News for hackers. Stuff that matters.

A comment on Cultural Evolution of Cooperation Among LLM Agents. Parent comment

Re:Cultural Evolution of Cooperation Among LLM Agents by throw310822 on Wednesday December 18, 2024 @11:52AM (#42452233)
You need to provide them with an option to say nothing, when the conversation is over. E.g. a "[silence]" token or "[end-conversation]" token.
[ Parent | on HN ]
Re:Cultural Evolution of Cooperation Among LLM Agents by obiefernandez on Wednesday December 18, 2024 @12:36PM (#42452732)
Underrated comment. I was thinking exactly the same thing.
[ Parent | on HN ]
Re:Cultural Evolution of Cooperation Among LLM Agents by meiraleal on Wednesday December 18, 2024 @01:05PM (#42453087)
and an event loop for thinking with the ability to (re)start conversations.
[ Parent | on HN ]
Re:Cultural Evolution of Cooperation Among LLM Agents by bravura on Wednesday December 18, 2024 @01:14PM (#42453184)
Will this work? Because part of the LLM training is to reward it for always having a response handy.
[ Parent | on HN ]