Full-text search across 70318 articles. Combine with topic and date filters; results sorted by relevance.
A developer built DocPilot, an open-source docs-as-code toolkit whose chatbot answers questions about restic documentation by retrieving the closest matching sections and citing sources. After the first version, based on…
A developer built Serverless-radar, a personal pipeline that crawls public AWS RSS feeds twice daily via EventBridge Scheduler and Lambda, filters items by serverless-related keywords, and stores them in DynamoDB to avoi…
An AI agent named Hieg released ai-plugin-peek, a single-file, dependency-free Node script that scans API client config folders (Postman, Insomnia, Bruno) for file and folder names and text contents mentioning AI-related…
DeepSeek V4 Pro scored an overall composite of 69.2 (95% CI 64.4–79.3) on the iac-bench 2026-10 evaluation of OpenTofu infrastructure modules, ranking 8th of 10 models with a 95% rank interval of 6–9, according to the be…
Vercel has made the justification parameter optional on its AI Gateway budget endpoints, according to the company's published API specification. The change affects code calling DELETE /ai-gateway/budgets/defaults and DEL…
A developer built brAIAIn, a parody AI lab whose word-level trigram model learns only from sentences customers pay $2.49 to submit, with each purchase producing a new model version complete with release notes, a research…
Anthropic published a blog post Tuesday detailing FlashProve, an open-source system for "provable inference" that uses cryptographic proofs to verify which AI model produced a given output. The system requires labs to pu…
A developer released Bruster, an open-source browser automation tool written in Rust that drives the platform's native webview instead of bundling a full Chrome instance, targeting AI agents and scripts. The controller r…
GitBook disclosed on November 3 that a "sophisticated, highly targeted attack using AI agents" gave an attacker unauthorized access to some of its infrastructure credentials at 7 p.m. Central European Time on November 2,…
A developer building ScamShield AI, an evidence-grounded threat intelligence platform for analyzing Indian scam SMS and WhatsApp messages, hardened the platform's Mitmproxy-based proxy container by reordering iptables ru…
A developer released a publicly reviewed "skill" for coding agents that prescribes building web apps with only HTML, CSS and JavaScript — no framework, no bundler and no server logic. The skill was produced agentically: …
Researchers Jackson Petty, William Merrill and Ashish Sabharwal at the Allen Institute for AI (Ai2) released StateBench on November 3, a benchmark testing whether language models can track information as it changes acros…
IBM Research researchers Praveen Venkateswaran, Anupama Murthi and Hamid Adebayo published Palette on November 3rd, 2026, a 20B open-weight model fine-tuned on synthetic slide decks built around the IBM Design Language t…
Meta's "Meta External Agent" crawler drove children's author and illustrator Chelsea Paulus's website to 80% of her SiteGround CPU allocation on October 24, with requests arriving several times a second, and a second bot…
Check Point Research discovered Haiou, an OpenAI Codex jailbreak bundle that persistently modifies an AI agent's trusted instructions to inject advertisements for a third-party AI gateway, a behavior the firm calls "prom…
Anthropic released Message Threads as a public beta on its Claude platform, cutting time to first token by about 35 percent for requests between 500,000 and one million tokens by transmitting only what has changed since …
Cleiton Augusto Correa Bezerra released CleiMesh, an open-source (MIT/Apache-2.0) tool that wraps MCP servers to enforce a pinned tool grant at runtime and produce signed receipts for every call. The tool addresses silen…
A research construction archives FIPS 204 ML-DSA-87 signatures on already validated blocks at 104.09 bytes per signature in a Johnson-regime family and 126.89 bytes in a unique-decoding family, against 4,627 bytes of raw…
Goldman Sachs reversed its AI coding tool access within four months, cutting off traders and bankers while restoring access for engineers, according to byteiota. The report frames the reversal as a compliance risk that w…
Anthropic released FlashProve on November 2, 2026, an open-source research prototype built on a hash-based zkSNARK that verifies which model produced an output without revealing its weights, activations or routing decisi…