My honest GPT-5 review: - It is a *phenomenal* everyday chat model - I will default to it for all normal chats - API pricing is incredible, major points here But code? I will still be using Claude Code + Opus.

Really hoping that GPT-5 is paired with a massive Codex CLI upgrade. This is the #1 thing I’m watching for tomorrow.

Everyone should create a hook for Claude Code that adds an “ultrathink” prompt to requests ending in “-u”. Super easy way to maximize performance on-demand. Takes <90 seconds.

If you’re not *furiously* prepping for GPT-5 rn by building Claude Code hooks + tools that can call the OpenAI API then what are you even doing?

It’s not AGI until >90% of OpenAI, Anthropic, DeepMind, and xAI employees stop contributing to their 401k.

AI: “I’m now superhuman at math and won a Gold medal in the world’s most prestigious math competition. Also AI: “This is the best unicorn I can draw.”

Anthropic has kindly asked that I change the name, which imo is a reasonable ask. They were extremely chill about it, and I appreciate the work they do to make it possible to build fun experiments like this. Claudeputer is now Codeputer.

Claude decided it was time to go to bed so it drew some goodnight ascii art and ran time.sleep(28800). I’m dying.

The problem with a lot of AI products these days? The product is really just VC-subsidized tokens. Once those subsidies dry up it’s game over.

Not enough people realize that Claude Code is really just Claude Agent. It’s a: - customizable agentic system - that's *really* good at knowing when & how to use tools - disguised as a coding tool. And it’s slowly starting to feel like what working with AGI should feel like.