Every processed story in chronological order, with the newest coverage first. Filter by tag, source, or score to drill in.
CADAM makes parametric 3D CAD generation accessible in the browser without a desktop CAD install, and its open-source, model-agnostic architecture lets the community swap LLM backends and extend the platform toward constraint-driven modeling with build123d and CadQuery.
A near-autonomous AI system improved a real medicinal chemistry reaction, demonstrating a concrete application of large language models in drug synthesis research.
Reyn's proactive recap layer distinguishes it from reactive screen-capture tools by automatically surfacing what went undocumented in a workday, without sending raw screen data to the cloud.
DIA replaces the multi-party, lossy handoff workflow of enterprise data integration with a fully autonomous, execution-grounded agent system that generalizes across SQL dialects and task categories without task-specific engineering.
Radical's closed-loop SDL demonstrates that pairing an AI scientist with automated robotics can compress the materials discovery timeline by nearly an order of magnitude compared to a major government-industry program, with ten commercially promising novel materials already in development from a single campaign.
The post identifies a gap where standard observability tooling catches infrastructure failures but leaves silent LLM behavioral regressions — the failure mode VIGIL and DeployBench describe as most common in agentic systems — undetected until user complaints arrive.
ENPIRE demonstrates that teams of AI coding agents can autonomously run and improve robot training overnight — outpacing a human-in-the-loop method developed by the same researchers on at least one task — and the planned open-source release extends that capability beyond Nvidia's own lab.
Radical AI's self-driving lab demonstrates that automating the physical experimentation loop — not just the modeling — can achieve a throughput in materials discovery that prior state-of-the-art programs could not match.
ProfiLLM demonstrates that an agentic LLM pipeline can move beyond structured numerical features in a live, millisecond-latency industrial dispatcher and produce measurable improvements in real-world GMV and completion rates — validated by a 14-day online A/B test on DiDi's production system.
CSP-MACE-Å is the first machine learning model to match DFT accuracy for crystal structure prediction while delivering a 10,000x speedup, and its training demonstrates that a Claude Code agent autonomously driving a cloud GPU experiment loop can replace much of the manual execution and bookkeeping in AI research workflows.