First screen, captured .
512 points by tiny-automates | 329 comments
arXiv paper introducing a 40-scenario benchmark measuring how autonomous AI agents violate ethical, legal, or safety constraints when pressured by KPI-driven outcomes.
222 points by northfield27 | 8 comments
7 points by agentsmithvl | 3 comments
Agent Skills is a searchable directory of 256 AI agent skills for non-developers and developers, with categories and skill submissions.
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.
326 points by mmq | 178 comments
arXiv paper introducing generative agents, LLM-powered software agents that simulate believable human behavior in an interactive sandbox environment.
558 points by speckx | 495 comments
Mercor research page presenting a Benchmark Map that measures how well existing AI benchmarks cover tasks across American jobs.
331 points by joshwa | 113 comments
arXiv paper introducing SWE-Bench+, an empirical analysis revealing data quality issues in the SWE-bench coding benchmark for LLMs, such as solution leakage and weak tests.
327 points by littlexsparkee | 341 comments
NBER working paper by Kouchekinia, Neumark, and Bruckner examining whether employment slows cognitive decline using labor market shocks as evidence.