computing power (and thus electricity and
water) than a traditional web search or spellcheck. Although AI company
datacenters are not intentionally wasting electricity in the same way that
bitcoin miners perform millions of useless computations, I'm also not sure that
generating a picture of a person with twelve fingers on each hand or text that
reads as though written by an endlessly smiling children's television star
who's being held hostage is altogether that much more useful than a bitcoin.

There's a huge human cost as well. Artificial intelligence relies heavily upon
"[58]ghost labor": work that appears to be performed by a computer, but is
actually delegated to often terribly underpaid contractors, working in horrible
conditions, with few labor protections and no benefits. There is a huge amount
of work that goes into compiling and labeling data to feed into these models,
and each new model depends on [59]ever-greater amounts of said data — training
data which is well known to be scraped from just about any possible source,
regardless of copyright or consent. And some of these workers suffer serious
psychological harm as a result of exposure to deeply traumatizing material in
the course of sanitizing datasets or training models to perform content
moderation tasks.

Then there's the question of opportunity cost to those who are increasingly
being edged out of jobs by LLMs,^[60]i despite the fact that AI often can't
capably perform the work they were doing. Should I really be using AI tools to
proofread my newsletters when I could otherwise pay a real person to do that
proofreading? Even if I never intended to hire such a person?

Finally, there's the issue of how these tools are being used, and the lack of
effort from their creators to limit their abuse. We're seeing them used to
generate disinformation via increasingly convincing [61]deepfaked images,
audio, or video, and the [62]reckless use of them by previously reputable news
outlets and others who publish unedited AI content is also contributing to
misinformation. Even where AI isn't being directly used, it's degrading trust
so badly that people have to question whether the content they're seeing is
generated, or whether the "person" they're interacting with online might just
be ChatGPT. Generative AI is being used to [63]harass and [64]sexually abuse.
Other AI models are enabling [65]increased surveillance in the workplace and
for "security" purposes — where their well-known biases are worsening
discrimination by police who are wooed by promises of "predictive policing".
The [66]list goes on.

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

I'm glad that I took the time to experiment with AI tools, both because I
understand them better and because I have found them to be useful in my
day-to-day life. But even as someone who has used them and found them helpful,
it's remarkable to see the gap between what they can do and what their
promoters promise they will someday be able to do. The benefits, though extant,
seem to pale in comparison to the costs.

But the reality is that you can't build a hundred-billion-dollar industry
around a technology that's kind of useful, mostly in mundane ways, and that
boasts perhaps small increases in productivity if and only if the people who
use it fully understand its limitations. And you certainly can't justify the
kind of exploitation, extraction, and environmental cost that the industry has
been mostly getting away with, in part because people have believed their lofty
promises of someday changing the world.

I would love to live in a world where the technology industry widely valued
making incrementally useful tools to improve peoples' lives, and were honest
about what those tools could do, while also carefully weighing the technology's
costs. But that's not the world we live in. Instead, we need to push back
against endless tech manias and overhyped narratives, and oppose the
"innovation at any cost" mindset that has infected the tech sector.

Footnotes

 1. When I refer to "AI" in this piece, I'm mostly referring to the much
    narrower field of [67]generative artificial intelligence and [68]large
    language models (LLMs), which is what people generally mean these days when
    they say "AI". [69]↩

 2. While much fun has been made of those describing themselves as "prompt
    engineers", I have to say I kind of get it. It takes some experience to be
    able to open up a ChatGPT window or other LLM interface and actually
    provide instructions that will produce useful output. I've heard this
    compared to "google-fu" in the early days of Google, when the search engine
    was much worse at interpreting natural language queries, and I think that's
    rather apt. [70]↩

 3. ChatGPT was publicly released in November 2022, right as the cryptocurrency
    industry was in peak meltdown. [71]↩

 4. Many of which are built with various other kinds of machine learning or
    artificial intelligence, if not necessarily generative AI. [72]↩

 5. As it happens, he has also [73]written about the "AI isn't useful"
    criticism. [74]↩

 6. Some AI boosters will argue that most or all original thought is also
    merely a mashup of other peoples' thoughts, which I think is a rather
    insulting minimization of human ingenuity. [75]↩

