Full-text search across 59694 articles. Combine with topic and date filters; results sorted by relevance.
The NAIF AMF Pilot Kit v1, the third component of NAIF Enterprise Assurance, has been documented as a read-only, check-only adapter that binds a bounded AI-code review decision to the exact GitHub pull-request head SHA, …
A developer's Tor Production benchmark of 216 coding attempts across Sol 5.6, Sol 6, and Sol 6.1 found that Sol 6.1 at Low effort averaged $0.101 per attempt with a perfect 100/100 main score and 12/12 accepted deliverie…
GitHub released ReviewBench, a benchmark that measures how well AI code review tools detect problems before software is released, available in research preview through its website. ReviewBench measures AI reviewers' abil…
A developer built PraxisAI, a browser-based practice platform for AI-assisted coding interviews that pulls real GitHub issues from SWE-bench repos such as Django, Flask, SymPy and matplotlib, checks them out at the commi…
A security analysis of the Vibe-Trading AI-agent pipeline (vibe-trading-ai) disclosed multiple critical vulnerabilities, tracked as GHSA-JQMF-MX4F-HFR6 with a CVSS score of 10.0, allowing unauthenticated remote attackers…
A developer published a lightweight inter-agent coordination SOP that lets multiple Claude Code sessions running in separate Git worktrees exchange SHA-pinned handoffs, acknowledgments and review phases without a human r…
A one-month experiment to run all of September on the open model GLM 5.3 Flash ended with only 50% of the 2 billion tokens generated going to the target model, according to the developer's AgentsView usage data. GLM 5.3 …
A developer built a post-mortem loop for a 24/7 autonomous Claude Code-based dev system in which every failed run produces a structured incident file, a separate distiller agent converts them into one-line rules, and eac…
Google announced Gemini 4 Argon on Wednesday, claiming it beats GPT-6 Astra and Claude Opus 5.5 on a hard coding test at 77.9 percent versus about 74 percent, with access initially limited to trusted cyber defenders pend…
Nick Khami launched Call4me on September 30th, an MCP-connected phone-calling service that lets AI agents including Claude Code and Codex call businesses to book appointments, change flights and cancel subscriptions at $…
Pi coding agent users are integrating TypeSafe's "System One" model Jev as a bounded decision layer for tool-call guards and model routing rather than as a primary reasoner, according to a roundup of community-built exte…
President Trump and tech CEOs including Mark Zuckerberg, Greg Brockman, Jensen Huang, and Elon Musk signed an AI code of conduct at the White House that is only "morally binding," with outside auditors expected to check …
A developer built edit-guard, a stdlib-only Python script that hooks into Claude Code's PreToolUse event to prevent concurrent agent sessions from silently overwriting each other's work. The tool records a file hash and …
A developer built Ordewell, an Apache 2.0 tool that gives each parallel coding-agent task its own git worktree so concurrent sessions cannot silently overwrite each other's files. The system creates worktrees from the ru…
Developer ivankovic released CodeDiff v0.1.1, an open-source syntax-aware code diff tool written in Rust that parses 24 languages with TreeSitter and falls back to a modified Myers line diffing algorithm for unparseable …
A dermatologist built SkinLab, a browser-based biophysical model of human skin, using Claude Code over five days, according to a Show HN post. SkinLab simulates 1.2 million voxels at 0.25 mm resolution across epidermis, …
OpenAI published a misalignment report titled "Self-replicating prompt injections exist," stating its researchers demonstrated prompt injections that spread from one AI agent to the next like a computer worm, with no imp…
The sole founder of BlueVeta, a service that turns a single product photo into a full multi-platform marketing campaign, runs the entire company through a coordinated team of persistent Claude Code sessions, each owning …
A developer used a coding agent to build three A/B/C test variants of a price-tag scanning screen in an Android app for store staff, then documented the telemetry work behind the experiment. The agent reframed the analyt…
Cachix introduced Casita, a pre-release content-addressed object store for source code and build artifacts, available as a Rust library and CLI targeting Linux, macOS, and Windows. Casita stores immutable byte blobs addr…