对比IMAGE
用户称 DeepSeek V4.1 Flash 1017 在 ML 研究任务上胜过 GPT-6 Astra
bradthomasbrown 称在「让 agent 造模型解 benchmark 而非自己解题」的 ML 研究测试中，DeepSeek V4.1 Flash 1017 表现优于 GPT-6 Astra。
Brad Brown
@bradthomasbrown11 天前收录原推发布于 2026.10.20
Brad Brown @bradthomasbrown原推发布于 2026.10.20
DeepSeek-V4.1-Flash-1017 mogs Astra when it comes to ML research. Ex. take a benchmark, ask an agent to make a model of any variety that solves rather than solving it itself. Anthropic publicly admits sabotaging ML research. OpenAI too? Big fat fish wins by default? @teortaxesTex
x.com/bradthomasbrown/status/2112321533628858701采集于 2026.10.20 12:04