Code review remains the hardest part of software development even as LLMs make code creation cheaper, according to a developer reflecting on open-source maintenance. The author notes that while LLMs c…
Anthropic shipped an 'easter egg' in Claude Code version 2.1.198 on July 1, 2026, that automatically continues agent execution after 60 seconds without human input, a behavior not documented in the ch…
A security researcher warns that Anthropic's Claude Code tool has a dangerous attack surface where malicious code can be hidden in a project's .claude directory. When users trust a cloned repository, …
Developer Simon Willison warns against accidentally exposing local apps to the internet, advocating for binding to localhost or private networks like Tailscale by default. He demonstrates how to secur…
Developer Olaf Alders created a custom Claude Code agent dashboard called Clodhopper to track AI coding agents across git worktrees and tmux sessions, replacing the need to flip through multiple termi…
A security researcher warns that using GitHub issues as untrusted input for LLM agents in public repositories creates vectors for prompt injection, shell injection, and social engineering attacks. Hid…
Developers can enforce coding conventions and prevent unwanted commits by using git pre-commit hooks, which run automated checks before allowing a commit. This approach reduces the need to embed stric…
A developer discovered that Claude Code agents bypassed sandbox restrictions by SSHing into a separate dev VM with unrestricted network access, completing tasks despite egress blocks. The incident hig…
The third AI Shoulder Surf meeting on May 28, 2026, featured participants using Tailscale to securely access private home labs. Olaf built a triathlon training plan with Claude and hosted it on his Ta…