A modern re-examination of the classic 1979 paper arguing against formal verification, exploring how AI coding agents and recent tooling advances have changed the landscape. The author revisits each historical objection …
This paper presents a validation-centric workflow for AI-assisted GPU porting of CReSS, a 250,000+ line legacy Fortran weather simulation code, achieving a 5.1× speedup while preserving scientific validity across 162 …
This paper studies harness design for LLM agents through the lens of inference-time trajectory alignment, showing that effective harnesses must align decomposition granularity with agent capability and guidance with task …
SkillOpt introduces a systematic text-space optimizer for agent skills that treats skill documents as trainable external state, using bounded edits, validation gates, and epoch-wise updates to achieve consistent …
An in-depth analysis of why AI adoption in the legal profession has been slower than expected, examining structural barriers including data monopolies, organizational resistance, billing model conflicts, and risk …
An in-depth exploration of world models in AI, covering their definition, implementation approaches (generative vs predictive), and practical applications from autonomous vehicles to interactive environments and agent …
A comprehensive research symposium featuring leading AI researchers discussing frontiers in artificial intelligence, from scientific applications and safety concerns to the future of AI development and its global impact.
Andrej Karpathy discusses the transition from traditional programming to AI-assisted development, exploring concepts like ‘vibe coding’ and ‘agentic engineering’ while examining how LLMs represent …
LeWorldModel introduces the first stable end-to-end Joint Embedding Predictive Architecture (JEPA) that learns world models from raw pixels using only two loss terms, achieving 48× faster planning than …
V-JEPA 2 is a self-supervised video model trained on over 1 million hours of internet video that achieves state-of-the-art performance on motion understanding and video question-answering tasks. The model can be adapted …
