prediction claim
The speaker expects compositional harnesses to make each language-model call in distribution, even when the overall task is out of distribution.
Alex Zhang · Academia is for Ambition — Alex Zhang, MIT · 2 Oct 2026
In their words
The transcript segments this claim was taken from
“If an RLM breaks down its computation into like a kind of a meta harness of sorts or like a program that involves sub agents that like look at a local problem,”
“every individual language model call over the course of this task is in distribution,”
“even if the entire task itself is out of distribution.”48:30Report a misattribution
0.78how strongly it was put, not whether it is true
0.78importance to the conversation
0.88confidence the claim was read correctly