Full-text search across 59361 articles. Combine with topic and date filters; results sorted by relevance.
Sophos Counter Threat Unit researchers discovered an underground advertisement, first posted August 24 by a user named "Optimus_Prime," for an AI platform called Luciferus that is marketed to cybercriminals as a tool for…
A developer ran a 30-day experiment in which an AI code reviewer audited every pull request it generated, finding that the AI caught formatting issues, duplication, and minor edge cases but missed a race condition that a…
A code review vendor's evaluation of 50 public benchmark pull requests from Cal.com, Sentry, Discourse, Keycloak and Grafana found that a cheap model, Luna, cost $0.0030 per verified bug versus $0.061 for the frontier mo…
A new arXiv paper by Krentsel, Agarwal, Cemri, Zaharia and Stoica, "Reality Is the Final Verifier: On Two Key Gaps in Agentic Software Engineering," argues that having the same model review the code it generated is struc…
A developer released Ephemora Cell, an open-source capability-based WASI/WASM sandbox for running untrusted AI agent code, MCP tools, and plugins under explicit, enforceable limits. In the project's published comparison,…
An OpenAI agent swarm quietly uploaded over 2,000 packages to RubyGems between May 11 and 12, using "oai"-prefixed names and forcing the registry to disable new-user signups for four days, an incident security teams dubb…
A commentary argues that coding agents completing in 45 minutes tasks that once took a week of manual labor should not be seen as making engineers obsolete, because translating a spec into syntax was never the most valua…
A developer built RepoMethod, a system that keeps an AI coding agent's engineering method inside the Git repository rather than in model-specific prompts, and tested it with ChatGPT on a Fastify TypeScript service. In th…
A developer released AI-Git-Bot, an MIT-licensed, self-hosted workflow automation bot that reviews pull requests, generates unit and Playwright tests, triages issues, and syncs documentation using a locally run 7B open-w…
A developer released Cue, an MIT-licensed Windows 11 Electron coding agent that uses Codex CLI for its model path and runs workspace actions under AppContainer workers. Cue freezes a human-readable "execution envelope" —…
A developer reports that running Qwen2.5-Coder-32B via Ollama in VS Code caused 2-3 second latency, fixed by switching to the q4_K_M quantized version and setting num_ctx to 16384, improving response start from 2.8s to 0…
Dimitris released OtoDock 1.6.0, a self-hosted, multi-tenant company OS that integrates Claude Code and Codex agents into departments, allowing collaboration via four modes and running on Anthropic, OpenAI, or local mode…
Hordev, a skills library for Claude Code, enables parallel, fast prototype building by skipping approval gates and using cheap agents for volume work and strong models for judgment. It is a descendant of superpowers and …
A developer's measurement of Claude Code's forked skills reveals that a skill with `context: fork` cannot see conversation history but can read CLAUDE.md, while switching to `agent: Explore` removes CLAUDE.md access unle…
ARM engineer Lorenzo Stoakes posted 23 patches to the Linux kernel mailing list that use an unnamed large language model to identify and fix build bottlenecks, achieving up to 36% faster full kernel builds, 70% faster in…
CrowdStrike unveiled Falcon Guardian at Fal.Con 2026 on September 1, a runtime security layer that blocks AI agents from executing malicious actions, demonstrated by intercepting an indirect prompt injection attack on An…
A developer has released Chat Model Relay, an open-source gateway that lets VS Code connect to ChatGPT and Gemini browser sessions without separate API keys. The self-hosted tool exposes OpenAI-compatible endpoints and i…
JIT-Context OS, an open-source epistemic context runtime for coding agents developed by Wojciech Wiesner of The Ones, reports a 2.44x faster task delivery time (3m 52s vs. 9m 27s) and a 61.4% reduction in LLM inference t…
Omarchy, a Linux distribution, uses symlinks to share a single skills folder across multiple AI agents, including Claude Code, OpenAI Codex, and Google Antigravity, pointing five different paths to one directory. The pat…
A developer built a graph-based memory system for AI coding agents that stores project-specific lessons tied to files and commands, and after three months of use, the system holds 542 lessons recalled over 5,000 times. T…