Re:Show HN: Is AI hijacking your intent? A formal control al...
by daikikadowaki on Sunday January 11, 2026 @09:58AM
(#46576257)
No apologies needed—I'm just glad to find I'm not the only 'insane' person here. It's easy to feel that way when obsessing over these problems, so knowing my ideas resonate with what you're building at superego is a huge relief.
I’m diving into your repo now. Please keep me posted on your progress or any new thoughts—I'd love to hear them.
Re:Show HN: Is AI hijacking your intent? A formal control al...
by judahmeek on Sunday January 11, 2026 @06:33PM
(#46581703)
> as it does make all these LLMs orders of magnitude more useful
That seems like something that should be really easy to prove statistically.
Re:Show HN: Is AI hijacking your intent? A formal control al...
by daikikadowaki on Sunday January 11, 2026 @07:01PM
(#46581931)
As for "proving it statistically"—you're looking for utility, but I'm defining legitimacy. A constitution isn't a tool designed to statistically improve a metric; it is a framework to ensure that the system remains aligned with human agency. I am not building an LLM optimization plugin; I am building a benchmark for human-AI co-evolution
https://github.com/open-horizon-labs/superego is probably the most useful tool we have, but I'm hoping that we can package it and bring it to the people, as it does make all these LLMs orders of magnitude more useful