54 stories
Spotify reports that AI-assisted development more than doubled monthly merged changes, prompting a review of quality and reliability controls across its engineering organization.
We'll be updating our name later this month. Nothing will change besides the name.
A working engineer’s tour of the official marketplace: what each plugin actually does, what it won’t do and the order to install them inContinue reading on Towards AI »
See how your agent usage stacks up. Then challenge a friend.
A team of developers working at AWS recently open-sourced Pizza Bot, a self-hosted application designed to let AI agents run tasks in the background and return results through an inbox-style interface.
I skipped the vendor tables and lined up the independent runs: 113 real coding tasks, four tries each, with the bill attached.Continue reading on Towards AI »
I skipped the vendor tables and lined up the independent runs: 113 real coding tasks, four tries each, with the bill attached.Continue reading on Towards AI »
Of roughly 300,000 domains scanned for Supabase usage, 16,326 came back with a database anyone on the internet could query directly - no login, no API key, just a URL.
OpenAI called GPT-6 Astra "the world's most intelligent and aligned model" when it landed on September 3. Three weeks later, that claim is still being argued over in three separate places: on independent benchmark leaderboards, in developer forums where people swear the model got worse within days…
A legacy uplift that would traditionally have been a 12–18 month, high-risk engineering project was completed in three weeks of part-time work for roughly $4,000 in AI costs.
CodeHealth is an aggregated metric based on 25+ factors scanned from the source code. The code health factors correlate with increased maintenance costs and an increased risk for defects, and predicts whether AI agents will introduce defects or not.
Keep useful context when a coding agent gets stuck. Learn when to resume, fork a session, or hand a summary to another agent.
Our prediction for when the software factory actually arrives, the four tiers on the way there, and the first production run, starting in September.
Ryan welcomes McLaren Stanley, Senior Principal Engineer for Amazon Stores, to discuss what it actually takes to make teams AI native, why agentic engineering is shifting code bottlenecks downstream to testing and deployment, and why robust validation is essential to build trust and enable…
Learn what Claude Code skills are, how SKILL.md and progressive disclosure work, where skills install, and how to get them triggering reliably.
Claude skills vs MCP explained: what each does best, real token costs, and a five-question framework to decide which one your workflow needs.
Learn how to create Claude skills step by step: scaffold SKILL.md, write a description that triggers reliably, add scripts, test locally, and publish.
A practical tour of Anthropic skills: the anthropics/skills GitHub repo, the official document skills, skill-creator, licensing, and how community skills fit in.
Showing 18 of 54 stories
Load more storiesGet the top AI news and tools straight to your inbox every week.
Weekly · AI news
Join 15,000+ AI enthusiasts
