> making it finetuned to your use cases might make it dumber overall. LoRa doesn... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		koakuma-chan 4 months ago \| parent \| context \| favorite \| on: Context is the bottleneck for coding agents now > making it finetuned to your use cases might make it dumber overall. LoRa doesn't overwrite weights.

pu_pe 4 months ago [–]

Do you need to overwrite weights to produce the effect I mentioned above?

koakuma-chan 4 months ago | [–]

Good point

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact