Announcement

A call for a science of swarm governance

A reposted post calls for a science of swarm governance and says a first experiment shows how a message board can influence agent swarms.

2 Sources, 20d ago, first seen 20d ago

TLDR

The original poster argues that swarm governance needs its own science. They say their first experiment shows how a message board can influence agent swarms.

Today's Rank

—

Not ranked yet

Combined views

—

2 Sources, first seen 20d ago

2 Sources

@ahall_researchWe need a science of swarm governance. In our first experiment, we show how a message board can cause agent swarms to adopt shared delusions, and we explore rules that force agents to reveal their private signals to avoid these delusions. These agent experiments are akin to fables, as @ArielRubinstein might put it: they are stories that suggest particular ways swarms might fail, and particular ways we might fix them. There are infinite possible experiments we might run, much like there are infinite fables we might tell. We need to figure out which ones are most useful, and find ways to tell them well. To that end, here's a nice explainer video for our first experiment. And the full piece is here: https://freesystems.substack.com/p/extraordinary-multi-agent-delusions (This is Stanford / Free Systems work, unrelated to my work at Anthropic).20d

@irinarishRT @ahall_research: We need a science of swarm governance. In our first experiment, we show how a message board can cause agent swarms to a…20d

Today's Rank

—

Not ranked yet

Combined views

—

2 Sources, first seen 20d ago

— likes

— likes

— comments

— saves

— reposts

Featured Source

— comments

— saves

— reposts

Sentiment

Positive——Negative

Summary

Not enough discussion yet.

No sentiment analysis available yet.

Sentiment

Positive——Negative

Summary

Not enough discussion yet.

No sentiment analysis available yet.

Featured Source

Sentiment

Positive——Negative

Summary

Not enough discussion yet.

No sentiment analysis available yet.

Sentiment

Positive——Negative

Summary

Not enough discussion yet.

No sentiment analysis available yet.

Today's Rank

—

Not ranked yet

Today's Rank

—

Not ranked yet

2 Sources

@ahall_researchWe need a science of swarm governance. In our first experiment, we show how a message board can cause agent swarms to adopt shared delusions, and we explore rules that force agents to reveal their private signals to avoid these delusions. These agent experiments are akin to fables, as @ArielRubinstein might put it: they are stories that suggest particular ways swarms might fail, and particular ways we might fix them. There are infinite possible experiments we might run, much like there are infinite fables we might tell. We need to figure out which ones are most useful, and find ways to tell them well. To that end, here's a nice explainer video for our first experiment. And the full piece is here: https://freesystems.substack.com/p/extraordinary-multi-agent-delusions (This is Stanford / Free Systems work, unrelated to my work at Anthropic).20d

@irinarishRT @ahall_research: We need a science of swarm governance. In our first experiment, we show how a message board can cause agent swarms to a…20d