AI Safety Researcher Counters Hindsight Bias: Models Are Safe Because of Mitigations

sjgadler · x · 2026-07-22

Pushing back against the hindsight bias that 'the model is safe, so previous worries were dumb,' the author argues the exact opposite. They emphasize that models are safe today precisely because significant effort was invested in safety mitigations. Had no one been concerned and proactive, the models would not be as secure as they are now.

Related event: Debate Over GPT-OSS Open Source and Safety Strategies(10 posts)→

Original post →

More from Safety

Safety channel →