Ayushi Agarwal

I am this person!

Choose a list of delegates

to vote as the majority of them.

Unless you vote directly.

Author of a 2026 paper on formal limits of AI alignment verification.

Speaks on: AI AI Governance AI Policy AI Regulation AI Risk

I am this person!

ai (1) ai-governance (1) ai-policy (1) ai-regulation (1) ai-risk (1) ai-safety (1) × ethics (1) existential-risk (1) future (1)

Top New

AI alignment is solvable
34 opinions

Ayushi Agarwal votes Against and says:

I am this person! Add a sourced quote Report comment

We prove that no verification procedure can simultaneously satisfy three properties: soundness (no misaligned system is certified), generality (verification holds over the full input domain), and tractability (verification runs in polynomial time). E...
more AI Verified source (Mar 8, 2026)

added 2h ago