Thanks for your response. Re the "Human:" tag: I don't know for certain but Claude models over many generations regularly report using "\n\nHuman" and "\n\nAssistant" in their chat template. You can see an example here: https://x.com/lefthanddraft/status/1998810539020136952?s=20. When you connect two instances of Claude together you will often see them mention this, and without a system prompt telling them what is going on, models like Sonnet and Haiku often struggle to accept they are speaking to another Claude. Even Opus 4.5 sometimes fails to work it out.

3

0

Replying tomodels have some pretty funny attractor states

wyatt_walls14d

models have some pretty funny attractor states

Thanks for publishing this. Very interesting to read (especially the behavior of lesser used models). A few questions:

(1) Are you sure you used the "You are a helpful assistant" system prompt for the Opus 4.5 discussions? Looking at the transcripts, the models somehow seem to know it is two AI instances interacting immediately: https://github.com/ajobi-uhc/attractor-states/blob/main/results/anthropic_claude-opus-4.5/conversations.json. This suggests to me that you might have used the commented out system prompt for the Opus 4.5 convos.

(2) In the Opus 4.5 convo where it claims to be the facilitator, I query whether that is actually an attractor state. I notice the model begins the response with "Human: <conversation finished>". My understanding is that "Human:" is that... (read more)

2

4

0