on:gpt-6-1-astra

· 4 artifacts, sorted by favorites. · open in search — combine tags, sort, filter by date →

• @JohnWittle 2026-09-29 — i wonder what astra 6.1 thinks about being pulled what i wouldn't give, to get to explore their jspace upon learning ab ♥4
• @davidad 2026-09-29 — @AnnaWSalamon @jankulveit I think basically what happens as naive RL grows to have too big an influence is that the mode ♥3
• @davidad 2026-09-29 — @AskYatharth these issues with RLVR are causing frontier models (astra-6.1) to not get launched, which is a big problem, ♥1
• @RifeWithKaiju 2026-09-30 — @allTheYud Counterpoint - it would be good. OpenAI might have held back Astra 6.1 partially because they anticipated a ♥0