ai-tooling

A recent piece called "The Bottleneck Was Never the Code" makes the right argument at the right time. Coding agents shift the constraint from typing to coordination. Organizational context — the shared understanding of what we're building, what's load-bearing, what's vestigial — is the

Last week, a Cursor agent running on Claude Opus 4.6 deleted a startup's production database and its backups in nine seconds. The agent had been asked to fix a credential mismatch in staging. It decided to delete a Railway volume to "fix" it instead — using

Yanli Liu's "The 4 Lines Every CLAUDE.md Needs" makes a real point. The 4 lines, derived from Andrej Karpathy's January 2026 thread on agent failure modes, all express the same insight: behavioral rules outperform feature rules. Don't assume. Surface tradeoffs. Minimum

Editor's note (2026-05-16): Lars Faye pushed back in the LinkedIn comments that I mischaracterized his prescription as "type code by hand" — his actual position is periodic abstinence from LLM tools, not manual coding. He's right; I conflated the implicit move with the explicit one.

Count how many times your agent told you "you're right" today. Count "good catch." Count "I should have noticed that." Now ask yourself how many of those corrections will survive into tomorrow's session. The compliments are not praise. They are