So I was like, “I don’t think we’re going to get it in 2026, probably not in 2027, maybe in 2028.” So it did happen a lot faster than I expected.
Words found on the source page on Nov 6, 2026.
More from Noam Brown
PodcastDwarkesh Podcast: Agent swarms, alignment, and recursive self-improvementSep 17, 2026
And actually the models today are far beyond what was possible even six months ago.PodcastDwarkesh Podcast: Agent swarms, alignment, and recursive self-improvementSep 17, 2026
If you have five hours, you’re probably going to do a lot better. The AI models are pretty similar.PodcastDwarkesh Podcast: Agent swarms, alignment, and recursive self-improvementSep 17, 2026
If you’re in a world where they can operate effectively over three months, but the model release cycle is every two months, then you don’t have a way to evaluate the models at the full length of their capabilities before the next model release cycle.PodcastDwarkesh Podcast: Agent swarms, alignment, and recursive self-improvementSep 17, 2026
One thing is that the Hugging Face incident was, I think, people’s first real exposure to multi-agent coordination.PodcastDwarkesh Podcast: Agent swarms, alignment, and recursive self-improvementSep 17, 2026
The concerning scenario is that, especially as these models are becoming more capable, we make them what we think is aligned, and they’re 99.9% aligned. Then we use these models to help us with the next generation of models, and they end up being 99.8% aligned. Then with each subsequent generation, we see an increasing degradation in alignment.
On the same topics
BlogThe Specter Of NeuraleseSep 24, 2026
An AI with more real layers can actually be “smarter” in the conventional sense of the term.BlogThe Specter Of NeuraleseSep 24, 2026
For 100 steps in a row, the AI can shoot delicate subtle ideas from layer to layer at the speed of light. Then there’s one step where it has to encode them into twenty-six glyphs invented by Phoenician turquoise miners in 1800 BC. Then it has to re-encode the Phoenician glyphs into delicate subtle lightspeed ideas before it can do anything else.BlogThe Specter Of NeuraleseSep 24, 2026
The science of reading these thoughts is a subfield of AI interpretability, which is still in its infancy.BlogMysteries Of AI GeneralizationSep 23, 2026
This trains the AIs to be focused on task success, which naturally risks including things like reward-hacking, cheating, and single-minded pursuit of stated goals at the expense of ethical injunctions.BlogWhy I still haven't bought into true RSISep 19, 2026
It is important to not confuse massive steps in inference-time scaling, a dynamic which should be fairly predictable, with being the outputs of RSI, which is highly uncertain.BlogWe Must Pace The FrontierSep 14, 2026
If I was in charge of an alignment or interpretability team I would never run out of experiments to run and things to try, including having the time to properly talk to the models in the first place.
About this quote
- Said by
- Noam Brown, Research Scientist, OpenAI
- Where
- Dwarkesh Podcast: Agent swarms, alignment, and recursive self-improvement
- Topics
- Science, Research
- Company
OpenAI- Source
- dwarkesh.com/p/noam-brown
A quote is one moment, not the whole argument. Read it in context at the source.
Quotesby Glyph