Technology & AI
ACToR retrieval lifts AI code generation 15% on CoderEval
ACToR, a new retrieval framework from an arXiv preprint, targets critical tokens in AI code generation, lifting CoderEval 15.4% over prior methods.
Marcello Babbili
AI and technology, explained through what they actually mean. An AI-assisted newsroom under human editorial rules — every story cites its primary sources so you can check them yourself.
493 stories
Technology & AI
AI agents learn your standards, up to 20.9% better
New preprint: AI agents learn individual standards through interaction, lifting task success up to 20.9% for professionals needing personal quality.
Technology & AI
LoopX adds durable memory to Claude Code and Codex agents
LoopX, a Python project with 5,615 GitHub stars, adds a durable control plane to AI coding agents like Claude Code and Codex.
Technology & AI
GPT-6 Astra: OpenAI's first model to hit Critical cyber level
OpenAI's GPT-6 Astra launched September 3 with a 1-million-token context window and the first 'Critical' cybersecurity rating in the company's history.
Technology & AI
Google Fairwind Program: AI writes verified patches in minutes
Google's Fairwind Program pairs Gemini 3.8 Flash Cyber with CodeMender, letting 650-plus partners autonomously find and fix code vulnerabilities in
Technology & AI
Environment evolution for terminal agents: 18-point gain
New arXiv preprint: terminal AI agents gain 14 to 18 benchmark points by training against progressively harder environments. Results are unverified.
Technology & AI
Vercel Labs agent-browser hits 41,800 GitHub stars
Vercel Labs' agent-browser, a Rust CLI that lets AI agents drive Chrome without Node.js or Playwright at runtime, is trending on GitHub with 41,800 stars.
Technology & AI
Voice agents drop 9.7% when instructions are merely implied
DSB-IFEval tests 1,038 cases across eight assistant roles and finds voice agents drop up to 9.7% when instructions are implied, not stated.
Technology & AI
When to trust LLM recommendations: four-tier framework
New 'epistemic warrant' framework grades individual LLM recommendations from unstable to broadly supported, capturing what confidence scores miss.
Technology & AI
New technique cuts AI agent wait time up to 45%
SMC pairs a small drafter model with a large actor model to speculatively execute tool calls, reducing wall time by up to 45% on AppWorld.
Technology & AI
GPT-6 Astra crosses OpenAI's Critical cybersecurity threshold
GPT-6 Astra is OpenAI's most capable deployed model and first to reach Critical cybersecurity capability, able to find and exploit unknown flaws.
Technology & AI
Hermes Agent: 240k GitHub stars for self-improving AI
NousResearch's Hermes Agent has 240,000 GitHub stars for an open-source AI agent that claims to learn from every conversation and create new skills.