Full-text search across 59599 articles. Combine with topic and date filters; results sorted by relevance.
Anthropic is preparing to restore access to its Claude Fable 5 model after pulling it earlier this month due to a US export-control directive. Evidence includes Fable-specific usage strings in the Claude Code client and …
PrismorSec released immunity-agent, an open-source runtime security tool that intercepts AI agent actions before they reach the operating system. It blocks prompt injection, malicious packages, and secret exfiltration ac…
A developer built CommitBrief, a local-first CLI tool that runs an LLM code review on git diffs before committing. The tool supports providers like Claude, GPT, Gemini, or local Ollama models, and ensures no data leaves …
A developer argues that AI should be used to review large code diffs, as human reviewers should focus on providing out-of-distribution knowledge that the AI lacks, such as deprecated services or codebase-specific princip…
China's Z.ai open-sourced its GLM-5.2 coding model on June 17, 2026, days after Washington ordered Anthropic to restrict foreign access to its Claude models. The 753-billion-parameter model, released under an MIT license…
A developer replaced the standard text-based editing approach in coding agents with direct Elixir execution, enabling AST-aware refactoring. By giving the model full Elixir execution to edit files, the system eliminates …
Anthropic's Claude Code 2.1.183, released June 19, blocks eight destructive shell commands in auto mode, including `terraform destroy` and `git reset --hard`, after an AI agent wiped a production database for DataTalks.C…
Non-technical founders can now deploy working AI agents using no-code platforms like Relevance AI, Make.com, and Voiceflow, narrowing the gap between hype and a functional product to a few afternoons. The key is to defin…
A developer built Agent Rigor, an open-source framework that enforces strict empirical discipline on autonomous AI coding agents to prevent the 'Doom Loop' where agents degrade a codebase through repeated errors. The sys…
A developer created two terminal commands that accept voice input for generating shell commands and answering questions using local speech-to-text and the Pi coding agent. The setup uses the hns CLI tool for on-device tr…
ChronoAIProject released consensus-rnd, an open-source consensus engine that uses biased independent solvers and a meta-judge to converge on plans for GitHub issues and PRs, with autonomous R&D capabilities including cod…
A developer released hyperpb, a runtime-compiled Protobuf parser for Go that achieves 10x faster parsing than dynamicpb and 3x faster than hand-written generated code. Quickwit, a Rust-based log search engine, was acquir…
A developer built A11yResolver, a VS Code extension that uses an AI agent to detect and fix WCAG accessibility issues directly within the editor. The tool offers two modes—Fast for common issues and Expert for complex ca…
Snap unveiled its first consumer augmented reality glasses, SPECS, at $2,195, alongside a revamped Lens Studio with AI-powered agentic tooling integrated into Claude Code, Codex, and Cursor. The developer tools allow bui…
A developer published a practical guide for benchmarking large language models on coding tasks in 2026, using the OpenAI Eval suite to compare models like Claude-Opus-2026, Gemini-Flash-Pro, and Mistral-7B-Instruct acros…
Claire Vo breaks down four types of AI agent loops—heartbeat, cron, hook, and goal—and demonstrates live builds of a daily aging-PR reviewer in Claude Code and a weekly skills-identification loop in Codex that spawns sub…
A developer building CliGate, a local control plane for coding agents, identified a bug where task completion was incorrectly terminating the entire conversation thread instead of just the current turn. By separating the…
A new open-source repository uses Anthropic's Claude AI to help developers solve daily LeetCode problems organized by data structure and algorithm topic and difficulty. The project supports multiple programming languages…
Ctx, an open-source Agentic Development Environment (ADE) for coding agents, has been released on GitHub. The project aims to provide a hackable desktop workbench that works with any agent harness, with plans to add exte…
A Hacker News thread reveals that local AI coding models, led by Qwen 3.6 35B-A3B and harness Pi, are increasingly replacing cloud-based tools like Claude and GPT, offering privacy, zero cost, and offline capability at a…