scaling01 doubts game-based benchmark novelty, suspects OpenAI already has similar RL envs
scaling01 · x · 2026-11-06
Responding to discussion of a game-based benchmark praised for its methodology, scaling01 notes the creator himself admitted it's just a game he likes and copied, and says he'd be surprised if OpenAI doesn't already have RL environments for all these games and analogous settings that could occur on message boards or the web.
More from Models
- Google Ultra subscriber blocked from Antigravity by region detection — lxfater · 2026-11-06
- Palisade's Jeff Ladish: skip the 40 benchmarks, ask if agents finish real work — FinanceYF5 · 2026-11-06
- AA Index 31: 594B total / 17B active params, Apache 2.0 open source — AIFlow_ML · 2026-11-06
- Moonshot's Kimi K 3.1 Pro surfaces: 2.8T-param MoE, weights on Hugging Face — thursdai_pod · 2026-11-06
- Tencent Hunyuan Hy4 hits limits on day one, WorkBuddy rushes 10x compute expansion — TencentHunyuan · 2026-11-06
- NaceAI open-sources Drex decision models, hitting SOTA 67.52 on Decision Index — nischay_twt · 2026-11-06