Julio Pereyra
@ItsJulioPereyra
Excited to run this back with GLM-5.2 and the @appliedcompute team!
Gabe Pereyra@gabepereyra · Jun 22Harvey partnered with @appliedcompute to train a legal agent.
We optimized each part of the agent stack, including the eval loop, agent harness and compaction, and post-trained the underlying GLM-5.1 model using reward signal from Harvey's Legal Agent Benchmark (LAB).
Check out
Open quoted post →We optimized each part of the agent stack, including the eval loop, agent harness and compaction, and post-trained the underlying GLM-5.1 model using reward signal from Harvey's Legal Agent Benchmark (LAB).
Check out
1 29