akshay_akula an hour ago

Evals on actual research workflows is the right direction, most agent benches are toy tasks.

rubslopes 2 hours ago

I'm glad to see that GPT Sol beats Opus at least in Mathematical Sciences, because that's my need right now, and I much prefer GPT's prose style.

mlmonkey 24 minutes ago

Sad to see no mention of Gemini ...

vatsachak an hour ago

Damn. These things aren't AGI... but I don't care.

Luna is good enough for me to give a parser spec and have it write one.