Testing models for other labs just feels completely pointless now after trying Claude Fable. Genuinely feels like a waste of time… this model is just so above and beyond incredible. Hats off to the Anthropic team.
@mattshumer_
-
GPT-5.5 and Opus 4.8 are best models with thinking maxed
By
–
Currently, the best models are GPT-5.5 and Opus 4.8. Make sure thinking is turned all the way up!
-
Using time in agents: obsession fix via system prompt
By
–
Pls do this! Makes agents so much better. They do tend to get a bit obsessed with time if they see it every message or two but a line in the system prompt usually fixes that.
-
Codex Mobile excels with super long-running prompts
By
–
Codex Mobile is amazing with super long-running prompts
-
Codex stores local state database for pulling
By
–
Yes you can… Codex keeps a state database on your local machine that you can pull from
-
Codex on Mac Mini controlled via Codex Mobile
By
–
Yep! Codex on my Mac Mini, mostly controlled via Codex Mobile
-
Tokens as insane leverage: Codex on one machine example
By
–
And this is just Codex, on one machine. Doesn’t even include my other machine, Claude, and Agent-S tokens. Tokens, when used correctly, are insane leverage.
-
Codex Mobile Improves Development Through Ambitious Prompting
By
–
Codex Mobile is making me a better developer in a way I didn’t expect: I step away from my laptop and stop micromanaging. I give it much more ambitious prompts (the way models work best). And I get space to think instead of sitting there with burning eyes spamming prompts.
-
Achieving SUPERHOT Design Style with Codex 5.5 and Prompt Tweaks
By
–
With a few prompt tweaks/strategies, and a switch to Codex 5.5 instead of Opus 4.7, you can get MUCH closer to the SUPERHOT design style.
— Matt Shumer (@mattshumer_) 18 mai 2026
This was a one-shot output! https://t.co/jCaDRX25Ap pic.twitter.com/fIEP3eWi6iWith a few prompt tweaks/strategies, and a switch to Codex 5.5 instead of Opus 4.7, you can get MUCH closer to the SUPERHOT design style. This was a one-shot output!
-
AI inference market size significantly underestimated, says optimistic observer
By
–
I firmly believe that even the most optimistic people in AI are severely underestimating how big the market for inference is going to be.