GitHub - Page 4
Stories from GitHub come first, newest first, then stories from connected topics (coding agents, Developer Tools, AI Coding, GitHub Copilot, Open Source, AI Agents), each labelled with where it comes from. This view is not indexed by search engines.
Latest
AI Helps Log 98 Million Bat Calls Across 310 English Woodlands
A national woodland bat survey used AI to sort 98 million calls from 310 English woods, finding rare barbastelles and publishing the data openly.
Cursor Says Tampered Claude Code Extension Reached Up to 5,000 Users
A tampered Claude Code extension sat in Cursor's marketplace for about 11 hours on 29 October, reaching up to 5,000 users. How to check and clean up.
Tencent Says WorkBuddy Passed 9bn Tasks as It Previews Hy4 Release
Tencent WorkBuddy has handled over nine billion task requests since March, Tencent says, as it previews Hy4 and reports doubled overseas cloud customers.
Anthropic Expands AI for Science Credits to 20 Research Partners
Anthropic's AI for Science programme now runs through 20 partners. Imperial plans fungal work with Claude; Johns Hopkins will map tumours.
EveNet, a Physics Foundation Model, Learns From 500m Collisions
EveNet, an open foundation model pretrained on 500 million simulated collisions, picked out the Upsilon meson in CMS Open Data, a new paper says.
AGIBOT Proposes Worken, a Robot Work Metric, and Launches Link-U OS
AGIBOT Worken is a proposed measure of useful robot work. AGIBOT also launched Link-U OS 1.0, due to be fully open source by end-2026, and the G2 Max.
Factory Says Droid 1.0 Beats Codex and Claude Code in Its Own Tests
Factory's Droid 1.0 coding-agent harness makes scripted tool calls the default. Its own Terminal-Bench 4 runs put it ahead of Codex and Claude Code.
Hugging Face and Five US Universities Launch ProtoStar for Science
Hugging Face and five US universities have launched Project ProtoStar to make publicly funded science data AI-ready, starting with a climate challenge.
Meta Says LLM-Written Tests Helped Catch 74 Serious Privacy Bugs
Meta says its LLM-generated JiTTests, built to fail on risky code changes, helped catch 74 serious privacy bugs before they landed in H1 2026.
GitLab Orbit Goes GA, Claiming Up to 45x Fewer Agent Retries
GitLab Orbit, a context graph for AI coding agents, is now GA. GitLab says its tests showed up to 45x fewer retries and 4.5x fewer tokens.
Latest on TSN
Explore the TSN Atlas: Every topic we cover, mapped. Click a bubble to dive in.