Harvey Post-Trains GLM-5.2 with Applied Compute: 50% Cost Reduction, Better Quality

ypatil125 · x · 2026-08-15

Legal AI company Harvey partnered with Applied Compute to post-train GLM-5.2 for its Review Table product, cutting inference costs by 50% while improving answer and citation quality. Review Tables let lawyers upload up to 10,000 documents and ask up to 500 questions each, generating up to 5 million model queries. In July, the largest query cost $26,000 in inference. Training data came from open-source legal corpora, with frontier models simulating user personas to generate realistic queries and answers.

Related event: Harvey Post-trains GLM-5.2 to Cut Legal AI Costs by 50%(4 posts)→

Original post →

More from Companies & People

Companies & People channel →