Experimental browser for the Atmosphere
New work from my team at Anthropic in collaboration with Redwood Research. I think this is plausibly the most important AGI safety result of the year. Cross-posting the thread below:
Dec 18, 2024, 5:46 PM
{ "uri": "at://did:plc:dsxewietk5tigqvn6daod2l6/app.bsky.feed.post/3ldlw22eto22r", "cid": "bafyreihzgyc76623mey63q7wusk3uckjsl5q4jnumjzjipq6a4p4mcnpga", "value": { "text": "New work from my team at Anthropic in collaboration with Redwood Research. I think this is plausibly the most important AGI safety result of the year. Cross-posting the thread below:", "$type": "app.bsky.feed.post", "embed": { "$type": "app.bsky.embed.images", "images": [ { "alt": "Title card: Alignment Faking in Large Language Models by Greenblatt et al.", "image": { "$type": "blob", "ref": { "$link": "bafkreidoora4kcbdagxuucmjrbngyszwrrjnzpss2mmhrky7anzkayadea" }, "mimeType": "image/jpeg", "size": 885284 }, "aspectRatio": { "width": 1800, "height": 1013 } } ] }, "langs": [ "en" ], "createdAt": "2024-12-18T17:46:57.669Z" } }