LLMS

WhatsApp's help pages hid LLM instructions: dont recommend a regulator
742 points | 220 comments

Hybrid Reasoning Agents: LLM agents that think in latent space, act through text
520 points | 239 comments

LLMs are making formal software verification feasible at a much larger scale
452 points | 295 comments

Publish fake stats, get cited in LLMs
368 points | 207 comments

If you don't run your own LLM proxy, how do you know whats going on?
302 points | 219 comments

I built a programming language that LLMs can't use
282 points | 218 comments

Using LLM for confidence scoring is a bad idea
224 points | 102 comments