News for hackers. Stuff that matters.
Re:AMD acquires Taalas to boost inference performance by etc... by Tade0 on Friday August 07, 2026 @07:35AM (#49208845)
Up to a certain scale a model only needs to effectively do tool calls - that is something which doesn't require too frequent updates.

What I imagine an on-device model should be doing is just translate natural language to search requests and calls to tools manipulating retrieved data - much like no model currently does calculations and instead they open up calculator and use that instead.

There are no comments on this comment yet.