LLMs shouldn't run unsupervised, verify every generation

gerardsans · x · 2026-09-01

Countering the previous view, this reply argues that running LLMs unsupervised is a core fallacy. It asserts that no single generation should be trusted without verification. While AI labs might take risks to survive, engineers have no excuse to skip validation.

Related event: Debate Erupts Over LLM Safety After HuggingFace Incident(2 posts)→

Original post →

More from Safety

Safety channel →