 7. Nor do I want to, by the way. I performed these tests for the purposes of
    illustration, but I neither intend nor want to start using these tools to
    replace my writing. I'm here to write, and you're here to read my writing,
    and that's how it will remain. See my [76]about page. [77]↩

 8. Something that is absolutely encouraged by the tools' creators, who give
    them chat-like interfaces, animations suggesting that the tool is "typing"
    messages back to you, and a confident writing style that encourages people
    to envision the software as another thinking human being. [78]↩

 9. Or, more accurately, by managers and executives who believe the marketing
    hype out of AI companies that proclaim that their tools can replace
    workers, without seeming to understand at all what those workers do. [79]↩

Loved this post? Consider [80]signing up for a pay-what-you-want subscription
or [81]leaving a tip to support Molly White's work, which is entirely funded by
readers like you.

Read more

[82] An image of Donald Trump at a podium, pointing, with a logo behind him
reading “robconf2024”

Issue 63 – RobConf 2024

Coinbase responds to campaign finance violation allegations, Trump panders to
bitcoiners, and I chat with Lyn Alden about sexism in bitcoin.

Aug 7, 2024
[83] The Coinbase logo and the US Marshals seal overlaid on a photo of two
people shaking ha

Coinbase appears to have violated campaign finance laws with a $25 million
super PAC donation

Actively involved in contract negotiations with a federal government agency,
Coinbase was likely prohibited from making its $25 million contribution to the
Fairshake cryptocurrency-focused super PAC in May 2024.

Jul 30, 2024
[84] A person dropping an orange envelope with a white bitcoin symbol into a
ballot box

When did cryptocurrency policy become a voter issue?

I don’t believe that it has.

Jul 29, 2024
[85] Rolls of artificial turf in a shop

Issue 62 – Grassroots

Coinbase’s Stand With Crypto Alliance fudges the numbers, a (former) crypto
industry CEO has a meltdown, and another exchange suffers a nine-figure hack.

Jul 23, 2024

Citation Needed features critical coverage of the cryptocurrency industry and
of issues in the broader technology world.

It is independently published by Molly White, and entirely supported by readers
like you.

[86]Subscribe

  • [87]Archive
  • [88]Recap issues
  • [89]Podcast feed
  • [90]Follow the Crypto
  • [91]About
  • [92]RSS
  • [93]Tip jar
  • [94]Privacy policy

  • [95]Twitter
  • [96]Mastodon
  • [97]Bluesky
  • [98]YouTube
  • [99]TikTok
  • [100]Etc.

© 2024 Molly White.

References:

