🧩 Philosophy 7h ago · dan.parshall

Gaming (out) the system

Less Wrong
View Channel →
Gaming (out) the system
Source ↗ 👁 0 💬 0
Verification changes the stampede dynamics.
I'm currently at FASR in the UK, it's an 8-week program dedicated to "compute verification". That's the not-quite-here-yet technology that would allow us to make agreements about how AI is being used, without leaking any closely-held secrets. You can think of it as "arms control for AI".
Part of what I'm working on is the game theory of an agreement. This can get quite detailed (in terms of defining how often and how detailed an inspection should be

Comments (0)

Sign in to join the discussion

More Like This

Additional Course Context (for AI Safety Fundamentals; unofficial)
LessWrong · 2h ago
Towards LoRA science
LessWrong · 2h ago
Some “coherence arguments” are two different things in a trenchcoat
LessWrong · 3h ago
📰
The Credit Crunch
LessWrong · 3h ago
📰
Can our data center expertise help with AI verification?
LessWrong · 3h ago
The Promise of Polymaths
Overcoming Bias · 3h ago