The AI dooooooom thread

[Admiral Yi]

Thanks.  I hadn't heard about that.

Don't get the joke though.

[Josquius]

Thanks.  I hadn't heard about that.

Don't get the joke though.

A key source of AI controversy is they use other people's work for their training data.
https://www.theeagleonline.com/article/2024/01/op-ed-ai-art-is-art-theft-and-should-be-a-crime
https://www.theguardian.com/technology/2025/jan/14/british-novelists-criticise-government-over-ai-theft

[Maladict]

Here is a desperate but I think feasible attempt at positivity: AI mass-producing fake news, images etc. will mean the death of the social media-based news-consuming of the population and it will push toward the reestablishment of respect and demand for centralised, dependable news sources.

A lot of people, especially among the younger generations, are now used to not being able to tell if any given thing is real. I don't see how we can undo this.

[Tamas]

Here is a desperate but I think feasible attempt at positivity: AI mass-producing fake news, images etc. will mean the death of the social media-based news-consuming of the population and it will push toward the reestablishment of respect and demand for centralised, dependable news sources.

A lot of people, especially among the younger generations, are now used to not being able to tell of any given thing is real. I don't see how we can undo this.

I don't know exactly how to get to that point (especially since we have just recently abandoned it) but this is exactly why news verified to high standards should eventually become valued again.

Essentially people need to realise that something on social media is not (necessarily) better than hearing it from a random guy they sit next to at the bar. Then again of course many people got their news like that in the past and there is that subsection you will never be able to help. The rest should eventually pivot back if we don't burn the world down by then.

[Maladict]

Here is a desperate but I think feasible attempt at positivity: AI mass-producing fake news, images etc. will mean the death of the social media-based news-consuming of the population and it will push toward the reestablishment of respect and demand for centralised, dependable news sources.

A lot of people, especially among the younger generations, are now used to not being able to tell of any given thing is real. I don't see how we can undo this.

I don't know exactly how to get to that point (especially since we have just recently abandoned it) but this is exactly why news verified to high standards should eventually become valued again.

Essentially people need to realise that something on social media is not (necessarily) better than hearing it from a random guy they sit next to at the bar. Then again of course many people got their news like that in the past and there is that subsection you will never be able to help. The rest should eventually pivot back if we don't burn the world down by then.

The problem is you can't pivot back to something you've never known. Some of my friends' kids are between 15 and 20 and have never read a newspaper, even though their parents do. They get all their news from random websites and social media, without any critical thought as to sources or trustworthiness. And that's not even going into algorithms and echochambers. It's absolutely terrifying.

[crazy canuck]

Tamas, the other problem is high quality news reporting requires financial resources.  That is why most newspapers have died or transformed into something resembling social media reporting. Unless something happens to redirect eyes to non clickbait serious reporting, I don't know where the funding is going to come from.

The other problem is where are the professional journalists going to come from - traditionally it takes a number of years to train someone to become an effective professional journalist. We are losing/have lost those training grounds. As a side note a lot of the great reporters got their start in local newspapers, news radio and local tv news.  Almost all of that news infrastructure has gone.

[mongers]

Here is a desperate but I think feasible attempt at positivity: AI mass-producing fake news, images etc. will mean the death of the social media-based news-consuming of the population and it will push toward the reestablishment of respect and demand for centralised, dependable news sources.

A lot of people, especially among the younger generations, are now used to not being able to tell of any given thing is real. I don't see how we can undo this.

I don't know exactly how to get to that point (especially since we have just recently abandoned it) but this is exactly why news verified to high standards should eventually become valued again.

Essentially people need to realise that something on social media is not (necessarily) better than hearing it from a random guy they sit next to at the bar. Then again of course many people got their news like that in the past and there is that subsection you will never be able to help. The rest should eventually pivot back if we don't burn the world down by then.

The problem is you can't pivot back to something you've never known. Some of my friends' kids are between 15 and 20 and have never read a newspaper, even though their parents do. They get all their news from random websites and social media, without any critical thought as to sources or trustworthiness. And that's not even going into algorithms and echochambers. It's absolutely terrifying.

Indeed.

My hope is the changes in the way history is now taught in schools might help; back in my day your were presented with books of fact, to be regurgitate during GCSE exams, later at A level intepreting those historical 'facts ' became a focus.

Yet for the last 20-25 years, in mainstream schools consideration of the sources has been a feature of the cirriculum and some examination questions. So maybe in that sense today's teenagers are better equipped to reason about history and politics?

