Full-text search across 60665 articles. Combine with topic and date filters; results sorted by relevance.
An engineer at Softjourn nearly installed a malicious package recommended by an AI agent, but company policy requiring verification on GitHub prevented the installation. Separately, security researchers at Wiz identified…
Endor Labs has launched an AI-powered Static Application Security Testing (SAST) tool for C code that detects more vulnerabilities than traditional scanners without requiring a software build. By combining deterministic …
Meta's experimental vibe-coding gaming app Pocket is now rolling out to all U.S. users after launching in Brazil last month. The app lets people generate small, interactive games using AI prompts, which can be shared, re…
A developer introduced a method to compress agent and skill definitions for Claude Code and OpenCodeAI, reducing token usage by 80-95% while preserving capability. The approach retains role, workflow, constraints, and he…
A developer has outlined a DIY method for evaluating AI code review tools, arguing that vendor-published precision and recall numbers are unreliable because they are based on self-selected benchmarks. The method involves…
Anthropic's Claude Code now offers a 'Concise' output style setting, which makes Claude lead with results, keep responses short, and provide full detail on request. Users can enable it via /config → Output style or by se…
Only-CLI released oc, an open-source tool that turns websites into compact, numbered command-line interfaces for AI agents, cutting token usage from tens of thousands to a few hundred per page. The tool, installable via …
OpenAI's Codex coding agent can now continue working on other tasks while waiting for a developer's response, eliminating the need to pause long-running operations. The update, announced by OpenAI, allows Codex to mainta…
UiPath introduced UiPath Maestro Flow, a developer-first orchestration canvas that lets builders use supported coding agents to design, run, observe, and govern end-to-end processes as a single artifact from prototype to…
A developer released a comic series explaining Anthropic's Claude AI assistant, covering chat, coworking, and coding, with guides in English and German. The project includes a command reference generated from the install…
Developer wdhwg001 released csift, an open-source Rust tool that recovers and analyzes Claude Code session files, addressing issues where Claude deleted project files and stalled during recovery. The tool performs byte-e…
Vercel Labs released fx, an open-source (Apache-2.0) coding agent harness and CLI written in Zig, optimized for research and embeddability, with a 7.8 MiB binary. The tool supports local and cloud inference, offers a Uni…
A developer argues that most complaints about Claude Code stem from context management issues rather than model limitations. The post identifies four common problems—rising token usage, ignored rules, vague responses, an…
Anthropic is extending the 50% increase to weekly Claude Code limits through August 31 for all Pro, Max, Team, and seat-based Enterprise users, citing strong demand for its models. The company hopes to make the increase …
HarnessRouter Community Edition, an Apache 2.0 licensed project on GitHub, has been released as a self-hosted unified API for running Codex, Claude Code, Hermes, and other agent harnesses on a single container. The tool …
Octomind released version 0.44.0 on August 17, followed by 0.44.1 and 0.44.2, which removes self-verification from AI coding agents by replacing in-memory boolean latches with a persisted verification policy and requirin…
A developer created Zeroparams, an OpenAI-compatible coding agent that replaces the LLM with a human operator via a custom VSCode extension, allowing real-time file edits and CLI commands. The project is an art piece exp…
A developer's guide introduces WEKA, a graphical machine-learning workbench that allows beginners to explore datasets and experiment with algorithms without writing code. The guide walks through loading data, preprocessi…
A developer proposes treating OpenAPI specifications as first-class Git artifacts for machine learning and inference projects, suggesting that API contracts should live alongside model code and configuration in version c…
Forklane, a new multiplayer coding platform with a built-in agent and orchestration stack, launched to help dev teams and AI agents collaborate in real time without conflicts. The platform, available at forklane.ai, aims…