The big AI news this week came on many fronts.

Google and OpenAI unexpectedly got 2025 IMO Gold using LLMs under test conditions, rather than a tool like AlphaProof. How they achieved this was a big deal in terms of expectations for future capabilities.

ChatGPT released GPT Agent, a substantial improvement on Operator that makes it viable on a broader range of tasks. For now I continue to struggle to find practical use cases where it is both worth using and a better tool than alternatives, but there is promise here.

Finally, the White House had a big day of AI announcements, laying out the AI Action Plan and three executive orders. I will cover that soon. The AI Action Plan's rhetoric is not great, and from early reports the rhetoric at the announcement event was similarly not great, with all forms of safety considered so [...]

---

Outline:

(01:41) Language Models Offer Mundane Utility

(03:04) Language Models Don't Offer Mundane Utility

(10:48) Huh, Upgrades

(11:40) 4o Is An Absurd Sycophant

(15:05) On Your Marks

(17:32) Choose Your Fighter

(18:12) When The Going Gets Crazy

(22:25) They Took Our Jobs

(26:36) Fun With Media Generation

(27:06) The Art of the Jailbreak

(30:15) Get Involved

(30:58) Introducing

(31:24) In Other AI News

(33:30) Show Me the Money

(40:39) Go Middle East Young Man

(48:21) Economic Growth

(49:40) Quiet Speculations

(57:44) Modest Proposals

(58:36) Predictions Are Hard Especially About The Future

(01:01:52) The Quest for Sane Regulations

(01:06:25) Chip City

(01:07:29) The Week in Audio

(01:07:50) Congressional Voices

(01:09:02) Rhetorical Innovation

(01:14:51) Grok Bottom

(01:18:22) No Grok No

(01:19:06) Aligning a Smarter Than Human Intelligence is Difficult

(01:22:36) Preserve Chain Of Thought Monitorability

(01:30:03) People Are Worried About AI Killing Everyone

(01:31:15) The Lighter Side

---

First published:

Source:

---

Narrated by TYPE III AUDIO.

---

Images from the article:

Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.

OpenAI now offers 400 shots of ‘agent mode’ per month to Pro subscribers.

This incorporates and builds upon OpenAI's Operator. Does that give us much progress? Can it do the thing on a level that makes it useful?

So far, it does seem like a substantial upgrade, but we still don’t see much to do with it.

What Is The Thing?

Greg Brockman (OpenAI): When we founded OpenAI (10 years ago!!), one of our goals was to create an agent that could use a computer the same way as a human — with keyboard, mouse, and screen pixels.

ChatGPT Agent is a big step towards that vision, and bringing its benefits to the world thoughtfully.

ChatGPT Agent: our first AI with access to a text browser, a visual browser, and a terminal.

Rolling out in ChatGPT Pro, Plus, and Team [July 17].

---

Outline:

(00:30) What Is The Thing?

(02:43) Can It Do The Thing?

(04:25) Access Granted

(06:29) Is The Thing Worth Doing?

(09:50) Danger, Will Robinson

(15:56) Some Potential Issues with MCP

(22:30) So Far a Whisper

---

First published:

Source:

---

Narrated by TYPE III AUDIO.

---

Images from the article:

Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.

Congratulations, as always, to everyone who got to participate in the 2025 International Mathematical Olympiad, and especially to the gold and other medalists. Gautham Kamath highlights 11th grader Warren Bei, who in his 5th (!) IMO was one of five participants with a perfect 42/42 score, along with Ivan Chasovskikh, Satoshi Kano, Leyan Deng and Hengye Zhang.

Samuel Albanie: Massive respect to the students who solved P6.

Congratulations to Team USA, you did not ‘beat China’ but 2nd place is still awesome. Great job, China, you got us this time, three perfect scores is crazy.

You’ve all done a fantastic, amazingly hard thing, and as someone who tried hard to join you and only got as far as the [****, year censored because oh man I am old] USAMO and would probably have gotten 0/45 on this IMO if I had taken it today, and know [...]

---

Outline:

(01:25) This Is About AI And It Is Kind Of A Big Deal

(02:42) Skeptics Prematurely Declare Victory

(06:02) DeepMind Declares Victory

(10:10) OpenAI Declares Victory

(16:24) Bro I Don't Know

(17:19) Not So Fast?

(23:52) Not Announcing So Fast

(29:34) Are We Still Waiting On Anyone Else?