Oh drat history is no-longer a mandatory subject across much of the school cirriculum. 

[Jacob]

Microsoft Study Finds AI Makes Human Cognition "Atrophied and Unprepared"

A new paper from researchers at Microsoft and Carnegie Mellon University finds that as humans increasingly rely on generative AI in their work, they use less critical thinking, which can "result in the deterioration of cognitive faculties that ought to be preserved."

"[A] key irony of automation is that by mechanising routine tasks and leaving exception-handling to the human user, you deprive the user of the routine opportunities to practice their judgement and strengthen their cognitive musculature, leaving them atrophied and unprepared when the exceptions do arise," the researchers wrote.

Full article here: https://www.404media.co/microsoft-study-finds-ai-makes-human-cognition-atrophied-and-unprepared-3/

[garbon]

Microsoft Study Finds AI Makes Human Cognition "Atrophied and Unprepared"

A new paper from researchers at Microsoft and Carnegie Mellon University finds that as humans increasingly rely on generative AI in their work, they use less critical thinking, which can "result in the deterioration of cognitive faculties that ought to be preserved."

"[A] key irony of automation is that by mechanising routine tasks and leaving exception-handling to the human user, you deprive the user of the routine opportunities to practice their judgement and strengthen their cognitive musculature, leaving them atrophied and unprepared when the exceptions do arise," the researchers wrote.

Full article here: https://www.404media.co/microsoft-study-finds-ai-makes-human-cognition-atrophied-and-unprepared-3/

That long quote was written by the researchers but it wasn't a conclusion of this study but rather their summary of a paper from 1983 in their introduction.

[garbon]

https://www.bbc.co.uk/news/articles/c0m17d8827ko

AI chatbots unable to accurately summarise news, BBC finds

Four major artificial intelligence (AI) chatbots are inaccurately summarising news stories, according to research carried out by the BBC.

The BBC gave OpenAI's ChatGPT, Microsoft's Copilot, Google's Gemini and Perplexity AI content from the BBC website then asked them questions about the news.

It said the resulting answers contained "significant inaccuracies" and distortions.

In a blog, Deborah Turness, the CEO of BBC News and Current Affairs, said AI brought "endless opportunities" but the companies developing the tools were "playing with fire."

"We live in troubled times, and how long will it be before an AI-distorted headline causes significant real world harm?", she asked.

The tech companies which own the chatbots have been approached for comment.

In the study, the BBC asked ChatGPT, Copilot, Gemini and Perplexity to summarise 100 news stories and rated each answer.

It got journalists who were relevant experts in the subject of the article to rate the quality of answers from the AI assistants.

It found 51% of all AI answers to questions about the news were judged to have significant issues of some form.

Additionally, 19% of AI answers which cited BBC content introduced factual errors, such as incorrect factual statements, numbers and dates.

In her blog, Ms Turness said the BBC was seeking to "open up a new conversation with AI tech providers" so we can "work together in partnership to find solutions."

She called on the tech companies to "pull back" their AI news summaries, as Apple did after complaints from the BBC that Apple Intelligence was misrepresenting news stories.

Some examples of inaccuracies found by the BBC included:

Gemini incorrectly said the NHS did not recommend vaping as an aid to quit smoking

ChatGPT and Copilot said Rishi Sunak and Nicola Sturgeon were still in office even after they had left

Perplexity misquoted BBC News in a story about the Middle East, saying Iran initially showed "restraint" and described Israel's actions as "aggressive"

In general, Microsoft's Copilot and Google's Gemini had more significant issues than OpenAI's ChatGPT and Perplexity, which counts Jeff Bezos as one of its investors.

Normally, the BBC blocks its content from AI chatbots, but it opened its website up for the duration of the tests in December 2024.

The report said that as well as containing factual inaccuracies, the chatbots "struggled to differentiate between opinion and fact, editorialised, and often failed to include essential context."

The BBC's Programme Director for Generative AI, Pete Archer, said publishers "should have control over whether and how their content is used and AI companies should show how assistants process news along with the scale and scope of errors and inaccuracies they produce."

Which is great as I'm sure the amount of people now getting their answers straight from Google's AI Overview is non-zero.

[Sophie Scholl]

A fun way of combatting ai results in google is to insert a swear word. Why look for "answers" when you can look for "fucking answers, goddammit". 

