Experimental browser for the Atmosphere
Loading post...
{ "uri": "at://did:plc:vg3thtvfbgfrr3u6pf6hy3yk/app.bsky.feed.like/3loopxracni2s", "cid": "bafyreichz3n7ut46bnhn4uwdrafhlptobie7ng7oqnyuxlykz2fa4fbhoa", "value": { "$type": "app.bsky.feed.like", "subject": { "cid": "bafyreihe2padvjkvzj7cip2rcck537sfi3dqxyndkhimjyf4buh63cp72m", "uri": "at://did:plc:565ebob5f6hw33hjdkxty6qj/app.bsky.feed.post/3loopvohkjk2l" }, "createdAt": "2025-05-08T20:13:25.182Z" } }
Fascinating read. I see that "The physics of language models" is one key source for this line of thought. Is another source, perhaps, recent papers showing that a small number of excellent examples of a heuristic can have huge benefits in training data? I unfortunately forget the citations.
May 8, 2025, 8:12 PM