Updated
AI Language Model Safety news: companies & tools
Who's bringing AI to Language Model Safety: the companies, the tools and the money behind it.
Pulled from 125 sources
This month
LLM & Text Generation1 min read
protecting qwen3-8b from gcg based persona jailbreaks by steering with a linear direction
LessWrong
AI Research4 min read
LLMs respond differently to harmful prompts when AI watermarking is used
Ars Technica
