Closing this gap is done in the harness, either through Skills, user behaviour/prompts , Agents.md etc etc.

I think that this is an area worth investing time in, but it is indeed hard to know what the scope of this is.

Also, the “encouragement helps” anecdote seems real in the AlphaEvolve workflow, but I can't see that forpublic models. Gómez-Serrano says this in Quanta (https://www.quantamagazine.org/the-ai-revolution-in-math-has... rived-20260413/), and the released AlphaEvolve notebooks really do contain prompts like “Good luck, I believe in you...” (https://github.com/google-deepmind/alphaevolve_repository_of... oblems, e.g. https://github.com/google-deepmind/alphaevolve_repository_of... blems/blob/main/experiments/finite_field_kakeya_problem/finite_f ield_kakeya.ipynb). But those prompts also bundled strong structural hints (“find a general solution”, “better constructions are possible”), so from my reading the evidence is: prompt phrasing matters, especially in an internal search stack, but not “pep talks are a universal reasoning hack.”

Not actually contradictory. Verification is cheap when there's a spec to check against. 'Valid Sudoku?' is mechanical. But 'good paper?' has no spec. That's judgment, not verification.

There's a famous satirical study that "proved" parachutes don't work by having people jump from grounded planes. This study proves AI rots your brain by measuring people using it the dumbest way possible.

TBH I found the whole thing quite flaky even when using Gemini. I don't think I'll keep using it, although the concept was promising.

to add these lines:

``` openrouter: api_key: "dummy_key" model: gemma3:4b base_url: http://localhost:11434/v1 ```

`ollama run gemma3:27b --verbose` gives me 42.5 TPS +-0.3TPS

`ollama run gemma3:27b-it-qat --verbose` gives me 41.5 TPS +-0.3TPS

Strange results; the full model gives me slightly more TPS.