Experimental browser for the Atmosphere
Loading post...
{ "uri": "at://did:plc:t7jbj4w3uo2sus4bc3znsspa/app.bsky.feed.like/3lhto2semgb26", "cid": "bafyreibhzfvcgnao4wii6kmioved5np4h7nlhynspqs6xjeqlcxqnqlu4q", "value": { "$type": "app.bsky.feed.like", "subject": { "cid": "bafyreiawn2svlfudgwirh4ps2odkglhqzkpcf74snicvnws4ipson5c4nu", "uri": "at://did:plc:7wcu6mt2wc66l5q253jit6yw/app.bsky.feed.post/3lhtnpnp4522f" }, "createdAt": "2025-02-10T17:26:17.231Z" } }
(1/9) Excited to share my recent work on "Alignment reduces LM's conceptual diversity" with @tomerullman.bsky.social and @jennhu.bsky.social, to appear at #NAACL2025! 🐟 We want models that match our values...but could this hurt their diversity of thought? Preprint: arxiv.org/abs/2411.04427
Feb 10, 2025, 5:20 PM