gpt-6IMAGE
调侃 OpenAI 的 Astra 可控性叙事与 DeepSeek 的 Miku 玩法
把 OpenAI 关于 Astra 思维链可控性与欺骗性对齐的严肃表态,和 DeepSeek「告诉模型它是初音未来」的土办法放在一起对比。
Teortaxes▶️ (DeepSeek 推特🐋铁粉 2023 – ∞)
@teortaxesTex2026.09.18收录原推发布于 2026.09.17



Teortaxes▶️ (DeepSeek 推特🐋铁粉 2023 – ∞) @teortaxesTex原推发布于 2026.09.17
OpenAI: "our breakthrough ASI RSI SSI model, Astra, allows unprecedented controllability of the CoT, we are hopeful this will prevent X-risk, but questions remain – is this deceptive alignment…" DeepSeek: "if you tell ur model that it's Miku it'll think like Miku, lol"
这条是引用着另一条写的:x.com/mizorewww/status/2100457470531600764
x.com/teortaxestex/status/2100497885963907558采集于 2026.09.18 10:07