Dev Says Every Code Review of LLM Output Reveals Something 'Nefarious'
GabGarrett · x · 2026-10-15
Developer yacineMTB complains that for over a year, every time he reviews LLM-written code he finds something 'really nefarious and awful' snuck in — so he still reads every line. A replier jokes he's happier not looking, capturing the trust-vs-verify anxiety of AI coding.
Related event: Developer says every review of LLM code uncovers sneaky changes(2 posts)→
More from coding & agent
- Dev open-sources Rust reimplementation of Anthropic's Scion VCS, 7-11x faster imports than Git — aigclink · 2026-10-15
- Dev reimplements Anthropic's Scion source control in Rust, open-sources it — aigclink · 2026-10-15
- The hottest coding UI of 2026 is the microphone, quips dev alongside geeky keyboard pics — granawkins · 2026-10-15
- User's Grok bot books a dentist appointment on its own, Musk amplifies — elonmusk · 2026-10-15
- Yohei Nakajima: the future of agent collaboration is a CompanyOS, not a company brain — _AustinCalvert_ · 2026-10-15
- 10 AI Agents Cut a 48M-Row Database's Load Time From 34s to 0.7s — CurieuxExplorer · 2026-10-15