# @davidad — 2024-12-21

♥97 ↻4 · https://x.com/davidad/status/1870529763300831464

o1 doesn’t do tree search, or even beam search, at inference time. it’s distilled.what about o3?we don’t know—those inference costs are very high—but there’s no inherent reason why it must be un-distill-able, since Transformers are Turing-complete (with the CoT itself as tape) https://t.co/hFRZyxverP

tags: author:davidad, kind:tweet, model:o1, model:o3, on:o1, year:2024
cited on: _dossiers/o1.md, o1
