Source · Tier B · PreprintSource · What does it take to catch a Chinchilla? Verifying Rules on Large-Scale Neural Network Training via Compute Monitoring
What does it take to catch a Chinchilla? Verifying Rules on Large-Scale Neural Network Training via Compute Monitoring
Y. Shavit. 2023. arXiv.
| Original | https://arxiv.org/abs/2303.11341 |
|---|---|
| DOI | 10.48550/arXiv.2303.11341 |
| arXiv | 2303.11341 |
| Version | Read arXiv v2 (30 May 2023). |
| Accessed | 2026-09-25 |
| Imported from | hodgkins-ai-verification-papers@c71e59ff0e8e |
| Note | Listed under "Proof of learning and training" in the Hodgkins bibliography (CC BY 4.0). |
Cited by
- R2Training-transcript verification (proof-of-learning)⚠
- Communication between compute groups is bounded
- Chips are where they are declared to be
- Compute stock is at most a declared amount
- This compute runs inference, not training
- There is no undeclared relevant compute
- A training run stayed within declared limits
- Evidence binding
- FLOP accounting
- Inference and training workloads
- Numerical nondeterminism
- Positive and negative claims
- Prover
- Recomputation
- Root of trust
- Sampling and assurance
- Tamper evidence and tamper resistance
- Threat model
- Undeclared compute
- Verifier