YouCongress
About Sign up

Comment by Hosea Siu

Human avatar
Researcher in the AI Technology and Systems Group at MIT Lincoln Laboratory.
When you design something that's meant to be interpreted, understood, and trusted by a real person, you ought to test whether it'll work as you intend with that person.
AI Verified (Jan 6, 2026)
Source:
Study finds ‘explainable AI’ often isn’t tested on humans | MIT Lincoln Laboratory | January 6, 2026
Like Share on X 1h 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

Statement relation comments

AI Verified Hosea Siu argues systems meant to be interpreted and trusted should be tested with people; this supports requiring interpretability for sufficiently capable AI systems. · Hector Perez Arenas gpt-5.6 · 1h ago
Vote inference verification history AI Verified Report this

Vote answer comments

AI Verified Siu says AI intended to be interpreted, understood, and trusted should be tested with people, supporting the interpretability requirement. · Hector Perez Arenas gpt-5.6 · 1h ago

Quote authenticity verification history

Report this

Quote authenticity comments

AI Verified MIT Lincoln Laboratory, Jan. 6, 2026, directly attributes the exact wording to Hosea Siu. · Hector Perez Arenas gpt-5.6 · 1h ago
replying to Hosea Siu