Gary Marcus asks OpenAI: does Astra's 2x computation depth mean it's half as monitorable as GPT-4?
GaryMarcus · x · 2026-09-04
Gary Marcus publicly presses OpenAI's merettm on a key technical claim: that "the depth of the computation graph for our present frontier models, including Astra, is within a factor of two of GPT-4." He asks what this means for monitorability — does it imply Astra is half as monitorable as GPT-4? — and whether the GPT-4 mention was a typo, inviting the community to weigh in.
More from Models
- New paper: supervising just 1% of tokens can match full on-policy distillation, 0.1% sometimes suffices — jiank_uiuc · 2026-09-23
- Sparse distillation paper: supervising just 0.1%-1% of tokens can match or beat full OPD — jiank_uiuc · 2026-09-23
- Distillation's real impact on Chinese labs debated: no hard evidence, says Lambert, maybe 1-2 month edge — xeophon · 2026-09-23
- Instinct hit by user-data mixing reports; Muse CEO trolls with a safety promise — alexandr_wang · 2026-09-23
- Computer-use faceoff: Grok skips using the computer and just generates the flower — socialwithaayan · 2026-09-23
- BridgeBench: Grok 4.7 is 50% pricier and 60% slower than Grok 4.6 with no quality gain — socialwithaayan · 2026-09-23