Perplexity and Intelligence
OpenAI November 22, 2026 Research Safety Perplexity and Intelligence By Jakub Pachocki, Chief Scientist at OpenAI Share From afar, it might seem like modern…
Summary
OpenAI November 22, 2026 Research Safety Perplexity and Intelligence By Jakub Pachocki, Chief Scientist at OpenAI Share From afar, it might seem like modern AI is built similarly to how software has been built in previous decades: with a diverse set of techniques targeting specific capabilities. There are indeed a variety of methods, but rather than designing something from scratch, they are mostly harnessing the intelligence coming from a much simpler and less interpretable process: training a compressor (or, equivalently (opens in a new window), predictor) on a very large corpus of data. 1 I believe tracking the pace of progress on training better compressors is key to understanding the arc of advances in AI. In this post, I argue for establishing perplexity (or, equivalently, cross-entropy loss) as a metric to compare between model developers and inform shared safety standards.
Positives
- OpenAI November 22, 2026 Research Safety Perplexity and Intelligence By Jakub Pachocki, Chief Scientist at OpenAI Share From afar, it might seem like modern AI is built similarly to how software has been built in previous decades: with a diverse set of techniques targeting specific capabilities.
- There are indeed a variety of methods, but rather than designing something from scratch, they are mostly harnessing the intelligence coming from a much simpler and less interpretable process: training a compressor (or, equivalently (opens in a new window), predictor) on a very large corpus of data.
- 1 I believe tracking the pace of progress on training better compressors is key to understanding the arc of advances in AI.
- As a first step, I provide more transparency into pretraining progress at OpenAI.
Risks & concerns
- In this post, I argue for establishing perplexity (or, equivalently, cross-entropy loss) as a metric to compare between model developers and inform shared safety standards.
- Publishing our internal perplexity measurements took some consideration; it gives competitors a clearer picture of where we stand, but that concern is outweighed by the urgency of establishing shared (opens in a new window) safety measures across the industry.