Showing stories from 2025-03. View all
Will AI be crueler than man?
Mechanistic interpretability is the science of understanding how AI works internally, and Neuronpedia is a interpretability platform with APIs and tools to explore, share, and steer AI models. We're open sourcing it today along with 4TB of interp data. Blog post here: <a href="https:/...
AI agents now have impressive reasoning capabilities. This raises an important question: how dangerous are these AI agents at identifying & exploiting web vulnerabilities?<p>We created CVE-bench to find out (I'm one contributor of 16). To our knowledge CVE-bench is the first benchmark using...
Over the past few weeks, I’ve spoken with several VCs who confidently claim that companies won’t need to hire anyone in the next year or two because AI will handle everything.<p>Even Bill Gates recently said we might all be out of work soon and won’t need to do anything in an "age of abundance....
Currently, I use Perplexity or ChatGPT via the web prompt for small coding tasks, but sometimes I'll use Ollama. Stuff like writing a shell script perform some task, or maybe a small Python function. I'd like to get to the next level, but I don't know where to start.<p>What are some...