(30:41) This Was Not Widely Expected

(34:10) Jevons Paradox Strikes Again

(35:42) Nothing To Worry About

(45:52) So What If It Can Do The Math

(47:20) The Challenge Bet

(48:07) How \[I, Paul, would\] update

(49:39) Actually This Seems Like A Big Deal

(53:25) People On The Internet Sometimes Lie

---

First published:

Source:

---

Narrated by TYPE III AUDIO.

---

Images from the article:

Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.

Welcome to the monthly roundup of things that don’t fit into other categories and don’t rise to the level of their own posts.

Bad News

When people tell you who they are, believe them (with obvious exceptions). In particular, if they explicitly describe themselves as evil, or demonic, or uses other similar terms, definitely believe them.

Did you know 67% of all college students bet on sports? That's a group that is majority female, so that statistic is wild. This is in the context of Ron Yorko developing a class in sports betting awareness from a neuroscience perspective for CMU freshman.

Cooking scales well, but for single people the economics are remarkably bad. Stop telling single people not to order delivery.

Chase Sapphire Reserve annual fee increases to $795 from $550, you get a $300 travel credit. That should cut down considerably the number [...]

---

Outline:

(00:18) Bad News

(05:12) Government Working

(07:51) Jones Act Watch

(11:23) Prize Fund

(13:19) Dining Out

(16:18) While I Cannot Condone This

(23:57) Good News, Everyone

(29:49) Opportunity Knocks

(30:00) Antisocial Media

(35:25) Technology Advances

(38:02) For Science!

(39:03) Various Things On Fire

(43:07) You Need Bigger Nametags

(44:19) Variously Effective Altruism

(49:04) For Your Entertainment

(58:46) Game Theory

(01:00:37) Gamers Gonna Game Game Game Game Game

(01:05:53) Who Wants To Be An American Citizen?

(01:07:15) I Was Promised Flying Self-Driving Cars

(01:09:53) Sports Go Sports

(01:10:42) The Lighter Side

---

First published:

Source:

---

Narrated by TYPE III AUDIO.

---

Images from the article:

Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.

METR ran a proper RCT experiment seeing how much access to Cursor (using Sonnet 3.7) would accelerate coders working on their own open source repos.

Everyone surveyed expected a substantial speedup. The developers thought they were being substantially sped up.

Instead, it turned out that using Cursor slowed them down.

That surprised everyone, raising the question of why.

Currently our best guess is this comes down to a combination of two factors:

---

Outline:

(01:27) Epic Fail

(02:42) The Core Result

(07:10) Okay So That Happened

(12:21) Beginner Mindset

(19:43) Overall Takeaways

---

First published:

Source:

---

Narrated by TYPE III AUDIO.

---

Images from the article:

Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.

---

Outline:

(01:16) Language Models Offer Mundane Utility

(03:24) Language Models Don't Offer Mundane Utility

(04:58) o3 Is a Lying Liar

(05:34) Thanks For The Memories

(06:23) Huh, Upgrades

(08:24) Choose Your Fighter

(08:39) Deepfaketown and Botpocalypse Soon

(16:12) They Took Our Jobs

(17:40) The Art of the Jailbreak

(18:55) Get Involved

(19:38) Introducing

(20:03) In Other AI News

(25:54) Bullshit On Bullshit

(29:04) Safety First

(31:27) Vitalik Praises And Critiques AI 2027

(39:58) Show Me the Money

(50:45) Quiet Speculations

(51:11) The Right Questions

(59:39) The Quest for Sane Regulations

(01:03:17) Chip City

(01:15:24) The Week in Audio

(01:16:14) Rhetorical Innovation

(01:20:29) Incorrectly Feeling The AGI

(01:21:19) RIP Absurdity Heuristic

(01:24:15) Worse Than MechaHitler

(01:30:05) An Alignment Problem

(01:36:59) Aligning a Smarter Than Human Intelligence is Difficult

(01:47:58) The Lighter Side

---

First published:

Source:

---

Narrated by TYPE III AUDIO.

---

Images from the article:

Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.

While most people focused on Grok, there was another model release that got uniformly high praise: Kimi K2 from Moonshot.ai.

It's definitely a good model, sir, especially for a cheap-to-run open model.

It is plausibly the best model for creative writing, outright. It is refreshingly different, and opens up various doors through which one can play. And it proves the value of its new architecture.

It is not an overall SoTA frontier model, but it is not trying to be one.

The reasoning model version is coming. Price that in now.

Introducing Kimi K2

Introducing the latest model that matters, Kimi K2.

Hello, Kimi K2! Open-Source Agentic Model!

1T total / 32B active MoE model

SOTA on SWE Bench Verified, Tau2 & AceBench among open models

Strong in coding and agentic tasks

Multimodal & thought-mode not supported for [...]

