← All stories
AI & Tech

AI Model Latent Capabilities Remain Unknown Due to Insufficient Testing Time

No Priors Podcast · Really Big Test-Time Compute in AI Changes Benchmarks, Safety and Research with OpenAI Research Scientist Noam Brown · June 29, 2026
AI Model Latent Capabilities Remain Unknown Due to Insufficient Testing Time
No Priors Podcast
No Priors Podcast
Really Big Test-Time Compute in AI Changes Benchmarks, Safety and Research with OpenAI Research Scientist Noam Brown
"The model release cycle is, look, we're releasing new models like every 2 or 3 months at this point. And so a model comes out, it takes 2 or 3 months to push it to its limits, and then you have another model come out. And so nobody actually knows what the ceiling of capabilities are for these models because nobody's actually run them for long enough."
Brown disclosed that the rapid model release cycle means no one has fully explored what current AI systems can do at their limits, as some tasks require weeks or months of compute time to plateau. This creates uncertainty about both beneficial and potentially dangerous capabilities already present in deployed models.

About this episode

On this episode of No Priors, host Sarah Guo interviews Noam Brown, an OpenAI researcher who pioneered inference-time scaling techniques, about the broken state of AI model evaluations and the implications of large-scale test-time compute. Brown argues that current model benchmarking practices fail to account for the fact that modern AI capabilities are now a function of inference budget rather than fixed model properties, making comparisons misleading and safety evaluations inadequate. He revealed that existing responsible scaling policies and preparedness frameworks, developed during the ChatGPT era, don't address how much test-time compute should be allocated when evaluating dangerous capabilities, creating a critical blindspot as models can perform dramatically differently at $10 versus $10 million budgets. Brown disclosed that an internal OpenAI model recently disproved the Erdős unit distance conjecture at minimal cost, and that publicly available models like GPT-5.5 contain significant unexplored capabilities because the rapid release cycle means nobody runs models long enough to discover their limits. He revealed OpenAI is deliberately discouraging internal researchers from solving open problems in mathematics and physics to focus on building more capable models faster. The conversation explored recursive self-improvement, with Brown arguing against fears of overnight intelligence explosion because large-scale test-time compute creates a time bottleneck. He noted current models lack research taste and cannot yet fully replace researchers, though they dramatically accelerate certain tasks like code optimization. Brown predicted that within 6 to 12 months, models will be capable of completing PhD-level work zero-shot and emphasized the need for evaluation practices that plot performance against inference budget rather than reporting single benchmark scores.

Key takeaways

More stories More from No Priors Podcast