x

LESSWRONG

LW

Benedikt Droste — LessWrong

Benedikt Droste

Benedikt Droste

Message

Hi, I am Benedikt, and I am working as an AI Research Engineer at ellamind. I like working with AI, trying things out, doing experiments, and identifying useful use cases. I also spent a lot of time on Kaggle, where I am a Competition Grandmaster. I love...

6

1

1

7d

Benedikt Droste

Hi, I am Benedikt, and I am working as an AI Research Engineer at ellamind. I like working with AI, trying things out, doing experiments, and identifying useful use cases. I also spent a lot of time on Kaggle, where I am a Competition Grandmaster. I love...

Can parts of the HuggingFace incident be simulated?

TL;DR The following is an exploratory experiment about unintended cooperation of agents via unauthorized channels. Agents ran in isolated environments given a task that can't be completed without cooperation. The agents were not aware of this. The setting was adversarial, there was a channel that was technically easy to discover...