claude = not bad
I’m quite impressed with how good Claude Code is. I assume it was long context RLed in similar environments. I’m stoked for open models to get this good, I tried GLM, Qwen3, and gpt-oss in Claude Code and they are all far worse than Opus 4.5.
Forget using apps and tooling, I just like how it can reverse engineer everything and write Python. Ads and dark patterns, i regret to inform you that you are up against an elite computer hacker AI that will pass any Turing Test now.
I always hoped for an aligned local agent accessed through my phone that handles everything for me. Book flights, send e-mails, scroll reels, read X, etc… Currently seeing if it can integrate into instamart and order me some carrots.
I also still think it sucks as an engineer, largely for the same reason it’s a terrible musician. It lacks taste, and it’s unclear how to teach it this. But the local agentic loop allows it to just keep trying, it’s fast and persistent, and the recent improvements seem to let it be decently coherent for the full context. RL is good, and can continue to scale for a bit.