开启时会模糊预览图，关闭后正常显示
RT @isha_gpt_: This is what I worked on during @MATSprogram with @AnthropicAI! 🌸🌱 Bloom lets you skip eval pipeline engineering and genera…
AI alignment + LLMs at Anthropic. On leave from NYU. Views not employers'. No relation to @s8mb. I think you should join @givingwhatwecan.
RT @AnthropicAI: We’re releasing Bloom, an open-source tool for generating behavioral misalignment evals for frontier AI models. Bloom let…
AI alignment + LLMs at Anthropic. On leave from NYU. Views not employers'. No relation to @s8mb. I think you should join @givingwhatwecan.
RT @AnthropicAI: Sadly, CEO Seymour Cash struggled to live up to its name. It put a stop to most of the big discounts. But it had a high t…
AI alignment + LLMs at Anthropic. On leave from NYU. Views not employers'. No relation to @s8mb. I think you should join @givingwhatwecan.
RT @OwainEvans_UK: New paper: We train Activation Oracles: LLMs that decode their own neural activations and answer questions about them in…
AI alignment + LLMs at Anthropic. On leave from NYU. Views not employers'. No relation to @s8mb. I think you should join @givingwhatwecan.
RT @tejalpatwardhan: we're open-sourcing a new frontier science eval in biology, chemistry, and physics. there are 2 tracks: olympiad level…
AI alignment + LLMs at Anthropic. On leave from NYU. Views not employers'. No relation to @s8mb. I think you should join @givingwhatwecan.
RT @abhayesian: 🧵 Earlier this year, Anthropic ran an auditing game where teams of researchers investigated a model with a hidden objective…
AI alignment + LLMs at Anthropic. On leave from NYU. Views not employers'. No relation to @s8mb. I think you should join @givingwhatwecan.