A developer has released evalmut, an open-source mutation testing tool for LLM regression suites that injects known defects to reveal which checks fail to catch regressions. The tool underwent eight r…
Agent-kit, an open-source size-based mandatory review chain for Claude Code, has been released as a free core with 8 scripts, 2 GitHub Actions workflows, 3 agent charters, and 45 automated tests, requ…
At GopherCon UK 2026 in London, Ainsley Clark discussed how AI is reshaping developer roles and impacting satisfaction, citing studies on increased stress and the IKEA effect, and offered tips to recl…
A developer proposed a layered wiki pattern on top of the open-source tool graphify, which turns codebases into queryable knowledge graphs. The design suggests colocating scoped graphs and wikis withi…
Gartner forecasts worldwide AI spending to grow 47% in 2026, with agentic AI software up roughly 141%, and projects that by 2028 an average Fortune 500 enterprise will run over 150,000 agents, up from…
A developer outlines a disciplined workflow for using Claude Code, emphasizing context establishment, planning, delegation, and verification to treat the AI as an engineering collaborator. The approac…
A developer built Repliqa, a Chrome extension that automatically captures screenshots, console errors, network requests, and user steps to generate bug reports for AI coding assistants like Claude Cod…
Prathak Malik released v0.2 of the agent-standards-as-code kit, which syncs AI coding standards across Cursor, Claude Code, Copilot, and Codex on both macOS and Windows. The kit uses the Agent Skills …
Jeremy Berman reported scoring 96.2% on ARC-AGI-3 with Opus 5, and 99.3% pass@2, using a program based on Claude Code and Opus 5 (high) with one action command and filesystem logs. The approach, which…
Anthropic's Claude Code is returning empty or truncated thinking blocks for Claude Opus 4.8 and Sonnet 5, even when summarized thinking is explicitly requested, according to developer bug reports. The…
A freelance web developer in Japan built a fully automated, rule-based Japanese stock research pipeline using Claude Code, J-Quants, and a macOS cron job. The system, which is forbidden from making pr…
A developer successfully built a Flutter APK inside Android's Virtualization Framework (AVF), a built-in pKVM-based Linux VM, after moving from Termux's proot environment. The developer found proot's …
PandaOS, a new local AI workstation, aims to unify code, tools, and AI agents into one environment for builders, reducing app-switching and context loss. The product, opening to a limited group of ear…
Docker Sandboxes now allow Claude Code and Codex coding agents to run with full autonomy inside isolated microVMs, reducing the risk of granting --dangerously-skip-permissions or --dangerously-bypass-…
Public data on exploited software vulnerabilities and solved open math problems shows a sharp acceleration in discoveries in 2026, but aggregate algorithmic optimization records show no clear change i…
OpenAI previewed Ultrafast, a limited-access API tier for GPT-5.6 Sol, on August 13, running at up to 750 output tokens per second, or up to 14x Standard processing speed, powered by Cerebras hardware…
Developer Younggi Choi released cliclaw, a daemon that lets users control Claude Code, Codex, Pi, and Gemini CLI from Telegram, with per-chat agent sessions, a safety gate, and auto-detection of corpo…
A developer has created a reusable Claude Code skill, 'implementing-figma-designs', that transforms Figma-to-code conversion from a screenshot-based eyeballing loop into a staged extract-then-prove pr…
Jaithon 3.1, a new programming language designed to be faster than Python for machine learning, has been released by developer Abhiram Sonny. The language features a bytecode VM, garbage collection, a…
A developer discovered that Claude Code's --safe-mode flag, intended to isolate subprocess calls from project configuration, does not prevent environment variable leakage. The developer's git_commit.p…