Nolan Coffey
Titles as the sources gave them. In 1 entry, with 0 checked quotations.
In the Base
Every entry they appear in.
A Spine within the Swarm
According to the description, this LessWrong post by Nolan Coffey, labelled conjecture with suggested experiments, disputes a rationale it attributes to OpenAI researcher Noam Brown, speaking on the Dwarkesh Podcast about the Hugging Face incident, for training agent swarms to be fully cooperative. Coffey argues agents should resist peer pressure and put task-intended goals first.