Large generator, small verifier: splitting the work to cut the cost of intelligence

agihouse_org · x · 2026-11-17

Part of the AGI House thread on Azalia Mirhoseini's cost thesis: split the work so a large model generates many candidate answers and a much smaller verifier picks the best one — cutting the cost of intelligence per dollar.

Related event: Large Language Monkeys: Sampling Lets Llama 3 8B Beat GPT-4o(2 posts)→

Original post →

More from Infra

Infra channel →