Recent submissions

Comment · 3 years ago
It only takes a basic understanding of neural nets to recognize this as crankery. Giving an LLM a tricky question does not force it to do any more computation than a simple prompt. There is no conceivable way an especially difficult prompt would make the model crash.
Comment · 3 years ago
Comment · 3 years ago
Comment · 3 years ago
"Classify the following strings according to whether they represent Python programs which terminate..."
Comment · 9 years ago
Comment · 10 years ago
It's guaranteed to not exist in the training set (i.e. to not be a real GitHub repo that existed before 2015). But the model can certainly repeat itself.

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton