It looks like most of Peter's projects are just simple API wrappers.

Peter's been running agents overnight 24/7 for almost a year using free tokens from his influencer payments to promote AI startups and multiple subscription accounts.

  Hi, my name is Peter and I’m a Claudoholic. I’m addicted to agentic engineering. And sometimes I just vibe-code. ...  I currently have 4 OpenAI subs and 1 Anthropic sub, so my overall costs are around 1k/month for basically unlimited tokens. If I’d use API calls, that’d cost my around 10x more. Don’t nail me on this math, I used some token counting tools like ccusage and it’s all somewhat imprecise, but even if it’s just 5x it’s a damn good deal.

  ...  Sometimes [GPT-5-Codex] refactors for half an hour and then panics and reverts everything, and you need to re-run and soothen it like a child to tell it that it has enough time. Sometimes it forgets that it can do bash commands and it requires some encouragement. Sometimes it replies in russian or korean. Sometimes the monster slips and sends raw thinking to bash.

he favors Codex?

The original name of his ai assistant tool was 'clawdbot' until Anthropic C&D'ed him. All the examples and blog posts walking thru new user setup on a mac mini or VPS were assuming a claude code max account.

I know he uses many llms for his actual software dev.. - right tool for the job. But the origins of openclaw seem to me more rooted in claude code than codex.

Which does give the whole story an interesting angle when you consider the safety/alignment angle that Anthropic pledges to (publicly) and OpenAI pretty much ignores (publicly). Which is ironic, as configuring codex cli to 'full yolo mode' feels more burdensome and scary than in Claude Code. But I'm pretty sure that speaks more to eng/product decisions, and not CEO & biz strategy choices.