JoshuaZ comments on Tiling Agents for Self-Modifying AI (OPFAI #2)

[JoshuaZ]

I don’t think this can’t happen, since A has proven Con(B), then it can now reason using system B for consistency purposes and get from the fact that B proves Con(A) to get A proving Con(A), which is bad.

[jsteinhardt]

Thanks for pointing this out. My mathematical logic is rusty.