TL;DR: Applications are now open for the Secure Program Synthesis Fellowship, powered by Apart Research and Atlas computing. Apply by Sunday the 31st of May. This fellowship offers part-time research opportunities on mentor-led projects at the intersection of formal methods, AI systems, and security. Participants work in small teams to...
TL;DR: We present a conceptual discussion and loose formalism regarding Expert Orchestration, emphasizing on judges. We motivate the problem of finding the best way of combining multiple judges scores and present a solution to it: learning the function. Then, we present the architecture and low level details of the experiments...
TL;DR Context. Feature‑steering promises a cleaner, more interpretable way to shape LLM behavior than other methods, such as plain prompting. But does it actually work better? What I did. Benchmarked Goodfire's Autosteer method against three others (Simple Prompting, Agentic, Combined Approach) + a control, on 10 steering goals × 30...