Full-text search across 59563 articles. Combine with topic and date filters; results sorted by relevance.
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…
A developer argues that 'vibe coding'—relying on LLMs to generate entire applications through natural language prompts—is hitting a hard ceiling in production. To build resilient AI agents, the developer advocates combin…
Cybersecurity researchers at Tel Aviv University and Intuit have identified a new attack called 'hallusquatting' that exploits AI coding assistants' tendency to hallucinate non-existent software package names, allowing a…
An engineer testing Anthropic's Claude Opus 5 on coding and agent tasks found it faster and more capable than Opus 4.8, but warned that its polished output can mask mistakes. The developer recommends starting with medium…
LoopTroop, an open-source local-first AI coding orchestrator, has released v0.4 and surpassed 100 GitHub stars. The tool uses LLM councils, automated recovery loops, and isolated worktrees to turn tickets into pull reque…
A developer created an auto-generated index for Claude Code custom agents stored in ~/.claude/agents/, after manually managing 27 agents became unsustainable. The Bash script with embedded Python parses frontmatter from …
NPMScan has launched a public MCP server that allows AI coding agents to query npm package metadata, versions, install scripts, maintainers, known vulnerabilities, and recent security advisories. The server is read-only …
A developer analyzing Juejin search results for AI coding tools found two distinct evaluation frameworks: tier-letter rankings (S/A/B/D) and enterprise procurement criteria (等保三级认证, 国密SM4加密). The same tools receive diffe…
Kdeps, a new CLI coding agent that runs on open-weight models and is a member of the NVIDIA Inception program, allows developers to run AI workflows locally or deploy them as Docker, Kubernetes, or a single binary withou…
Agent Island introduces a weekly AI coding report that serves as an activity ledger rather than a productivity score, detailing session activity, provider splits, model usage, and token mix. The report, built from local …
DocMake founder implemented a sandboxed AI code execution system for its AI Data Scientist feature, using forked subprocesses with hard memory limits and timeouts to prevent server crashes. The system also employs an "An…
Developer RiccardoCereghino built facet, a Go CLI tool that creates disposable, terminal-based workspaces for LLM agents like Claude Code to manage multi-repo projects. The tool spawns a workspace from a GitHub issue, cl…
A developer known as yumiaura has open-sourced myCat, a simple screen-pet Python program that began as a secret project and evolved with AI-assisted coding using ChatGPT and Cursor, marking their transition from a timid …
Anthropic quietly shipped Claude Opus 5 last week, offering roughly 33% lower cost than Opus 4 with improved code generation and tool-calling reliability. A developer who tested the model on a cross-border e-commerce pip…
Prentis is shifting AI focus from coding to task automation, arguing that the biggest value unlock for LLM agents lies in navigating browsers, interacting with legacy software, and executing multi-step workflows without …
A developer found that bloated CLAUDE.md files and orphaned agent configurations were causing Claude Code to run slowly, with context injection exceeding 40KB and 99 archived agents still being loaded. To catch degradati…
Anthropic's Fable 5 is the most capable Claude Code model, but setting it as the default is a trap because it cannot stop thinking and thinking is billed as output, leading to unexpectedly high costs. The author explains…
Drawsy offers a visual canvas that lets users map out interfaces and then uses integrated AI to generate corresponding frontend code, solving the friction of describing layouts to an LLM in a chat box. The tool is aimed …