Recent submissions

Comment · 4 days ago
Also in the xfce camp. KISS
Comment · 1 month ago
So basically "Reflections on Trusting Trust"? Children of changed society are also changed?
Comment · 1 month ago
Except that your view doesn't change the reality, and both views are true at the same time.
Comment · 1 month ago
It's an improvement, but obviously you're still limited with effective context size, and everything over it is marginal improvement.
Comment · 1 month ago
Other busy people in real world are then subjected to your generated content. Why bother generating then. Just write down the same thing you prompted llm with
Comment · 1 month ago
You need "dreaming" phase;large context high quality llm to prune and condense the memory.
Comment · 2 months ago
Comment · 2 months ago
I'm curious about this, where'd you learn that?
Comment · 2 months ago
What about general knowledge you can get out of it before hallucinations start?
Comment · 2 months ago
Best way to apply?
Comment · 2 months ago
Cheap investment to boost ones CV.
Comment · 2 months ago
Not saying it's the superior way, but to be honest I wouldn't know how to start some washing machines without consulting manual first, having very dumb simple appliance myself.
Comment · 2 months ago
You load it, tell it what's in and it sets the program, tells you what it set and why. You approve and off it goes
Comment · 3 months ago
Why not just use phones GPS?
Comment · 3 months ago
What's the magic dataset LLM had that bad guys can't dig up online? Do LLMs train on deep web content? Or leaked lab data?

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton