forecast

Superintelligence may emerge mid-training run undetected

Because we only learn a model's capabilities after training completes, a system could become superintelligent partway through a long training run while training continues, so that by the time testing begins it is already a dangerous system whose level of danger no one anticipated.

forecastpending

Speaker

Roman Yampolskiy

Evidence Quote

“We start training GPT- 5 and... started that point of about human and we train it for the next nine months. Maybe two months in, it becomes super intelligent. We continue training it. At the time when we start testing it, it is already a dangerous system.”

Source

Roman Yampolskiy— Lex Fridman Podcast
Created: 6/13/2026, 3:37:06 AM

Your notes

Loading notes...