Harvey and Applied Compute Post-Train Legal Model, Pushing Quality-Cost Frontier
ypatil125 · x · 2026-08-15
Harvey and Applied Compute post-trained a model for Harvey's Review Table, significantly improving the quality-cost Pareto frontier. Key methods include building a corpus of public legal documents, using oracle agents to generate expert-reviewed query-answer-citation tuples, designing a reward function with sentence-level citation precision/recall, and leveraging domain expertise from Harvey's legal researchers.
Related event: Harvey Post-trains GLM-5.2 to Cut Legal AI Costs by 50%(4 posts)→
More from Companies & People
- Course: Building Intelligent C# Apps — adnan_hashmi · 2026-08-15
- Bloomberg criticized for misleading headline on OpenAI ARR — ns123abc · 2026-08-15
- Anthropic Safety Report Contradicted by Claude: Understaffed Safety Teams a Growing Concern — Miles_Brundage · 2026-08-15
- Tim Ferriss: Has AI already killed how-to nonfiction? Sales trends and personal data reveal impact — TuhinChakr · 2026-08-15
- Stanford HAI Launches Human-Centered AI for Social Impact Program for Nonprofits and Government Leaders — StanfordHAI · 2026-08-15
- Farming Robots' Toughest Problem Is Mud, Not AI — Engineers Build World Models to Sense It — Scobleizer · 2026-08-15