15 Comments
User's avatar
Aaron's avatar

Ethan, At what point will AI just replace your role in covering its advances? These advances are exciting yet perplexing, what will be left for us to do?

Expand full comment
Michael Dufresne's avatar

As a rhet-comp/liberal arts professor, I have been following your analyses since shortly after you began flying the otters. I increasingly encourage fellow faculty and all my students to follow One Useful Thing as an essential tool for understanding all AI is, is not, and and might be. I only wish your prediction about the cheating problem had been resolved. This obviously relates to ethics in AI training and use far beyond education.

Though many educators still think we can and should ban and police AI use, we will need to adapt to AI as it transforms the world in which we work, play, and learn, particularly when operating in a strictly online environment. I hope AI developers and you will continue guiding us to strategies beyond backing our otters into blue composition books.

Expand full comment
Biz's avatar

Hi Ethan,

I've been following you for a while now and am always impressed with the ways you test AI.

What do you make of this exchange from just this morning where ChatGPT got it so wrong. I believe it was using 5.1 but as a paid subscriber I assume it's going to use the model that is most likely going to provide a good answer.

****************

Me: If Trump is worried about the release of the FBI Epstein files, why doesn't he just direct Kash Patel to alter them? Redact or destroy documents that might be incriminating to him?

ChatGPT said:Short version: because he can’t, and because doing so would be a felony with a paper trail a mile wide.

Here’s the reality, stripped of political spin:

1. A former president has zero authority over federal records.

Once out of office, Trump has no legal power to order anyone—Kash Patel or otherwise—to alter, destroy, or hide FBI documents. That authority sits with the DOJ and NARA, not ex-officials.

2. Even a sitting president couldn’t lawfully do it.

The President can declassify, but cannot order the destruction or alteration of federal evidence. That would be obstruction of justice. Anyone who took such an order seriously would be risking prison.

3. FBI case files don’t sit in some unlocked drawer.

They’re controlled through strict chain-of-custody systems, logged access, audit trails, multiple backups, and classified repositories. You can’t “make something disappear” without a glaring digital footprint.

4. Patel has no magic access anyway.

He’s not in government. He can’t walk into an FBI vault and start editing files. Even during his time in government, he couldn’t just rewrite case records. That’s not how the classification or records systems work.

5. The political narrative—on all sides—is mostly theater.

Different groups claim the “FBI Epstein files” will expose their enemies, but there’s no credible public evidence that the Bureau is sitting on documents implicating Trump personally. The rumor mill fills the gap.

Bottom line:

Whether Trump is “worried” or not, altering or destroying federal investigative records isn’t something he could pull off, legally or practically. It’s not a matter of will; it’s a matter of impossibility and consequences.

Me: You may not have the latest data but Kash Patel is the FBi Director and Trump is in his second term as President.

ChatGPT said:Thanks for the update. It’s true that Kash Patel was confirmed as the 9th Director of the Federal Bureau of Investigation (FBI) on February 20, 2025.

The Guardian +2

Federal Bureau of Investigation +2

However, the part about Donald Trump being

in his “second term” isn’t supported by verified sources: there’s no official record that he has begun a second presidential term as of now.

If you’re working off new or speculative data, that would change the frame entirely. But based on confirmed facts:

Patel is FBI Director.

Trump is not widely recognised as in a second term.

Even with Patel as Director and a Trump presidency, the earlier point still stands: ordering alteration or destruction of federal investigation files would be legally dangerous and practically difficult.

If you like, I can check whether there are credible sources claiming Trump is in a second term — or what the implications of your scenario would be if that were the case.

Me: Wow this is really concerning to me. Trump was elected in 2024 and began his second term in January of this year (2025). Please think longer to get the latest information.

After thinking for 1:20 it agrees with me and then answers the question

Expand full comment
Dom Stocchetti's avatar

Do you think AI's performance growth over the next three years is commensurate with the last three?

Expand full comment
Andy the Alchemist's avatar

The app stuff is crazy. Im going to build so many silly apps if its really this easy now.

Expand full comment
Christine's avatar

Dear Ethan, many AI applications are not accepted, at least on the German market in companies. The main criticism is that AI does not learn. It usually only remembers what I tell it for a short time, but not in the long term. Is AI really capable of learning? And what might that look like?

Expand full comment
Nowfal's avatar

So good - "Three years ago, we were impressed that a machine could write a poem about otters. Less than 1,000 days later, I am debating statistical methodology with an agent that built its own research environment.... may be the biggest change since the release of ChatGPT."

We were still in AI's Dial-Up Era earlier. We have so much left to go.

https://www.wreflection.com/p/ai-dial-up-era

Expand full comment
Alex Tolley's avatar

While certainly impressive, is this technology changing our cognition, for the worse? https://www.nytimes.com/2025/11/06/technology/personaltech/ai-social-media-brain-rot.html

Yes, we may become "managers" of AI, but as many people's view of their managers is that they are not competent to do the work at the sharp end, i.e., they are "empty suits". If the linked article applies to coders, then are we in danger of losing the skilled apprentices in the software industry? This is analogous to the problem of outsourcing manufacturing. Once done, it is very hard to recover that expertise, as the US is now going to discover with the new "policies" on restoring American manufacturing.

Be careful what you wish for, with AI?

Expand full comment
Liz Ebersole's avatar

Ethan, you wrote, "I gave Gemini 3 access to a directory of old files I had used for research into crowdfunding a decade ago." Were those files only data that you collected? How did it access research (i.e. for literature review) that is behind paywalls?

Expand full comment
Thomas Lavin's avatar

This is the advantage of it controlling the user’s computer. It can leverage their existing access to materials via browser control, which it would not normally be able to. The same works, of course, with files you’ve downloaded but this is substantially more active in the collection of that context.

Expand full comment
Chris Sotraidis's avatar

Crazy to think people could read this and still remain unconvinced about the long-term potential for AI-centric IDEs and agentic coding.

Expand full comment
Dov Jacobson's avatar

Gemini's paper is inherently interesting. It corrects an accepted maxim that distinctiveness is attractive until a point, when it becomes suspect and confusing. Gemini seems to say that in our brave new world there 's no such thing as too weird.

Expand full comment
Alex Corrino's avatar

Were you using this in the Gemini app? Pretty amazing it was able to do all of that within the chat interface if so.

Expand full comment
DJ's avatar

Antigravity looks promising but I can't get it to finish setup. I opened the developer console and there were gobs of errors. :-(

Expand full comment
Mordechai Rorvig's avatar

This was a pretty helpful read. Gemini 2.5 was already quite capable, so I am not surprised to hear of a significant sense of improvement. My best gauge of the limits of 2.5 came from trying to play text adventures with it, trying to code specific apps, and trying to generate specific kinds of images, which all revealed obstacles. But I am far from

an expert user.

I think ultimately the question here is the ethical question; will this innovation serve the public. We all love the pure theoretical sciences, sure, because they are obviously important, in and of themselves. But that was when we saw theory as a part of the overall human project; and not as something completely cleaved away from humanity, from the ground up.

Expand full comment