HackerTrans
トップ新着トレンドコメント過去質問紹介求人

russlan

1 カルマ登録 4 日前

コメント

russlan
·4 日前·議論
imo model switching only works if you normalize outputs and keep model specific weirdness behind well designed adapters
russlan
·4 日前·議論
generic model benchmarks are less useful than workflow benchmarks.

Nowadays it's all about workflows , think prompt injections, tool permissions is a big one, logs and lately what anthropic claims is the model distillation risks