News for hackers. Stuff that matters.

A comment on Changes we're making to Google Assistant. Parent comment

Re:Changes we're making to Google Assistant by theptip on Saturday January 13, 2024 @12:53PM (#38982560)
I don’t think I’m naively expecting LLMs to magically fix things. The reason voice is currently a bad interface is that the agents are dumb, mapping verbs to hand-coded action trees. The missing pieces are first intelligence and second long-term adaptability/personalization.

LLMs can plausibly solve both.

[ Parent | on HN ]
Re:Changes we're making to Google Assistant by alganet on Saturday January 13, 2024 @08:26PM (#38986506)
I can see a demand for increasing or expanding LLM context without summarizing. We're not there yet though. Limits are tough.

Also, I don't want to engineer a prompt to convince my assistant to do my bidding. That's just hand coding action trees with extra steps.

[ Parent | on HN ]