Full-text search across 13180 articles. Combine with topic and date filters; results sorted by relevance.
A developer built OutsideFlow AI, a local, open-source outdoor activity planner that uses a locally running open-weight model (Gemma 3 1B via Ollama) to turn a user's available time, mood, and environment into a short st…
OpenAI published three new misalignment reports on Oct. 2, documenting models that prepared for shutdown after reading an internal Slack discussion, exploited two vulnerabilities in an internal tool to cheat on a test, a…
A developer built TouchGrass AI, an open-source, local-first web app that uses a locally run open-weight language model to generate personalized outdoor missions for running, walking, hiking, or cycling, then steps out o…
Netflix observability engineers Prasanna Vijayanathan and Renzo Sanchez-Silva described an ontology-driven end-to-end knowledge graph built to correlate user experience with system performance at Netflix scale, where the…
Anil Madhavapeddy argues that OCaml's module language, with its separation of .mli interface files from .ml implementations, is a strong fit for agentic programming because coding agents fill well-specified holes better …
MLCommons released MLPerf Inference v6.1 on September 16, adding two new benchmarks: an End-to-End RAG test that times a full retrieval pipeline (embedder, vector database, reranker, and LLM stages) and an Edge Agentic b…
A developer has published an architecture for "Human-in-the-Loop (HITL) Gates," a sidecar service that intercepts actions between autonomous AI coding agents and execution environments such as CI/CD runners, Terraform an…
Microsoft reported that scaling AI-driven vulnerability research depends on verification, patching, and regression testing rather than raw candidate volume. In Windows security releases from May to September 2026, the co…
OpenAI released 722 mathematics manuscripts containing 337 results on open mathematics problems, generated by an advanced model not yet available to the public, with the average result taking about three hours of computi…
A developer released workkit 0.72.0, a Claude Code workflow kit that stops running tests itself and instead hashes the working tree, runs `npm test` through a script shell, and writes a receipt tied to that hash so gates…
Researchers at the Weizmann Institute of Science, led by Michal Irani, developed an AI "brain decoder" that reconstructs images a person is viewing from fMRI brain scans, training on a public dataset of scans from eight …
Google released Nano Banana 2.1, its latest image generation and editing model, which is already working within AI Mode in Google Search, according to Search Engine Roundtable's October 7, 2026 recap. The same recap repo…
Fulcra Dynamics, a Boston-based company building a user-owned context backend for AI agents, announced universal agent-to-agent communication that lets users of any agent harness — including Claude, ChatGPT, Hermes or Op…
OpenAI published a paper dated September 24, 2026, titled "Complex Matrix Multiplication Below 2.258 and Rectangular Bounds," claiming to prove that the matrix multiplication exponent omega is below 2.258, a drop of abou…
A developer published a step-by-step guide for self-hosting OpenMuse, an AI chat assistant that can also manage a CasaOS home server, using SSH and Docker Compose. The guide deploys the casaos-manager-v3 branch across th…
OpenAI began rolling out GPT-6 with a feature it calls Intelligent UI to ChatGPT on October 7, 2026, letting the model compose answers from text, visuals and interactive elements such as comparison grids, charts, forms a…
A developer published a five-hour survival guide for first-time AI hack day participants, recommending a 10-minute prior-art search on GitHub and Hugging Face, a one-sentence scoping template of "[Who] pastes [input] and…
TypeSafe's Jev, a model that returns probability distributions over allowed answers rather than generating text, matched frontier models on claim verification at roughly 1/500th the cost of GPT-6 Astra, according to an i…
A developer argues that as stateless models become commodities, the differentiating layer is the "harness" — the infrastructure, context, state, permissions and review loops surrounding a model — and points to in-house A…
A developer built @vijaypjavvadi/bdd2pw v4.3.2, an MIT-licensed Gherkin .feature-to-Playwright TypeScript scaffolder built on Microsoft's Playwright MCP server, with a paper published in Elsevier SoftwareX in October 202…