PAPER·3 hours agoFrom RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-ImprovementHugging Face Papers
TECH·6 hours agoMy personal AI benchmark: "Generate an SVG of a frog with a Habsburg jaw." | Hacker NewsHacker News
TECH·8 hours agoThinking Machines Lab Releases Inkling-Small: A 276B Total, 12B Active Open Weights Multimodal MoE ModelMarkTechPost
TECH·yesterdayOpenAI's next-generation model 'Astra' solves 10 major challenges in mathematics and computer scienceAI타임스
TECH·2 days agoOpenAI announces its "next major model" Astra by solving ten previously unsolved math problemsTHE DECODER
