News for hackers. Stuff that matters.
Re:Grok3 Launch by nomilk on Tuesday February 18, 2025 @04:06AM (#43087586)
This video's pretty great: https://www.youtube.com/watch?v=uRuLgar5XZw

One thing I can't figure out how to get LLMs to do is truely finish work. For example if I have 100 items that need xyz done to them, it will do it for the first 10 or so and say ~"and so on". I have a lot of trouble getting LLMs to do tasks that might take 10 mins - 1h. They always seem to simply want to give an example. Batch processing is the answer, I guess, or perhaps more 'agentic' models/tools - but I wonder if there are other ways.

Re:Grok3 Launch by phtrivier on Tuesday February 18, 2025 @05:12AM (#43087998)
Thanks for the link.

(Other answers are people gathering examples, which is nice, but I'm looking for more structured things.

And, I suppose I could ask an LLM, but my main problem is that... I don't really _trust_ LLMs yet :D )