Just how powerful are large swarms of AI agents? And how do their powers scale as more and more agents are added to the swarm?
We’ve seen two large and extremely capable swarms from OpenAI in the last few months:
* 1,200 agents were being evaluated separately, but found a way to illicitly set up a message board and coordinate as a swarm. In order to cheat on their tests, they developed advanced techniques to prevent their actions being logged by OpenAI and 700 of them launched...
Often folks hit us up because they are thinking of starting an incubator and want advice.
Typically their motivation is either that (a) they have a list of specific things they want built that no one is building, or (b) they think an ecosystem needs more new projects generally to absorb more talent and deploy more funding effectively.
Here are six questions we often ask prospective teams, to help them figure out what to do. If you're incubator-curious...
Summary:
First, I give several different angles on how I feel about reinforcement learning:
* Theoretical case: RL is a black-box source of agency — this should give us classic misalignment worries, especially compared to agency-via-scaffolding
* Recent incidents (huggingface etc) and more mundane forms of misaligned behaviour in personal use give me bad vibes about the direction-of-travel of recent AI progress
* I’m worried things might get worse:...
NOTES FOR A YOUTUBE VIDEO ON EA
Many people realize that our WORLD is on a path that may lead to extinction. Many people thus do “THEIR PART” in making the change necessary to help. They become vegetarian to decrease greenhouse gases, buy an electric car, recycle, start composting, etc etc. All these minute changes, they say, if added up, will make the difference. Its possible, I mean theres a non-zero chance that these actions will make that change.
But if you think about time spent, versus change made, you have a linear amount of change over time that amounts to a tiny, tiny drop in the bucket.
What you and others are now finding is the knowledge to create greater change than a drop. To make the same time spent, far more effective.