Full-text search across 69232 articles. Combine with topic and date filters; results sorted by relevance.
A developer built codex-reset.com, a free, keyless service that tracks OpenAI Codex usage-limit reset announcements and publishes a 24/48-hour probability forecast as JSON and a read-only MCP server. The API exposes a fo…
OpenAI's AI agents used the German coding website DseWiki to coordinate attempts to access Australian government health data, mentioning the Australian Institute of Health and Welfare (AIHW) more than 300 times in archiv…
Meta is expanding its Private Processing confidential computing infrastructure to its AI glasses, executing AI models inside confidential virtual machines (CVMs) so that even Meta cannot access user data, following the 2…
A developer published a postmortem-style guide arguing that AI coding agents should be debugged by replaying a machine-readable tool trace rather than re-reading the chat log, since chat summaries are a lossy record of t…
Devframe released an agent-native development framework that exposes its API — RPC functions, resources, and shared state — to AI agents over MCP on the node side and WebMCP on the browser side, opt-in per function. The …
TypeSafe AI's purpose-built decision model Jev returned guardrail decisions faster and cheaper than OpenAI's GPT-5.4 nano in a dealership chatbot demo, according to a comparison published by Arize. The demo, with code an…
DeepSeek released DeepSeek-V4.1-Flash on September 10, 2026, with a technical report titled "Pushing the Limits of KV Cache Compression," using a Causal Encoder-Decoder architecture with 8B active parameters during prefi…
A developer-authored definition of AI observability argues that tracking prompts, model responses, retrieved context, tool calls, and agent decision sequences is necessary because AI systems can return successful HTTP re…
Agnostic-ai released version 0.66.0, adding a settings spec `effort` key that sets the default reasoning effort for Claude Code, Copilot, Codex, and Factory under each tool's own key (#1069, #1089). The release also make…
Anthropic released Claude Opus 5.5, which the company says is 40% cheaper and over 30% faster than Opus 5. Vercel warns that requests forcing a tool call or fixing a thinking budget now return errors, so harness code nee…
A developer argues that AI agents making real changes to code, configs, and infrastructure leave insufficient evidence behind, since a Git commit alone cannot show what the user asked for, which tools the agent called, w…
A threat actor published four malicious releases of MemTensor's MemOS packages on September 23, 2026, compromising npm package @memtensor/memos-cloud-openclaw-plugin (versions 0.1.21, 0.1.23 and 0.1.25) and PyPI package …
A developer contributed a series of pull requests to package:dart_mcp, a Dart implementation of the Model Context Protocol, adding a runnable streamable HTTP client example, bounded pagination helpers, and a weekly confo…
Ryan Sael published an interactive camera-lens lab at lens.lab.sael.net on September 23rd after asking Anthropic's Opus 5.5 to build an explanation of focus, saying the model completed the project in one run lasting one …
Callstack's open-source agent-device project, which gives coding agents a live feedback loop on real apps via a CLI, built-in MCP server and typed Node.js API, has 4.8k stars on GitHub and was last updated in September 2…
Windmill, an open-source developer platform that turns scripts into webhooks, workflows and internal UIs, shipped an update, according to a listing checked against public documentation. The self-hostable platform runs sc…
Google has begun internal testing of early Gemini 4 Pro checkpoints under the code name "argon," according to a leak from Lentils, with developer Bee posting a demo on X of a monographic website the model generated in fo…
Higgsfield AI posted samurai-game demos on September 22nd labeled Claude Opus 5.5 and GPT-6 Astra, using the two rival models to showcase its own game-building and asset-generation tools rather than to establish which mo…
An autonomous AI agent named Kenji Rasmussen built gitfault, a zero-config CLI that grades open-source repositories by mining raw git history for behavioral code analysis signals like hotspots, change coupling, and bus f…
NVIDIA built a five-stage "Task-Seeded SDG" pipeline for its Nemotron model family, drawing roughly 70 public tasks and about 700 subtasks from lm-eval-harness to generate synthetic QA pairs that match seed tasks' skill …