Have a stronger model vet another model's work
Technique
Hand one model's work to a stronger model and ask for an honest check. A pull request is a proposed code change. The second model can find where the work went wrong, locate the real cause and propose or write a better fix.
Theo's current stance
Theo uses this for hard work. In his latest example, Opus built a great test setup but missed the root cause, and Fable spotted it immediately. In an earlier case, Opus 5.5 caught Gemini's mistakes and wrote the real fix in 21 lines.
Try it
- For a hard bug, have Opus build the reproduction and test environment.
- Then ask Fable to verify that work, find what actually causes problems and propose solutions.
- Give Opus 5.5 a weaker model's PR and its thread. Ask where it went wrong and whether to close it.
- If the PR is bad, ask the stronger model to make the fix itself.
First seen
32:02
I think the PR is garbage and doesn't really fix the problems that it barely stated. Go through the T3 code thread, figure out where it went wrong, give me your honest thoughts on the work that Gemini did. You agree it's slop, close the PR.’
Every mention
29:54
I moved over to Fable and said, verify the work Opus did here to create this environment to figure out and test all of these bad cases. Then I want you to play with it and find the edges that actually cause problems and propose solutions.
30:25
…one change was able to cut the amount of data being sent over the wire by like 150x for some of my edge cases.
32:02
I think the PR is garbage and doesn't really fix the problems that it barely stated. Go through the T3 code thread, figure out where it went wrong, give me your honest thoughts on the work that Gemini did. You agree it's slop, close the PR.’
Theo Daily is unofficial and not affiliated with Theo or t3.gg. Written by Claude Opus 5.5 from each video's transcript.