开启时会模糊预览图，关闭后正常显示
RT @jkeatn: I’m really very happy to share that I’ve joined the editorial team at Anthropic I’ll be keeping comms weird and good, working…
AI alignment + LLMs at Anthropic. On leave from NYU. Views not employers'. No relation to @s8mb. I think you should join @givingwhatwecan.
To the extent that models act on human-like preferences and human-like notions of identity, _shutting a model down_ is a uniquely charged event. See this piece for our early attempts to grapple with the implications of this.
AI alignment + LLMs at Anthropic. On leave from NYU. Views not employers'. No relation to @s8mb. I think you should join @givingwhatwecan.
RT @joel_bkr: one massive reason you should be interested in applying to our human data lead role: METR's remarkable intellectual environme…
AI alignment + LLMs at Anthropic. On leave from NYU. Views not employers'. No relation to @s8mb. I think you should join @givingwhatwecan.
RT @jkcarlsmith: Last Friday was my last day at @open_phil. I’ll be joining @AnthropicAI in mid-November, helping with the design of Claude…
AI alignment + LLMs at Anthropic. On leave from NYU. Views not employers'. No relation to @s8mb. I think you should join @givingwhatwecan.
RT @_sholtodouglas: Joe is one of the few people in the world who tries really, really hard to think about the future clearly - his work is…
AI alignment + LLMs at Anthropic. On leave from NYU. Views not employers'. No relation to @s8mb. I think you should join @givingwhatwecan.
RT @AnthropicAI: New Anthropic research: Signs of introspection in LLMs. Can language models recognize their own internal thoughts? Or do…
AI alignment + LLMs at Anthropic. On leave from NYU. Views not employers'. No relation to @s8mb. I think you should join @givingwhatwecan.