Often I meet seasoned engineers who want to pivot into AI safety *research*. I think this is a mistake: safety is now a production problem and the world needs great engineers more than ever.
I wrote a short post expanding on this:
- it's time to make safety scaleWe’re giving out $1M in grants of free Silico usage for academic and nonprofit researchers focused on AI interpretability and alignment. We feel extreme urgency about advancing interpretability for alignment, and we want to help more researchers push it forward. 🧵
- a glimpse into the mind's eye of an LLMCan you see what an LLM is "thinking"? We tried: take a real direction that correspond to your prompt inside a Qwen2.5-VL, and optimize a blank canvas against it Built this on @GoodfireAI's new Silico! 🧵
- less slop, more scienceSilico, the platform for ambitious AI research, is publicly available today. AI is advancing fast. The tools to understand it need to advance even faster. Silico lets you interpret and train your models at frontier scale. Learn more + get access 🧵
- we are starting to debug models the way we can debug codeYou ask an AI model a question. Why does it answer the way it does? Using the model's own neurons, we can trace how it makes decisions — and steer it toward better ones. Case study: we tested an LLM and found that it sometimes endorses drunk driving.🧵 (1/5)
