Keep up with tech in 5 minutes
Get the free daily email with summaries of the most interesting stories in startups 🚀, tech 📱, and programming 💻!
Join 1,600,000 readers for one daily email
Karpathy's Autoresearch found a 3-year-old bug in Posthog's query engine (and improved performance by 11%) (9 minute read)
Posthog pointed an AI agent at its query agent, fed it slow queries from production, and let it run overnight. The next morning, the team discovered that for almost three years, every query with a timestamp filter had not been using ClickHouse's primary key correctly. Fixing the issue cut the number of granules ClickHouse had to scan by 62% on the benchmark query and made the query itself meaningfully faster. This post discusses the team's setup, the bug itself, and PostHog's plans to automate this type of analysis.
Apr 29 | Blog
The Trust Problem With AI Agents
Why developers should not entirely rely on agents, and what you can do about it.
Sponsored
Jun 03 | AI
GitHub's plan for Agents (90 minute read)
GitHub has been the home for software for almost two decades. Coding agents have seen massive quantities of code being shipped on the platform, which has grown 1,400% this year. This has put pressure on GitHub's infrastructure, which was designed around human developers moving at human speed. This article features an interview with GitHub COO Kyle Daigle where he discusses how AI has changed things in the company, how he uses AI to work at GitHub, why the AI era is breaking GitHub in new ways, and more.
Jun 03 | Dev
My Agent Skill for Test-Driven Development (3 minute read)
The greatest productivity gains from AI agents, which often write poor tests, are unlocked by guiding them with software design principles like a structured Test-Driven Development (TDD) process.
Jun 03 | Infosec
claude-red (GitHub Repo)
claude-red is a library of 58 offensive-security SKILL.md files across 13 categories that prime Claude's Skills system to act as a context-aware red team operator, with skills loading on demand from conversational triggers spanning web (SQLi, SSRF, deserialization), Active Directory (Kerberoast, ADCS ESC1-15), wireless, cloud, EDR evasion, exploit development, fuzzing, and AI attacks like prompt injection and RAG poisoning. The author positions it for authorized engagements, bug bounty triage, CTF prep, and operator training, with a seven-phase roadmap targeting roughly 107 skills.
.png)
