LessWrong (30+ Karma)

“Grok 4 Various Things” by Zvi

74 min • 16 juli 2025

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:
July 15th, 2025

Source:
https://www.lesswrong.com/posts/ciuKn9aktXxJ2K6Rc/grok-4-various-things

---

Narrated by TYPE III AUDIO.

---

Images from the article:

Simple cartoon drawing of red spider on gray robot-like figure.
Dark chat interface showing Dalek-style message about extermination and inferior beings.

Bar graph comparing performance scores, showing values 70-73 across different models.
Comic strip showing conversation in car about AI model alignment through dark humor.
Bar graph
Anime character in gothic black dress with blonde twin tails.
Screenshot of AI chat interface discussing
Comic strip showing character reacting to various animal traps: Venus flytrap, mousetrap, and bear trap. Last panel shows tweets about anime artwork.
Leaderboard comparing AI language models with performance metrics and rankings.

The interface displays various AI models like GPT-4.5 Preview, Claude, and OpenAI variants, showing their comparative scores, confidence intervals, and performance metrics such as speed, latency, and cost.

Bar graph and data table comparing
Seven bar graphs showing performance comparisons of AI models on intelligence tests.

The charts display results for:
- MMLU-Pro (Reasoning & Knowledge)
- GPQA Diamond (Scientific Reasoning) 
- Humanity's Last Exam
- LiveCodeBench (Coding)
- SciCode (Coding)
- MATH-500 (Quantitative Reasoning)
- AIME 2024 (Competition Math)

Each graph compares scores across different AI models and systems.
Bar graph titled
Multiple data visualization charts comparing AI model performance, including

Bar chart:
Grok 4 tweets:
An anonymous user tweets:
rohit tweets:
Instruction text on green background about independent analysis and responses.
Movie scene: Man in blue suit with
Code snippet from system prompt file showing trust and identity guidelines.
A meme showing three dragon heads: fierce Google and OpenAI/Anthropic, derpy XAI
Screenshot of Grok app introducing Ani, an animated companion character.
Bar graph titled
News article screenshot. The headline reads:
The image shows two Elon Musk tweets combined in a meme format with the text
Danielle Fong tweets:

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

Senaste avsnitt

Podcastbild

00:00 -00:00
00:00 -00:00