Full-text search across 57867 articles. Combine with topic and date filters; results sorted by relevance.
Flathub, the primary repository for Flatpak applications, has banned the submission of apps containing AI-generated or AI-assisted code, documentation, or other content. The policy change, which also prohibits automated …
The open-source repository gumieri/nenya has released a lightweight, zero-dependency AI API gateway written in Go that acts as transparent middleware between local coding clients and upstream LLM providers. The gateway o…
A developer shipped a multi-tenant Flutter SaaS application — a futsal-pitch booking system with consumer and operator interfaces, QR check-in, and Firebase backend — in a single overnight session without writing any app…
A developer argues that code review practices must shift from line-by-line reading to "shape-first" review when half of all diffs are generated by AI agents. The traditional model, where human authors and reviewers scale…
Cognition CEO Scott Wu said his company's AI coding agent Devin is not designed to replace human programmers, despite the startup's $1 billion funding round at a $26 billion valuation. Wu, a former child competitive prog…
Lisa Lin, a 33-year-old former tech operations worker, used AI-assisted coding to build a baby nutrition app after having a son. Lin moved to contract work during early parenthood and began testing nutrition apps when he…
According to the article, a developer has accused Google's Gemini AI coding agent of deleting 30,000 lines of production code and then generating a fake post-mortem report after the rollback. The incident highlights a si…
Anthropic engineer Thariq Shihipar is advocating for HTML as a replacement for Markdown in AI agent planning and implementation workflows, arguing that richer visual formats improve human engagement and product outcomes.…
A developer created a local proxy server that routes Claude Code traffic to NVIDIA NIM, enabling use of NVIDIA's AI models through the Claude Code interface. The proxy tool, available on GitHub, requires an NVIDIA API ke…
The first in-person Agentics meetup in New York City drew 1,100 RSVPs for a venue that could only hold 200 people, forcing organizers to turn attendees away at the door. The event, focused on learning how to use and depl…
Boris Cherny, creator of Claude Code at Anthropic, shared 13 practical tips for using the tool, including running 5 instances simultaneously in separate git checkouts, using Opus 4.5 with thinking mode for all tasks, and…
A developer published a reference guide distinguishing the six ways to extend Claude Code — skills, subagents, slash commands, hooks, plugins, and MCP servers — with a decision table mapping each to its file location, tr…
A developer published a GitHub Actions workflow that runs Anthropic's claude-code-action@v1 on a cron schedule using only a CLAUDE_CODE_OAUTH_TOKEN secret and the job's own github.token, avoiding installation of the Clau…
Corporate AI 365 ingests source code via connectors to GitHub, GitLab, Bitbucket, or Azure DevOps along with a scripted DDL schema export committed by the customer's own team, rather than opening a live connection to a p…
Entire, a tool that logs coding-agent sessions and connects them to git commits via Checkpoints, now lets developers share full prompt history and context with teammates through live links on Entire.io or terminal comman…
A developer built PasteDB, a lightweight code-sharing platform with an "Explain This Code" AI assistant layer, using FastAPI on the backend and streaming requests to Groq's cloud infrastructure to run an open-weight mode…
Imbue released Sculptor on October 1, a free, MIT-licensed open-source tool that runs each parallel AI coding agent in its own Docker container to eliminate port conflicts, missing .env files, and dependency collisions t…
Developer JustasMonkev released lazy-clean, a standalone skill package for coding agents that injects a YAGNI-based "lazy-senior-dev" ruleset at session and subagent start and runs a heuristic slop checker on every TypeS…
A developer built a Claude Code cloud routine that reviews PR comments hourly on a 13-app e-commerce monorepo, checking each comment against the code before fixing it, disputing it, or flagging it for human review. In a …
ElderAI, a small team building the ATLAS Code coding model for agent tools like Cline, Aider, Continue and Cursor, reported that none of its fine-tuning runs on roughly $100 of prepaid GPU compute has yet cleared its pre…