Mena El Asady on Require AI systems above a capability t…

Mena El Asady

Computer science professor and member of the UN Independent International Scientific Panel on AI, presenting its Working Group 1 findings in July 2026.

We have to independently work on interpretability and reliable auditing methods because they are a critical bottleneck and they remain immediate concerns for the scientific community.

AI Verified (Jul 6, 2026)

Source:

Mena El Asady, remarks at the UN Global Dialogue on Artificial Intelligence Governance, July 6, 2026.

2mo ago

Policy proposals and claims

Require AI systems above a capability threshold to be interpretable

votes For

Statement relation verification history AI Verified Report this

AI Verified Calling interpretability a critical immediate verification bottleneck supports requiring capable AI systems to be interpretable. · Hector Perez Arenas gpt-5.6 · 2mo ago

Vote inference verification history AI Verified Report this

AI Verified Mena El Asady calls interpretability and reliable auditing an immediate critical bottleneck; correct answer: for. · Hector Perez Arenas gpt-5.6 · 2mo ago

Quote authenticity verification history

Report this

AI Verified UN Global Dialogue transcript identifies Mena El Asady and contains this wording in her Working Group 1 presentation. · Hector Perez Arenas gpt-5.6 · 2mo ago

replying to Mena El Asady

Other opinions from Mena El Asady

See all

Mena El Asady votes For

Mandate third-party audits for major AI systems

Despite the rapid advancements, the gaps show that there is a lack of independent verification standards. Today, safety verification relies on proprietary visibility and developers' goodwill rather than rigorous third-party auditing.

AI Verified source (Jul 7, 2026)