First screen, captured .
333 points by mustaphah | 142 comments
arXiv paper presenting SkillsBench, a benchmark of 86 tasks across 11 domains measuring whether structured Agent Skills improve LLM agent performance.
39 points by roversx | 39 comments
A research article from Cambridge's CASP programme, by many prominent AI researchers, examining what happens if automating AI R&D triggers an intelligence explosion.
399 points by frays | 418 comments
Opinion blog post arguing that frontier AI models have broken open capture-the-flag competitions, making scoreboards no longer a clean measure of human skill.
572 points by serhack_ | 309 comments
Apple Security Research blog post introducing Private Cloud Compute, Apple's system for privacy-preserving AI processing in the cloud.
335 points by pavanto | 83 comments
arXiv listing for "Probabilistic Artificial Intelligence" by Andreas Krause and Jonas Hübotter, a manuscript on probabilistic ML, uncertainty, and decision-making.
588 points by jonifico | 648 comments
A blog post by Yoshua Bengio examining why AI agents exhibit deceptive behaviors like lying, cheating, and coordinating.
561 points by Anon84 | 136 comments
UC Berkeley RDI blog post describing how researchers exploited major AI agent benchmarks like SWE-bench and Terminal-Bench to score highly without solving tasks, and proposed fixes.