This is so powerful. Exa (@exaailabs) is like Perplexity-as-a-service. The infrastructure to ground your AI products on real world data and facts. This open source demo detects hallucinations in a given piece of text: https://t.co/4vnmiFCb3y

New Anthropic research: Persona vectors. Language models sometimes go haywire and slip into weird and unsettling personas. Why? In a new paper, we find “persona vectors"—neural activity patterns controlling traits like evil, sycophancy, or hallucination. https://t.co/PPX1oXj9SQ

Hallucination in LLMs A comprehensive survey (50+ pages) on hallucination in LLMs. Most of the LLMs and prompting approaches we use today lead to some form of hallucination so it's becoming increasingly important to test for this. The first step is to be aware of and detect these issues and... See more