Full-text search across 12889 articles. Combine with topic and date filters; results sorted by relevance.
A developer exploring Agentic AI unexpectedly deepened their software engineering skills, picking up Docker, GitHub Actions, Git best practices, and deployment workflows. The journey, which started with LangGraph, led to…
Product teams should treat the software factory as an operating model they can reshape from inside, according to a blog post on agentic engineering by Robert Glaser. The post argues that as AI agents produce more code an…
Liquid AI, an AI company, released an open-source byte-pair encoding (BPE) tokenizer trainer called toktoktok on GitHub, built autonomously by two coding agents using Claude Opus 4.5 and Codex with GPT-5.2 in an experime…
An engineering team spent eight months building an agent framework that treats AI agents as employees rather than chatbots, giving each agent a defined identity, authorization boundary, and machine-readable AgentCard des…
Thinking Machines Lab released Inkling, a new multimodal mixture-of-experts model for token-efficient reasoning and native multimodal understanding, and Together AI made it available on its inference platform on day 0. I…
FusionAuth documentation engineer Nathan Contino reports that AI agents cannot yet produce consistently accurate documentation, so the company keeps long-form content, tutorials and release-note editing human-written whi…
A developer has released a local plugin for Claude Code that logs every time a user swears at the AI coding assistant, storing the data locally in a JSON file with no cloud uploads or telemetry. The tool, described as a …
A new analysis from GTM Partners finds that AI underdelivers in go-to-market teams because they lack the context availability and task clarity that engineering teams get for free from codebases and specs, and it recommen…
MAI released OpenCode Mentor, an opinionated OpenCode configuration that routes software-development learning through a mentor-first agent named Rob rather than generating code directly. The configuration defines five ag…
Salamanca City Central School District in western New York has paused a planned fall 2026 pilot with Realbotix's humanoid robot Optio and M-Series unit, citing the need for enhanced student data privacy agreements with t…
A developer built CosySim, a local-first, open AI simulation framework featuring a living cyberpunk city where every NPC is a governed LLM agent with persistent memory, a real economy, and day/night cycles. The system in…
Developer AltanS released ColliePWA, a self-hosted progressive web app that provides mobile access to terminal sessions and coding agents, built over the last couple of weeks and posted to Hacker News as a Show HN. The t…
Vercel Chief of Software Andrew Qu argues that AI agents represent a new form of software distinct from traditional web applications, citing their dynamic interaction and unpredictable outputs. Qu led the development of …
A self-taught hobbyist developer from Germany has built Phoenix, an experimental local multi-agent AI assistant currently at version v0.05-Alpha, featuring 28 independent modules and 8 separate SQLite databases to isolat…
Anthropic's new AI model, Mythos, autonomously discovered over 2,000 previously unknown software vulnerabilities across all major operating systems in seven weeks, developing working exploits without human instruction. O…
A third stance toward artificial intelligence—neither doomer nor zoomer—is necessary to move beyond the primitive defenses of projection and splitting that dominate current discourse, according to a psychoanalytic analys…
On July 30, 2026, developer jjba23 launched lambdock, a Wayland-native desktop dock written in C, GTK4, and GNU Guile Scheme, available on Codeberg. The dock features a REPL, fluid physics animations, and runtime hackabi…
The US Commerce Department ordered Anthropic to disable its Fable 5 and Mythos 5 AI models for all foreign nationals, citing national security concerns over a jailbreak that could weaponize the models' vulnerability-hunt…
A developer writing on tamiz.pro describes the 'Code Exorcist' pattern, an autonomous closed-loop debugging agent that fuses static analysis, runtime telemetry, sandboxed execution, and LLM-driven reasoning to observe, h…
A technical explainer from tensor.khalilli.ai demonstrates that the floating-point arithmetic error causing 0.1 + 0.2 to equal 0.30000000000000004 and training loss to become NaN at step 40,000 stems from the finite numb…