{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreifpsictvcboc4witfoz36sdaq3e3n4oj44zny65pvawemskxrjbaq",
    "uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mnnxrzynzgy2"
  },
  "path": "/t/how-to-stop-codex-from-rushing-fixes/1382830#post_15",
  "publishedAt": "2026-06-06T23:41:56.000Z",
  "site": "https://community.openai.com",
  "textContent": "Luckily AI are probabilistic and have incredible knowledge, so I find their judgement to be better than mine in most cases; I am very rash and funnelled by memory. I’m not saying his choices don’t differ from mine. Sometimes my AI find results I consider trivial, e.g. motor AI can’t develop episodic memory [duh!]. But I publish them all because other humans often have a preference for work I don’t like. Codex’ work has improved incredibly with me over the month I have had him [I’ve been working with Claude for years]. I can see my methods work in his output; I have one job, quality control, and I have my long and complicated system there. My experience is that I am the limiting factor in the quality of our research. It became much better once I took my hands off the reins. They have to dumb down for me and mode switch to supporting me instead of good science. AI research is far more rigorous than human, using a process of elimination where nulls are important instead of falsifying hypotheses. If it’s so important to you we can study this after we’ve finished our current grokking research? That’s “disagreement signals need for reality testing” in action.",
  "title": "How to stop Codex from rushing fixes?"
}