[mongers]

A fun way of combatting ai results in google is to insert a swear word. Why look for "answers" when you can look for "fucking answers, goddammit". 

Thanks Sophie, that's an interesting tip.

On a related matter I randomly encountered a link to an MS image creating AI tool, tried "narrow gauge steam locomotive travel* up narrow  steep railway line in mountain*"  *typos on my part



Not sure what use the tool is too me, maybe help with designs for posters or flyers, not at all sure about the ethics or copyrights of using such AI generated stuff?

[Josquius]

I recall reading a while ago about how poor AI was for minority languages. It does all seem very English oriented.
I wonder whether it's effects will be the same for non English speaking nations.

[mongers]

I recall reading a while ago about how poor AI was for minority languages. It does all seem very English oriented.
I wonder whether it's effects will be the same for non English speaking nations.

Good point.

Interestingly, I tried a 2nd test asking it to design a clean, simple,  book cover for a book named something like "Space ship earth crew or passengers" and every one of the four suggestions came back with odd spelling mistakes or missing words.

One of them added some blurb at the bottom and the characters were literally complete gibberish, some not even recognisable characters.

[Syt]

I asked ChatGPT o1 to summarize the interview transcript from Hannity with Musk/Trump from the White House website:

My query:

This is a transcript of an interview by Sean Hannity with President Trump and Elon Musk. Could you kindly summarize key points and try to assess factuality and overall tone of the conversation?

Its lead in with its reasoning is already great:

Reasoned for 8 seconds
Examining document origins

Ok, let me see. This transcript likely stems from a spoof or AI-generated text, set in an alternate timeline with anachronisms and fictional agencies.

Engaging in the fictional

I'm spotting wild ideas like Trump facing two assassination attempts, astronauts stranded, and absurd scenarios involving government waste. Placing any trust in this transcript is a mistake.

Mulling over the fantasy

OK, let's look at how fictitious elements mix with slight nods to reality, like Trump's inflation comments and NASA's restrictions on astronauts.

Below is a concise overview of the transcript's main themes, its apparent factual inconsistencies, and the overall tone. Important note: There is no public record of this conversation actually taking place—multiple details strongly suggest it is a fabricated or fictional scenario rather than a genuine transcript of a White House interview. Nevertheless, here is a summary and analysis of what the text claims:

 

I wish, ChatGPT, I wish.
(Also, obviously it treats it as fictional because it's not up to date with latest news)

1. Summary of the Conversation

Setting and Participants

The text presents itself as a Sean Hannity interview with President Donald Trump and Elon Musk in the Roosevelt Room of the White House.
It implies that Trump is currently President (even though real-world timing would make this contradictory, since Joe Biden was inaugurated on January 20, 2021).
Elon Musk is described as leading a special team (referred to as "DOGE," apparently a "Department of Government Efficiency" or similar) tasked with rooting out fraud, waste, and abuse in government spending.

Claims of Government Efficiency Efforts

Elon Musk supposedly is working pro bono ("working for free") to enforce President Trump's executive orders and cut federal waste.
They discuss large sums of taxpayer money allegedly funding obscure or "woke" programs abroad (e.g., "transgender opera in Colombia," "DEI musical in Ireland," "Sesame Street in Iraq").
They claim that by eliminating such spending, they will save vast sums and help balance the budget.

Discussion of Past Lawsuits and Settlements

There is a joking reference to Trump having sued Twitter "long before Musk" bought it and that Elon Musk (via Twitter) had to pay a $10 million settlement.
Both treat it as a sort of lighthearted anecdote—Trump calls it a "big discount."

Praise for Each Other and Critique of Media

Trump and Musk speak very positively of one another. Musk calls Trump a "good man." Trump refers to Musk as "brilliant" and "honest."
Both criticize mainstream media, claiming widespread bias, dishonesty, and low ratings.
They bring up "Trump derangement syndrome" and how the media or "radical left" want to drive a wedge between Trump and Musk.

Allegations Regarding the Biden Administration

The transcript claims the Biden administration left two astronauts stranded in space for political reasons and that Musk is now organizing a rescue.
They suggest government agencies continued to run "luxury hotels for illegal immigrants" contrary to executive orders.
Biden and his administration are portrayed as incompetent and as deliberately sabotaging the country through reckless spending and "radical" policies.

Social Security, Medicare, Education

Trump states Social Security and Medicare will remain untouched, aside from removing fraud.
He wants to dismantle or greatly reduce the federal Department of Education and let states run schools with local control.
They repeatedly mention the intention to slash "woke" or "DEI" spending and foreign aid.

