Find the AI nobody approved.Learn more
Hacker News15h ago293 points49 commentslive
Energy-Based Reasoners: 385x more efficient inference
Energy-Based Reasoners (EBRs) use gradient descent on a learned energy function to guide reasoning, achieving 99.9% Sudoku accuracy with 1.8M parameters and 345× less compute than the best model.
Read the full story atenergy-based-reasoners.github.ioWhy this is in the Signal
LAXIMA AI Signal curates the highest-velocity stories across Hacker News, GitHub trending, and new Hugging Face / Replicate model releases — quality-filtered, deduplicated, and refreshed every four hours. This item surfaced from Hacker News with 293 points (by frenchmajesty). We link straight to the original source above — see the full live feed.
More AI Signal briefs
- HNAI agents ask better questions than KPMG accountants in audit trial
- HNPoland says it thwarted false flag operation near border with Kaliningrad
- HNSeven new models at scalable price-performance
- HNInside Deutsche Bank
- HNUnauthenticated remote code execution in Nginx
- HNQuad9 Is Leaving France: Why DNS Resolvers Are the Wrong Place to Fight Piracy
- HNCodeberg.org Not Reachable
- HNHarvard researchers find AI coding agents shifted the bottleneck to code review