Code quality and AI reliability
When AI-generated code breaks or fails despite high output volume, and what instincts developers need to catch errors. Every AI Coding Weekly story on code quality and AI reliability, newest first. 3 stories since October 2026.
- Theo says Gemini hallucinated in over 80% of his review runs
One engineer's harness, one set of receipts, and a failure mode that looks exactly like a real code review.
- Bun's author corrects claim that its Claude rewrite avoids security bugs
Jarred Sumner and Theo both pushed back within hours, and Bun had already announced a v1.4.4 fix.
Have the good opinion, not the loud one
One email a day. Under three minutes. What working engineers found out about coding with AI.
- Theo says agents triaged his outages and rolled dozens of API keys
Days after saying his vibe coded work collapsed, Theo quote-posted himself with the opposite experience.
People on Code quality and AI reliability
Get the next one by email
Coding with AI, read daily so you do not have to. The experiments, the receipts and the arguments from engineers shipping real software. Not a changelog.