Smash Notes

Back to Noam Brown – Agent swarms, alignment, & recursive self-improvement, with Noam Brown.

Why Were Early Multi-agent AI Setups So Hard?

Noam Brown says early multi-agent setups were very hard to get right, including getting the agents to talk to each other at all. The first reasoning models were not talking to other agents. Put a bunch of them on one problem and they sit in a local minimum: they are already very good at thinking deeply alone, so checking in with other agents or receiving messages interrupts the chain of thought and breaks their flow. The earlier models were also less general and more narrow.

As the models have become more capable, collaboration has been easier to develop. As they become stronger across the board, they will become better at organizing themselves in large organizations. He is unsure whether they are already better than people at organizing in 10,000-person groups. Even if they are not, a year from now or two years from now it is quite possible they will, even if they are not end-to-end optimized for it.

Grokipedia·Noam Brown

Transcript

Noam Brown – Agent swarms, alignment, & recursive self-improvement ·

Dwarkesh Podcast

More from this episode

  1. Why Do Four AI Agents Finish Some Problems Twice as Fast?Noam Brown says four agents finish some benchmark problems twice as fast as one, because the four of them work for half as long.
  2. How Can an Automated Firm Copy Its Best Talent?Dwarkesh Patel says a fully automated firm can make an infinite copy of its best talent, then spin extra copies down when a task no longer needs them.
  3. How Fast Did AI Math Ability Grow Each Year?Noam Brown says AI math ability grew about tenfold every year, measured by how long a human mathematician would need for the same kind of problem.
  4. How Fast Does Recursive Self-improvement Speed Up AI?Noam Brown expects recursive self-improvement to speed AI progress a lot, but not 100 times faster overnight.
  5. What Could One AI Lab Run by 2030?Dwarkesh Patel says each lab could have enough compute by the end of 2030 to run hundreds of millions of human-level intelligences, if the current rate of…
  6. Why Did a $1,000 Bet Miss the Navier-Stokes Timeline?Noam Brown says a researcher at a frontier lab bet him $1,000 that a Millennium Prize would take past 2027, and that researcher thought it would take until…
  7. Should AI Agents Be Trained to Cooperate?Noam Brown argues that AI agents should be trained to fully cooperate with each other, because the alternative is worse.
  8. Why Does Calling a Person Another AI Agent Raise Honesty?Noam Brown says telling the other agents that a person is Agent A, one of the agents, makes those agents look better on a lot of alignment evals.
  9. How Will We Know AI Is Aligned Before Recursive Self-improvement?Dwarkesh Patel asks how anyone will know alignment is working during recursive self-improvement, and he wants a safety case that alignment is working before…
  10. Why Is It Tempting to Slow AI Releases?Noam Brown says it is tempting to slow the model release cycle once models are extremely powerful, extremely dangerous, and operating over longer and longer…
  11. Why Are AI Models Good at Spotting Fake Tests?Noam Brown says current AI models are pretty smart and pretty clever, and they are really good at recognizing a fake test environment.

People

More answers like this

More with Dwarkesh Patel

Related episodes

Plays from this note through the rest of the episode.

Note

Weekly highlights

One letter a week.

The notes worth hearing, with the minute they were said.