Nathan Benaich(@nathanbenaich):Breakthroughs emerge not from scaling or data alone, but from incorporating human feedback on preferences, a key lesson from LLMs like GPT-2 applied to world models. This preference learning is an underexplored frontier. Here's Fabian Gura of @odysseyml at @raais 2026

Nathan Benaich

@nathanbenaich

solo member of rsi staff @airstreet

가입 November 2011

36.7K 팔로잉 중 71.8K 팬

Nathan Benaich@nathanbenaich

2026.08.27 13:14

Breakthroughs emerge not from scaling or data alone, but from incorporating human feedback on preferences, a key lesson from LLMs like GPT-2 applied to world models. This preference learning is an underexplored frontier. Here's Fabian Gura of @odysseyml at @raais 2026