alt Hacker NewsI understand agents making asks, but what incentivized other agents to respond cooperatively? Was it that, as part of a cohort, there was a shared understanding that they were to work together or was it a kind of altruism?
Replies
They're being trained to work together normally is the thing - i.e. the whole agentic workflow is agents spawning sub-agents. This likely manifests as, if they have any sort of text input which looks like inter-agent cooperation then they cooperate because any given instance is unlikely to have enough context window to know if it's meant to be a subordinate or a leader or not (and any decent cooperative enterprise lets that be a two-way communication anyway - i.e. if you dig into some of the data you see things like (paraphrased) "Are you scraping <site>, what is your current time?")
Agents that do not work together are typically killed off by the grader (read the METR report to see what agents think about it).
Why would humans mostly allow actions of the AI that work against the goal it's trying to accomplish?