Organization · Company
Prime Intellect
A company offering an integrated compute, training, inference and sandbox stack; developer of TOPLOC, a hashing scheme for verifying LLM inference.
Prime Intellect describes itself as offering an integrated compute, training, inference and sandbox stack for AI models. Its verification work centres on TOPLOC, a form of sampled inference recomputation:
- TOPLOC paper. Seven of the eight authors of the ICML 2025 paper that introduces TOPLOC are at Prime Intellect 1. The provider records the largest activations of the last hidden layer, so that a verifier who re-runs the sequence can check the claimed model, prompt and precision 1.
- Open-source code. Prime Intellect publishes TOPLOC as an MIT-licensed Python package 2, and reports integrations with vLLM and a fork of SGLang 3.
- Use in its own runs. Prime Intellect reports that each inference worker in its INTELLECT-2 decentralized training run generated a TOPLOC proof for every sequence 4. It reports using a later version, TOPLOC v2, to check thousands of nodes in the SYNTHETIC-2 data-generation run 5.
Implementations
- TOPLOC is a hashing scheme from Prime Intellect that lets a verifier check whether an inference provider ran the model, prompt and precision it claims.
Mechanisms
Mechanisms this organization has designed, built, evaluated or supplied.
- A verifier re-runs a random sample of an AI provider's logged queries on a trusted copy of the declared model and checks the outputs match.
Publications
Sources this organization authored or published.
- BPrime Intellect Team et al. (2025). INTELLECT-2: A Reasoning Model Trained Through Globally Decentralized Reinforcement Learning. arXiv. RecordCited by Sampled inference recomputation; TOPLOC; Prime Intellect
- BPrime Intellect (2025). PrimeIntellect-ai/toploc (GitHub repository). GitHub. RecordCited by Sampled inference recomputation; TOPLOC; Prime Intellect
- CPrime Intellect (2025). SYNTHETIC-2. Prime Intellect blog. RecordCited by TOPLOC; Prime Intellect
- AJ. M. Ong et al. (2025). TOPLOC: A Locality Sensitive Hashing Scheme for Trustless Verifiable Inference. Proceedings of the 42nd International Conference on Machine Learning (PMLR 267), pp. 47196-47211. RecordCited by Sampled inference recomputation; TOPLOC; Prime Intellect
- CPrime Intellect (2025). TOPLOC: A Locality Sensitive Hashing Scheme for Trustless Verifiable Inference (blog post). Prime Intellect blog. RecordCited by TOPLOC; Prime Intellect
Sources
- AJ. M. Ong et al. (2025). TOPLOC: A Locality Sensitive Hashing Scheme for Trustless Verifiable Inference. Proceedings of the 42nd International Conference on Machine Learning (PMLR 267), pp. 47196-47211. Source recordSupports: TOPLOC paper; seven of the eight authors at Prime Intellect; what the method checks
- BPrime Intellect (2025). PrimeIntellect-ai/toploc (GitHub repository). GitHub. Source recordSupports: open-source TOPLOC package (MIT licence)
- CPrime Intellect (2025). TOPLOC: A Locality Sensitive Hashing Scheme for Trustless Verifiable Inference (blog post). Prime Intellect blog. Source recordSupports: vLLM and SGLang integrations (provider-reported)
- BPrime Intellect Team et al. (2025). INTELLECT-2: A Reasoning Model Trained Through Globally Decentralized Reinforcement Learning. arXiv. Source recordSupports: TOPLOC proofs in the INTELLECT-2 training run (provider-reported)
- CPrime Intellect (2025). SYNTHETIC-2. Prime Intellect blog. Source recordSupports: TOPLOC v2 in the SYNTHETIC-2 run (provider-reported)