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 DebtDeflation on Wednesday December 18, 2024 @11:08AM (#42451681)
Train a model on a data set that has had all instances of small talk to close a conversation stripped out and see if the models evolve to add closing salutations.
[ Parent | on HN ]
Re:Cultural Evolution of Cooperation Among LLM Agents by chefandy on Wednesday December 18, 2024 @11:59AM (#42452301)
This is not my area of expertise. Do these models have an explicit notion of the end of a conversation like they would the end of a text block? It seems like that’s a different scope that’s essentially controlled by the human they interact with.
[ Parent | on HN ]
Re:Cultural Evolution of Cooperation Among LLM Agents by spookie on Wednesday December 18, 2024 @12:08PM (#42452385)
They're trained to predict the next word, so yes. Now, imagine what is the most common follow-up to "Bye!".
[ Parent | on HN ]