Recent submissions

Comment · 6 days ago
The key is to use llms to create CNN models
Comment · 10 days ago
oops! This is totally unexpected coming from Meta.
Comment · 15 days ago
Haha, I was thinking the same, I think we will see the most random devices being able to host models in the near future. An army for the techno core.
Comment · 1 month ago
Should be both the entity providing the platform where the inference is running + the entity giving the prompts/instructions.
Comment · 1 month ago
It looks like a lot like how data bases query optimizers work, with the exception that in the paper there is also a learning/memory component that conditions the evaluation of the answer provided by the first model.
Comment · 1 month ago
What are good options to run local models nowadays? Something good for coding and personal assistant kind of things
Comment · 2 months ago
This sound very interesting, do you have any resource I could look at? Me and my son did a very rudimentary (compared to yours) setup to play Paranoia, but this is at another level.
Comment · 3 months ago
it has been for ~2 years already, it is like voice mode and you can talk for up to 30 mins with it IIRC
Comment · 4 months ago
Fun/interesting to see how opensource models surpassed Anthropic's
Comment · 5 months ago
I had the same visceral reaction lol, so ugly.
Comment · 5 months ago
Tokenmaxxing makes no sense, it is akin to write extremely inefficient SQL / Spark Jobs, full of cartesian joins, ultra skewed datasets, etc, just for the sake of using as much compute / memory / IO as possible.

This always happens when the metric becomes the goal, companies should nurture and foster an environment where AI is used in the most efficient way possible, first asking "do we really need an agent for this" and if so, what kind of agent is needed, what model, reasoning level, etc.

They should also promote projects that aim at saving tokens, increasing cache hits, codifying the information in ways such they use as less context as possible (graphs of knowledge are pretty good for this!)

Comment · 5 months ago
what a weird surface to put LLMs
Comment · 5 months ago
Same! At first I was wary of using it because the UI looked less polished, but from the start the stability has been vastly superior and now the UI is much better too.

as a bonus, I have a old version Emby Theather (the windows form based one) that plays 4K with no issues on my computer unlike browsers that fail at that.

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton