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.
More from Companies & People
- MIT Biology and Schwarzman College hiring tenure-track professor in computational biology with generative AI focus — anshulkundaje · 2026-10-16
- DynaRobotics CEO Lindon Gao on running deployment and research feedback loops together — micoolcho · 2026-10-16
- Companies rushed in on AI. Now some are pulling back — return2ozma · 2026-10-16
- ai& × AMD Build Day hackathon in Tokyo: 8 teams, 4.5 hours, Chinese models allowed — DavidBennett__ · 2026-10-16
- Sakana AI opens first dedicated ISV, SI and CS roles in Japan GTM push — SakanaAILabs · 2026-10-16
- Kaggle teams with Google DeepMind and Zapier for inaugural Bench Summit — jocarrasqueira · 2026-10-16