3 comments

[ 1.8 ms ] story [ 18.9 ms ] thread
I did the exact same thing! Uncanny.

I agree with models being better at different tasks: gemini-cli is superficial, codex is stubborn as a mule and dependable, claude-cli just wants to get something working and done. qwen-cli, Qwen, in general, has a tendency to pendulate too much.

I also reduced the team to two, codex and claude, for me.

Makes sense. This also tracks with the research on human-AI collaboration. A single model converges to the mean of its training distribution, but adversarial multi-model setups break that pattern because each model's blind spots are different.

I wrote about why single-model AI has a structural quality ceiling and why ensemble/hybrid approaches consistently outperform: https://philippdubach.com/posts/the-impossible-backhand/