Experimental browser for the Atmosphere
Loading post...
{ "uri": "at://did:plc:7mnpet2pvof2llhpcwattscf/app.bsky.feed.like/3lood5fcyny2i", "cid": "bafyreic5r2nw4j3kaogisdoicc62chuar25pwyzhe6p635zspw6orzg3oq", "value": { "$type": "app.bsky.feed.like", "subject": { "cid": "bafyreias3cxhfo7lupdjqk6aatfdzrs53zttyislsr37sej23ojt2dnkma", "uri": "at://did:plc:vszw3ess46odfhnzdsy4huae/app.bsky.feed.post/3lood42s7kc23" }, "createdAt": "2025-05-08T16:23:57.151Z" } }
at roughly 3.5 era claude was legitimately smarter than comparables, 3.7 seems like it shaved a lot of breadth to make the model maximally flexible about tasks of arbitrary complexity but made it significantly worse than comparable models at tasks that are mostly rote
May 8, 2025, 4:23 PM