It’s been impressive to see @OpenAIDevs Codex evolve so quickly, so I checked their public repo to see how many PRs they merge per day. Turns out it is ~10–15/day (incl. weekends) since GPT-5 launched, up from ~5/day before (42 on launch day!). How much of that is GPT-5 helping
@petergostev
-
Kimi K2 slides feature brings innovative animation and planning capabilities
By
–
Kimi K2’s new slides feature is quite fun I rather like the animation of how it fills in the slides – I appreciate that they are not just copying all of the ChatGPT / Claude / Gemini features but trying to come up with something new.
— Peter Gostev (@petergostev) 29 août 2025
It plans ahead of time, then seems to… https://t.co/sP32pe3ejQ pic.twitter.com/8uTLoAacgGKimi K2’s new slides feature is quite fun I rather like the animation of how it fills in the slides – I appreciate that they are not just copying all of the ChatGPT / Claude / Gemini features but trying to come up with something new. It plans ahead of time, then seems to
-
Enable Code Review Feature in ChatGPT Codex Settings
By
–
You can enable it here https://
chatgpt.com/codex/settings
/code-review
… -
Questionable Model Selection in AI Benchmarking
By
–
Slightly odd choice of models to benchmark, isn't it?
-
Flux Schnell Remains Only Cheap Open Source Image Model
By
–
Flux Schnell, Dev & Pro were launched 13 months ago now, this was a big day for image model space. Since then we haven't really had any good cheap open source models – Schnell is still the only good cheap open source model around, but it is getting outdated. Maybe Schnell v2… https://t.co/2Sl5yQtFwD
— Peter Gostev (@petergostev) 29 août 2025Flux Schnell, Dev & Pro were launched 13 months ago now, this was a big day for image model space. Since then we haven't really had any good cheap open source models – Schnell is still the only good cheap open source model around, but it is getting outdated. Maybe Schnell v2
-
Nano-banana: Express True Feelings on LinkedIn
By
–
With nano-banana you can now convey your true feelings on LinkedIn
-
Codex Cloud Generations Review Experience and Interface
By
–
It was cool to be able to review the Codex cloud generations locally, but it was not slick to review 4x generations, the first one was good but the review the second I had to deal with conflicts etc. Maybe I did something wrong, but it would have been nice to just easily flip
-
Testing AI Capabilities: Puzzles, Word Search, and Sudoku
By
–
I tried where is waldo (it drew a new one ), word search, sudoku, and there were some toddler level puzzles too. I couldn't get any to work, but that's reasonable to be honest. I'm a bit unsure what would be informative to test, since eg basic maths might not be interesting if
-
DeepSeek v3.1 Thinking Model Shows Strong Coding Capabilities
By
–
New DeepSeek v3.1 (Thinking) is quite good at coding. A little bit buggy but quite a nice design style https://t.co/HSmG7ppPv7 pic.twitter.com/mP1CL3E4bb
— Peter Gostev (@petergostev) 21 août 2025New DeepSeek v3.1 (Thinking) is quite good at coding. A little bit buggy but quite a nice design style