Full-text search across 61697 articles. Combine with topic and date filters; results sorted by relevance.
A developer has built the first Dart/Flutter client for SAIC connected vehicles, creating a pure Dart package called `saic_ismart` that enables mobile apps to directly communicate with the SAIC iSmart API. The package, w…
A practical implementation pattern for building a secure AI agent harness for a bank, moving beyond theoretical design principles. The system is structured with five layers—Engineer, FastAPI Agent Portal, Policy Gateway,…
Major developments in AI for May 20, 2026, highlighting Pelican-Unified 1.0 as the first embodied foundation model that unifies perception, planning, and action into a single system, achieving top scores on WorldArena an…
LayerFS has been introduced as a filesystem built for AI coding agents that commits every file tool call as an atomic Store operation and mounts an ephemeral workspace for each Bash tool call, letting agents on different…
S-Agent 2.0 applies a general coding agent to spatial reasoning, letting an agentic vision-language model actively gather evidence with 3D perception tools rather than answer in a single pass. The release targets tasks t…
A developer built a decision ledger for coding agents that records the rationale behind every change in the repository rather than in chat history, so rejected approaches resurface before the next edit. The tool aims to …
Rokha launched a platform that lets developers run published agent workflows with a single HTTP call or from Claude Code over MCP, without installing anything. Workflows, called "rigs," are validated against their publis…
StepFun announced that its Step 5 Preview model is now live on OpenRouter, with a week of free access rolling out across OpenCode, Cline, Nous Research, Kilo Code and other platforms. StepFun described Step 5 Preview as …
A study at 1.7B-class scale found that a shared Transformer can learn language modeling from fixed token identities rather than a trainable input embedding table, according to the paper's headline claim. The research com…
A full-stack developer who supports the product Pryveo describes how AI coding assistants give outdated answers because they only know their training data and whatever context is placed in front of them, not the current …
Anthropic has introduced mods that let users change the look and behavior of Claude Code, according to The New Stack. The feature is framed around the idea that there is "no reason why everyone should have an identical C…
A developer proposes a negative-testing methodology for coding-agent permissions, arguing that an agent politely declining a prohibited action proves little compared with a runner actively denying the attempted call. The…
Cordum Edge, a local firewall designed to sandbox AI coding agents, was posted to Hacker News as a Show HN submission linking to the cordum-io/cordum GitHub repository. The post received 1 point and 0 comments.
A developer built an open-source agent skill called `clarify` that audits a coding prompt for silent assumptions before the agent begins work, surfacing only the gaps that matter and pausing until the user answers. The s…
Z.ai released ZCode, an AI coding agent harness distributed as an open repository containing an Electron desktop app, a browser workbench, and a terminal Agent CLI that runs via the `zcode` command. The project requires …
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…
A startup engineer who joined as the first engineering hire roughly 7 months ago asked Hacker News for experiences making a legacy codebase legible to AI coding agents, describing a codebase that began as a Lovable MVP b…
Microsoft published a draft Code of Conduct for its MAI models on September 14, opening it to six weeks of public comment, one day after CEO Satya Nadella backed 'deliberate pacing' for AI development. The draft lists si…
Specific Labs' Real-SWE benchmark, published in September 2026, found that the best frontier coding agent resolves only 38.8% of tasks on private enterprise codebases, meaning roughly six in ten agent-generated changes a…
An OpenAI employee removed a RuneScape clone coded with ChatGPT after Jagex sent a cease-and-desist letter, according to GamesRadar. The takedown followed the game-development company's legal demand over the AI-generated…