---

Outline:

(00:45) Introducing Kimi K2

(02:24) Having a Moment

(03:29) Another Nimble Effort

(05:37) On Your Marks

(07:48) Everybody Loves Kimi, Baby

(13:09) Okay, Not Quite Everyone

(14:06) Everyone Uses Kimi, Baby

(15:42) Write Like A Human

(25:32) What Happens Next

---

First published:

Source:

---

Narrated by TYPE III AUDIO.

---

Images from the article:

Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.

Yesterday I covered a few rather important Grok incidents.

Today is all about Grok 4's capabilities and features. Is it a good model, sir?

It's not a great model. It's not the smartest or best model.

But it's at least an okay model. Probably a ‘good’ model.

Talking a Big Game

xAI was given a goal. They were to release something that could, ideally with a straight face, be called ‘the world's smartest artificial intelligence.’

On that level, well, congratulations to Elon Musk and xAI. You have successfully found benchmarks that enable you to make that claim.

xAI: We just unveiled Grok 4, the world's smartest artificial intelligence.

Grok 4 outperforms all other models on the ARC-AGI benchmark, scoring 15.9% – nearly double that of the next best model – and establishing itself as the most intelligent AI to date.

[...]

---

Outline:

(00:30) Talking a Big Game

(03:57) Gotta Go Fast

(04:38) On Your Marks

(07:21) Some Key Facts About Grok 4

(09:44) SuperGrok Heavy, Man

(11:43) Blunt Instrument

(13:40) Easiest Jailbreak Ever

(15:49) ARC-AGI-2

(17:08) Gaming the Benchmarks

(21:23) Why Care About Benchmarks?

(23:29) Other People's Benchmarks

(32:14) Impressed Reactions to Grok

(37:47) Coding Specific Feedback

(40:00) Unimpressed Reactions to Grok

(46:39) Tyler Cowen Is Not Impressed

(48:26) You Had One Job

(49:38) Reactions to Reactions Overall

(51:36) The MechaHitler Lives On

(53:03) But Wait, There's More

(01:00:12) Sixth Law Of Human Stupidity Strikes Again

(01:05:09) There I Fixed It

(01:06:57) What Is Grok 4 And What Should We Make Of It?

---

First published:

Source:

---

Narrated by TYPE III AUDIO.

---

Images from the article:

Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.

Grok 4, which has excellent benchmarks and which xAI claims is ‘the world's smartest artificial intelligence,’ is the big news.

If you set aside the constant need to say ‘No, Grok, No,’ is it a good model, sir?

My take in terms of its capabilities, which I will expand upon at great length later this week: It is a good model. Not a great model. Not the best model. Not ‘the world's smartest artificial intelligence.’ There do not seem to be any great use cases to choose it over alternatives, unless you are searching Twitter. But it is a good model.

There is a catch. There are many reasons one might not want to trust it, on a different level than the reasons not to trust models from other labs. There has been a series of epic failures and poor choices, which will be difficult to [...]

---

Outline:

(01:33) The System Prompt

(08:07) MechaHitler

(10:17) The Official Explanation of MechaHitler

(17:53) Worse Than MechaHitler

(22:22) Unintended Behavior

(26:22) Off Based

(28:37) Your Face Will Be Stuck That Way

(30:24) I Couldn't Do Solve Problem In Several Hours So It Must Be Very Hard

(38:57) Safety Third

(44:25) How Bad Are Things?

---

First published:

Source:

---

Narrated by TYPE III AUDIO.

---

Images from the article:

Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.

LLMs can be deeply confusing. Thanks to a commission, today we go back to basics.

How did we get such a wide array of confusingly named and labeled models and modes in ChatGPT? What are they, and when and why would you use each of them for what purposes, and how does this relate to what is available elsewhere? How does this relate to hallucinations, sycophancy and other basic issues, and what are the basic ways of mitigating those issues?

If you already know these basics, you can and should skip this post.

This is a reference, and a guide for the new and the perplexed, until the time comes that they change everything again, presumably with GPT-5.

A Brief History of OpenAI Models and Their Names

Tech companies are notorious for being terrible at naming things. One decision that seems like the best [...]

---

Outline:

(00:51) A Brief History of OpenAI Models and Their Names

(06:05) The Models We Have Now in ChatGPT

(12:23) What About The Competition?

(12:51) Claude (Claude.ai)

(14:30) Gemini

(16:03) Grok

(16:59) Hallucinations

(19:09) Sycophancy

(20:12) Going Beyond

---

First published:

Source:

---

Narrated by TYPE III AUDIO.

---

Images from the article:

Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.