[1] https://www.citationneeded.news/
[4] https://www.citationneeded.news/page/2/
[5] https://www.citationneeded.news/tag/weekly-recaps/
[6] https://www.citationneeded.news/podcast/
[7] https://followthecrypto.org/
[8] https://www.citationneeded.news/about/
[9] https://www.citationneeded.news/rss/
[10] https://donate.stripe.com/14k8AseTNaqLaZy7ss
[11] https://www.citationneeded.news/privacy/
[13] https://www.citationneeded.news/ai-isnt-useless/#/portal/signin
[14] https://www.citationneeded.news/signup
[24] https://www.citationneeded.news/tag/newsletter/
[25] https://www.citationneeded.news/author/molly/
[26] https://www.citationneeded.news/author/molly/
[34] https://www.citationneeded.news/content/media/2024/04/2024-04-16-AI-isnt-useless-voiceover.mp3
[35] https://www.citationneeded.news/podcast/
[36] https://www.citationneeded.news/ai-isnt-useless/#footnote-1
[37] https://www.citationneeded.news/signup
[38] https://www.citationneeded.news/ai-isnt-useless/#footnote-2
[39] https://www.citationneeded.news/ai-isnt-useless/#footnote-3
[40] https://www.citationneeded.news/ai-isnt-useless/#footnote-4
[41] https://en.wikipedia.org/wiki/Integrated_development_environment
[42] https://www.mollywhite.net/blogroll
[43] https://simonwillison.net/2023/Mar/27/ai-enhanced-development/
[44] https://simonwillison.net/2024/Mar/22/claude-and-chatgpt-case-study/#not-notable
[45] https://www.citationneeded.news/ai-isnt-useless/#footnote-5
[46] https://www.harihareswara.net/posts/2022/speech-to-text-with-whisper-how-i-use-it-why/
[47] https://www.youtube.com/watch?v=SaCVSUbYpVc
[48] https://github.com/molly/courtlistener-download
[49] https://www.pbs.org/newshour/economy/sports-illustrated-found-publishing-ai-generated-stories-photos-and-authors
[50] https://www.washingtonpost.com/media/2023/01/17/cnet-ai-articles-journalism-corrections/
[51] https://docs.google.com/spreadsheets/d/e/2PACX-1vSYCmj-hH51Yz8uc0W55lYYvrCD3464Jb2uULI9_aqsZ6ZGsLl-5IXYv1HkNiNagLFyYgtMubGQx-Ns/pubhtml
[52] https://www.citationneeded.news/ai-isnt-useless/#footnote-6
[53] https://www.citationneeded.news/ai-isnt-useless/#footnote-7
[54] https://www.citationneeded.news/ai-isnt-useless/#footnote-8
[55] https://en.wikipedia.org/wiki/Enshittification
[56] https://en.wikipedia.org/wiki/Keyword_stuffing
[57] https://en.wikipedia.org/wiki/Content_farm
[58] https://en.wikipedia.org/wiki/Ghost_work
[59] https://www.wsj.com/tech/ai/ai-training-data-synthetic-openai-anthropic-9230f8d8
[60] https://www.citationneeded.news/ai-isnt-useless/#footnote-9
[61] https://apnews.com/article/artificial-intelligence-elections-disinformation-chatgpt-bc283e7426402f0b4baa7df280a4c3fd
[62] https://www.newsguardtech.com/special-reports/ai-tracking-center/
[63] https://www.nytimes.com/2024/01/08/technology/ai-4chan-online-harassment.html
[64] https://www.technologyreview.com/2023/12/01/1084164/deepfake-porn-scandal-pushing-us-lawmakers/
[65] https://www.theguardian.com/technology/2024/jan/07/artificial-intelligence-surveillance-workers
[66] https://incidentdatabase.ai/
[67] https://en.wikipedia.org/wiki/Generative_artificial_intelligence
[68] https://en.wikipedia.org/wiki/Large_language_model
[69] https://www.citationneeded.news/ai-isnt-useless/#footnote-anchor-1
[70] https://www.citationneeded.news/ai-isnt-useless/#footnote-anchor-2
[71] https://www.citationneeded.news/ai-isnt-useless/#footnote-anchor-3
[72] https://www.citationneeded.news/ai-isnt-useless/#footnote-anchor-4
[73] https://simonwillison.net/2024/Mar/22/claude-and-chatgpt-case-study/#llms-are-useful
[74] https://www.citationneeded.news/ai-isnt-useless/#footnote-anchor-5
[75] https://www.citationneeded.news/ai-isnt-useless/#footnote-anchor-6
[76] https://www.citationneeded.news/about/
[77] https://www.citationneeded.news/ai-isnt-useless/#footnote-anchor-7
[78] https://www.citationneeded.news/ai-isnt-useless/#footnote-anchor-8
[79] https://www.citationneeded.news/ai-isnt-useless/#footnote-anchor-9
[80] https://www.citationneeded.news/signup
[81] https://donate.stripe.com/14k8AseTNaqLaZy7ss
[82] https://www.citationneeded.news/issue-63/
[83] https://www.citationneeded.news/coinbase-campaign-finance-violation/
[84] https://www.citationneeded.news/when-did-cryptocurrency-become-a-voter-issue/
[85] https://www.citationneeded.news/issue-62/
[86] https://www.citationneeded.news/signup
[87] https://www.citationneeded.news/page/2/
[88] https://www.citationneeded.news/tag/weekly-recaps/
[89] https://www.citationneeded.news/podcast/
[90] https://followthecrypto.org/
[91] https://www.citationneeded.news/about/
[92] https://www.citationneeded.news/rss/
[93] https://donate.stripe.com/14k8AseTNaqLaZy7ss
[94] https://www.citationneeded.news/privacy/
[95] https://twitter.com/molly0xFFF/
[96] https://hachyderm.io/@molly0xfff
[97] https://bsky.app/profile/molly.wiki
[98] https://www.youtube.com/@molly0xfff
[99] https://www.tiktok.com/@molly0xfff
[100] https://www.mollywhite.net/