Experimental browser for the Atmosphere
You think any user cares what the LLM Arena or some benchmark score is of their favorite AI model? They just use the one which gives them the best output for them, which everyone keeps saying they're noticing significant improvement.
May 2, 2025, 11:50 AM
{ "uri": "at://did:plc:k3ke2ul5n2vbbpq3sw2dhhzu/app.bsky.feed.post/3lo6r2fkyxk2h", "cid": "bafyreieyenfssxxmcksjwsqbauneurolhryzutc2dext5ejzelyyeimmoa", "value": { "text": "You think any user cares what the LLM Arena or some benchmark score is of their favorite AI model? They just use the one which gives them the best output for them, which everyone keeps saying they're noticing significant improvement.", "$type": "app.bsky.feed.post", "langs": [ "en" ], "reply": { "root": { "cid": "bafyreihmeidcjej4yhpmpgdld64lxz6r44jj7ycfc3z7vro6t5g2evb5jy", "uri": "at://did:plc:4sforn5o5soqsndnny42aerw/app.bsky.feed.post/3lo6qakvdf22j" }, "parent": { "cid": "bafyreihmeidcjej4yhpmpgdld64lxz6r44jj7ycfc3z7vro6t5g2evb5jy", "uri": "at://did:plc:4sforn5o5soqsndnny42aerw/app.bsky.feed.post/3lo6qakvdf22j" } }, "createdAt": "2025-05-02T11:50:12.015Z" } }