[rwmj]

I wonder if anyone has run one of the free models continuously for a long time to see what it outputs? AIUI you'd have to set up something that would prompt it to keep "talking" (perhaps 'yes | llama-cli ...`)

[nisegami]

I think the concept you're talking about has been described as LLM attractor states. Here's a LW post about it for Deepseek v3 https://www.lesswrong.com/posts/rvbjZMp6aEDn2jiyp/mapping-ll...