NewsLayer.com

OpenAI Proposes Shared AI Development Limits Tied to Safety Milestones

OpenAI Chief Scientist Jakub Pachocki on November 22, 2026 released internal perplexity measurements and proposed shared limits on frontier AI development, warning that alignment and monitoring research may not keep pace if pretraining…

Unite.AI

Publisher

Nov 22, 2026 at 6:43 PM UTC · Updated hace 2 horas · 3 min de lectura

OpenAI Proposes Shared AI Development Limits Tied to Safety Milestones
Image via Unite.AI
Traduciendo…

OpenAI Chief Scientist Jakub Pachocki on November 22, 2026 released internal perplexity measurements and proposed shared limits on frontier AI development, warning that alignment and monitoring research may not keep pace if pretraining advances accelerate as soon as 2027.

The disclosure concerns log-perplexity, the logarithm of perplexity, also called cross-entropy loss. Perplexity measures how well a model predicts the next token on average; lower values indicate better predictions. OpenAI’s figures use a fixed snapshot of held-out data from its internal codebase, the main evaluation dataset it has tracked since GPT-3.5.

Pachocki reports that GPT-3.5 measured about 0.99 and supported fluent conversation, forming the basis for the original ChatGPT, while GPT-4 measured about 0.91 and could productively use chain-of-thought reasoning. New cybersecurity and mathematics capabilities emerged at losses below 0.8. At about 0.76, a model began producing notable results on open mathematics problems after OpenAI had spent more than a year posing such problems to its models.

Shared Limits Tied to Monitoring Milestones

Pachocki expects further significant capabilities around the 0.68–0.70 log-perplexity window, extrapolating from recent progress, while acknowledging that he does not know what they will be and that current evaluations may not test for them. The proposal asks frontier developers not to cross limits based on perplexity and other measurements until researchers’ ability to understand and monitor AI behavior reaches a concrete milestone. One example is a successor to chain-of-thought monitors, which inspect a model’s written reasoning for signs of misalignment.

Article Intelligence

Topics

Sponsored

Ad
House — Advertise on NewsLayer
NewsLayerLearn more

NewsLayer Premium

Unlock deeper intelligence.

Ad-free reading, exclusive research, and real-time onchain insights.

Go Premium