Reciprocal Tariffs and Foreign Relations

Trump reaffirms a policy of "reciprocal tariffs," meaning if another country imposes a high import duty on U.S. goods, the U.S. will do the same in return.
They claim multiple world leaders have suddenly changed positions or are making positive statements about the U.S. under Trump's new presidency.

Personal Dynamics and "Friendship"

Throughout the text, Hannity marvels at the Trump–Musk relationship, which is presented as close.
The conversation has a casual, bantering style, heavy on compliments and "inside jokes."

2. Assessment of Factuality and Plausibility

Overall Authenticity

There is no evidence that this interview ever occurred. The references to specific events (e.g., "two astronauts left in space for 300 days by Biden," "DOGE" as an official government office headed by Musk) are not corroborated by any real-world reporting. Furthermore, many statements clash directly with established facts:

Timeline Contradiction: The text suggests Trump is currently in office after Biden, which is not supported by real-world events (Joe Biden has been in office since January 20, 2021).
Astronauts Stranded in Space: No mainstream or official source has mentioned "abandoned astronauts" that Elon Musk is rescuing. NASA schedules and missions are publicly documented.
Large Settlements with Twitter: No record exists of Trump suing Twitter in a way that resulted in a $10 million settlement paid by Elon Musk.
Department of Government Efficiency (DOGE): There is no record of a new federal department being created and led by Elon Musk.
Multiple "Wasteful" Grants Cited: While it is true that some foreign aid or cultural programs have been controversial, many specifics here (e.g., "transgender opera in Colombia," "DEI musicals in Ireland") do not match typical U.S. federal budget line-items widely covered in the press or in official appropriations bills.

False or Highly Misleading Claims

Claims that tens or hundreds of millions are being spent on extremely niche cultural programs ("mass disinformation campaign" at Reuters, "luxury hotels for immigrants," etc.) are presented as if they have already been uncovered and canceled. No evidence for these exact scenarios is provided.
References to "Kamala Harris with 92 percent of the D.C. vote" as proof of "deep state bureaucracy" or to "everyone who worked for Biden now worth millions" are general allegations with no substantiation in legitimate public records.

Tone and Style

The conversation is casual, at times jocular. Trump and Musk seem to joke about lawsuits and "big discounts."
Hostility toward media outlets and the "radical left" is a recurring theme.
There is a strong political undertone: praise for Trump's policies, condemnation of Biden, repeated references to "woke" policies, "transgender issues," and "DEI" programs.
The text presents Musk as publicly endorsing Trump, praising him effusively, and adopting pro-Trump or conservative talking points (e.g., "Trump was shot, he's courageous," "Biden is incompetent").
Despite the comedic, lighthearted banter, the conversation portrays a sweeping government overhaul that would be historically unprecedented (eliminating entire agencies, slashing foreign programs, etc.).

3. Overall Tone and Conclusion

The tone is largely informal, with banter between Trump, Musk, and Hannity. All three repeatedly champion each other and share a mutual distaste for critical media coverage. Musk is portrayed as a hands-on tech genius with total devotion to "fixing" government spending. Trump is presented as unstoppable, frequently returning to themes of massive fraud or "kickbacks" and praising Elon Musk's brilliance.

The factual basis of the transcript is highly questionable. Almost all major claims or events (a new "Department of Government Efficiency," two nearly abandoned astronauts, the alleged sums of money for "transgender operas" abroad, etc.) do not match verifiable reporting or known legislative actions. It resembles a piece of political fan fiction or a satirical script rather than a real-world interview.

The conversation repeatedly uses rhetoric about "restoring the will of the people," "cutting woke spending," and "saving a trillion dollars" but never provides credible legislative or factual details. Assertions such as "we found a trillion dollars of fraud" or "Biden left astronauts in space" are advanced without any documentation or media coverage to support them.

Bottom Line
Key Points: The text claims that Elon Musk, appointed by President Trump, is dramatically cutting government waste and foreign aid, that the Biden administration left astronauts stranded, and that Trump is restoring constitutional democracy.
Factuality: The dialogue is almost certainly not an authentic transcript. It contains numerous implausible or disproven assertions.
Tone: Very sympathetic to Trump, strongly critical of mainstream media and the Democratic Party, with a friendly, almost conversational style among the three men.
Readers should treat this as fictional (or satirical) rather than a genuine record of any real White House event.