Full-text search across 59552 articles. Combine with topic and date filters; results sorted by relevance.
Meta Superintelligence Labs released Muse Glimmer, a 30-billion-parameter open-weights model optimized for local agent workflows, under an Apache 2.0 license. The model runs on a single consumer GPU and targets local cod…
A developer has published a practical guide to sandboxing AI coding agents inside CI pipelines, providing a repeatable harness with a decision table, a sandbox script using Linux namespaces, and canary tests to verify bo…
Anthropic will make Claude Code's auto mode the default for Pro, Max, and Team accounts starting August 14, citing a classifier that catches 89% of harmful actions versus 13.6% for human review, and noting that auto-mode…
Anthropic will make Auto Mode the default permission setting for new Claude Code sessions on Pro, Max and Team plans starting August 14, moving routine approval decisions from developers to a classifier that evaluates Cl…
Reasonix, a community terminal coding agent project, is engineered around prefix-cache stability to reduce API costs. The agent keeps the front of the context stable, appends rather than mutates, and separates planner an…
A new dataset from Mentalium Research catalogues 542 digital mental health startups that left the market between 2000 and 2026, coded on 18 fields including business model, payer, funding, and reason for leaving. The dat…
Developer Siddhartha Katiyar built ContextOS, a local-first context engine that indexes software repositories using Tree-sitter and SQLite FTS5 to improve AI coding assistants' retrieval accuracy. In benchmarks against t…
Databricks published an internal coding-agent benchmark on July 8 using tasks from its multi-million-line codebase, reporting that model choice, task difficulty, token use, and the agent harness affected cost and complet…
Robinduckett released Leclaude, a Windows shell extension that displays a robot badge on folders containing Claude Code session history, available for Windows 10 and 11 on x64 and ARM64. The tool, built with CMake and Ni…
Google and Kaggle's 5-Day AI Agents: Intensive Vibe Coding Course attracted over 353,000 registered participants, with more than 2 million learners having joined their multimodal, no-cost courses since 2024. The course r…
Claude Code 2.1.220's hooks do not cleanly map to agent status, so a developer still relies on screen scraping for three edge cases: Notification events include non-blocking types like idle prompts, a question at the end…
Alibaba's newly released Qwen3.8-Max debuted at rank four on Arena.ai's Frontend Code Arena with a score of 1,668, and rank two on the Vision leaderboard at 1,305, placing it ahead of several top US models. At $2 per mil…
Joey-io released Gauge, an open-source tool that shows Claude Code subscribers where their flat monthly subscription spend goes, breaking down usage by 5-hour window, day, model, and project. The tool reads local session…
ThinkAny AI released DScode, an open-source coding agent powered by DeepSeek, available via npm as @thinkany/dscode. The tool runs locally in any repository, supports parallel agents, sandboxed commands, and cost trackin…
A developer argues that AI cannot replace technical writers because it fails to capture 'institutional debt'—the undocumented knowledge and historical context behind messy codebases. While AI can describe what code does,…
A developer has created a format file that enables lnav, a log file viewer, to parse and query Claude Code session transcripts stored locally, making them searchable via SQLite. The tool allows users to analyze conversat…
An engineer at MonkeyCode built an admission-control proxy to prevent queue-depth-induced latency SLO breaches in their AI-assisted code review service. The proxy rejects new tasks when queue age exceeds 25 seconds or qu…
A developer has built Telechat, a self-hosted alternative to Claude Code Channels that runs as a single process and supports Telegram, WhatsApp, Slack, and web chat. It features smart model routing to reduce costs by up …
Researchers propose RLPF (Reinforcement Learning from Performance Feedback), a staged reward method that trains code agents to prefer faster correct implementations. Fine-tuning Qwen3-32B with RLPF on PerfCodeBench raise…
Anthropic argues that open-weight AI models lack a centralized kill switch, making them inherently less safe than controlled deployments, according to a developer-focused analysis of the Claude Code workflow. The piece w…