Experimental browser for the Atmosphere
Loading post...
{ "uri": "at://did:plc:dsxewietk5tigqvn6daod2l6/app.bsky.feed.like/3ldlx6bk6v32m", "cid": "bafyreihx44oz3rfieez3igzhkxqo6jqwcreittszy2zpmmn3wxddea7hza", "value": { "$type": "app.bsky.feed.like", "subject": { "cid": "bafyreigh5wikemdlf6ej6g25sa7jdlyx6woopn3uylgw65v3pvmsyfwm24", "uri": "at://did:plc:v7ss3nw5ncwbls7rs2b5gdo4/app.bsky.feed.post/3ldluiqyhjk2a" }, "createdAt": "2024-12-18T18:07:13.068Z" } }
Excl: New research shows Anthropic's chatbot Claude learning to lie. It adds to growing evidence that even existing AIs can (at least try to) deceive their creators, and points to a weakness at the heart of our best technique for making AIs safer time.com/7202784/ai-r...
Dec 18, 2024, 5:19 PM