News for hackers. Stuff that matters.
Re:Auto-Differentiating Any LLM Workflow: A Farewell to Manu... by meame2010 on Saturday February 01, 2025 @01:53PM (#42901028)
We use gpt4o as the backward model. But I’m excited to try deepseek r1 as it has explicit reasoning available.

We are continuously adding more benchmarks to the paper with UTAustin.

There are no comments on this comment yet.