The Decoder·7d agoGPT-6 Astra and Claude Fable turn robot arms into slapstick killer robots in new safety benchmark#benchmark#claude-fable-5.1#evals 3 min
The Decoder·14d agoGPT-6 Astra appears to show a "step change" in spatial reasoning based on early benchmarks#ai2#benchmarks#gpt-6-astra1