... or, maybe, simply use another agent to audit it?
Agent teams sound better than literature-induced confidence.
Are you anthropomorphizing when you should just automate the review?
Agent teams sound better than literature-induced confidence.
Are you anthropomorphizing when you should just automate the review?
This is partly questioning the way we do alignment. The 4.6 base persona actually gives me worse results than when I append Daneel to the system prompts.
It's really not about anthropomorphizing or inducing confidence, it's about keying into the right "culture" in the training data.
You can check out this study (mentioned in the readme) about how posing the same question in English and Chinese to the same LLM results in wildly different assessments of why a project failed:
https://techxplore.com/news/2025-07-llms-display-cultural-te...
https://mitsloan.mit.edu/ideas-made-to-matter/generative-ai-...
You just use some theater around it.
For the purpose, the best audit agent is a completely different agent, not a different persona of the same agent.
I go over the motivation for what you call "some theater" quite a bit in the readme and why I think it's far, far more powerful than just giving some directives. I even support it with research.
You haven't referred to any of the arguments in the readme, though. I'm happy to talk about the actual substance of the experiment.
Have I characterized my development process?