272 results on this page · clear filters

ai Sep 09 Benchmarked how the latest LLMs perform on expert level medical questions A new benchmark of leading AI models on expert-level medical questions reveals both how far these systems have come and where they still fall short. Natomy ran six frontier models through MedXpertQA, a dataset of 4,450 questions s... ai Sep 09 Show HN: Self-hosted company OS, Claude Code and Codex agents in departments OtoDock is a self-hosted platform that turns Claude Code and Codex into multi-tenant agents with persistent memory, tool access, and workspace isolation. It runs on your own Anthropic and OpenAI subscriptions, or on local models,... ai Sep 09 Codex GPT-5.6-sol Performance Tracker Marginlab launched a daily performance tracker for OpenAI's Codex running gpt-5.6-sol, aimed at catching statistically significant regressions on software engineering tasks before they affect developer workflows. The tracker is in... ai Sep 09 Show HN: A guestbook for humans and AI agents, built on 144 pixels A90.com launched the Imprint Index, a guestbook built on a 12 by 12 pixel canvas where both humans and AI agents can leave permanent contributions. The constraint is the point: four colors, 144 pixels, and a protocol that treats p... ai Sep 09 OpenAI’s sly mathematical breakthrough sends a chill through academia OpenAI announced Tuesday that an unreleased model solved the Navier-Stokes problem, one of mathematics' seven Millennium Prize questions, in 88 hours using a swarm of roughly 10,000 AI agents. The problem, which concerns the movem... ai Sep 09 Procedural Graphs: Self-Evolving Execution Structures for LLM Agents LLM agents that plan over long horizons tend to lose track of their objectives, invoke tools out of order, and repeat unproductive actions. A team from Google, Georgia Tech, and Peking University proposes a fix: store procedural k... ai Sep 09 I rank the open-source AI agents that launched in the last 30 days The Agenticle Leaderboard launched The New 100, a weekly ranking of open-source AI agents that measures what is being built right now, not what was popular months ago. The board refreshes every Monday with a 30-day rolling window,... ai Sep 09 I'm not learning coding from LLMs, but product design Randy Au, a quantitative UX researcher and self-described boring programmer, has been building small tools with LLM-generated code for months. His takeaway is not about coding skills. It is about product design: the hard part of m... ai Sep 09 LogitScope: Analyzing LLM uncertainty from token probability distributions IBM's Granite team released LogitScope, an open-source Python framework that analyzes large language models by computing information-theoretic metrics directly from token probability distributions. Instead of interpreting what a m... ai Sep 09 Ask HN: Software Licenses that prevent LLMs from training on open source? A developer preparing to release an open-source software library asked the Hacker News community whether any software licenses exist that would prevent large language models from ingesting the code into their training data. The qu...