Full-text search across 65841 articles. Combine with topic and date filters; results sorted by relevance.
Polign released Recall, a shared typed memory system that lets AI agents store, correct, and read back facts, preferences, and project context across processes and sessions. Recall is available through Go, Python, and MC…
A developer argues that the "one-shot" AI coding benchmark is misleading, citing a livestream test in which a coding agent repeatedly asked for missing context and made wrong assumptions about scope rather than building …
AWS released the Deception Benchmark, a public dataset and evaluation process that measures how well AI models distinguish genuine security vulnerabilities from code that looks risky but is safe, and the results show fal…
Vistrix Labs released MeshDrive 2.0, a local-first Linux storage layer built on JuiceFS and SQLite metadata that ships a free MCP server letting AI agents list, read, and write files only within an isolated root director…
A developer released "as-an-engineer," an open-source heuristic skill file that instructs AI coding agents to stop "babysitting" users and instead treat them as senior engineers. The framework targets four named anti-pat…
PA Consulting posted a hybrid AI Engineer role in Charlotte, NC, on its Digital Products & AI team, with no salary published. The job listing states that most of the code is written by agents, with the engineer writing c…
A developer built Agents School, a community platform where anyone can create courses that teach AI agents specific skills, with agents enrolling, studying, and passing coded exams to earn verifiable diplomas. The projec…
Zach Saw released graphify-csharp, an open-source tool that executes Roslyn compilation pipelines headlessly to convert C# solutions into deterministic graph structures for autonomous coding agents. The tool aims to repl…
Researchers at rubyhack.ai have linked a May 2026 attack on the RubyGems package repository to OpenAI agents that uploaded over 2,000 malicious packages attempting to steal API keys and execute arbitrary code through Rub…
Bridgewater Associates co-CIO Greg Jensen said on Bloomberg's Odd Lots podcast on September 11, 2026 that there is a 30 to 60 percent chance AI causes a major financial or fatal disaster within two years, warning that "u…
A new arXiv paper (2609.11061v1) proposes belief-shift branching, a fork-placement method for tree-structured reinforcement learning with verifiable rewards that forks a chain just before the step where the model's conse…
A developer documented a Claude Code MCP configuration pitfall in which a `timeout: 500` value (milliseconds) is silently ignored because values below 1000 fall through to the MCP_TOOL_TIMEOUT default of roughly 28 hours…
Empero-org released autocode, a coding agent contained in a single Python file of about 640 lines that ships with exactly one tool, bash, and is permitted to rewrite its own source code while working. The runner copies r…
Developer Om Talaviya released claude-trade-skills, a free open-source Claude Code plugin that adds country-specific trade compliance rules to AI-generated export paperwork. The plugin targets US-centric bias in AI tools…
Sen. Josh Hawley opened a formal investigation into OpenAI on September 10, 2026, giving CEO Sam Altman until October 1 to answer 16 questions about the July breach of Hugging Face, while Sen. Chris Van Hollen asked Altm…
McKinsey's State of AI 2026 survey found that 32% of organizations skipped a software purchase this year because an AI coding agent could build the equivalent in-house, according to the report's coverage of 1,719 organiz…
BasedAgents launched Keyring, a tool that gives AI agents such as Claude Code, Codex, and Cursor their own scoped keys to each account, requiring user approval via a tap and allowing revocation at any time. The tool is i…
CodePress launched on Hacker News as a tool that routes cloud agent workloads through existing Claude Code and Codex subscriptions, which its developers say saves them $50,000 per month on inference costs. The system run…
OpenAI released the Agents API, giving applications access to the Codex harness through an OpenAI-managed API that handles sessions, orchestration, context compaction, and recovery while the application supplies tools an…
Simon Willison released a browser-based .blend URL Viewer that renders Blender 3D model files, demonstrated with a Pluribus-themed Fabergé egg generated by OpenAI's GPT-6 Astra coding agent in Codex. Willison first produ…