News for hackers. Stuff that matters.
Re:Auto-Differentiating Any LLM Workflow: A Farewell to Manu... by xg15 on Saturday February 01, 2025 @05:14AM (#42897330)
Just read the abstract so far. Sounds amazing, but just for the sake of understanding, what would be the inputs and outputs of such a system? If the prompt is generated, how do you tell the system what you'd like to have? And what is the ground truth that is trained against? Examples of the desired text?
Re:Auto-Differentiating Any LLM Workflow: A Farewell to Manu... by amelius on Saturday February 01, 2025 @08:02AM (#42897987)
I think what they mean is intermediate prompts, i.e. the prompts that the system gives to itself when solving a problem that requires multiple stages.
Re:Auto-Differentiating Any LLM Workflow: A Farewell to Manu... by xg15 on Saturday February 01, 2025 @09:36AM (#42898608)
Ah, that makes sense. So (very) basically, they're putting a number of regular LLMs into a sort of compute chain/graph, where one LLM feeds into the other, then doing gradient descent on the whole chain at once, essentialy treating the boundaries between LLM n and LLM n+1 as "hidden layers"?
Re:Auto-Differentiating Any LLM Workflow: A Farewell to Manu... by meame2010 on Saturday February 01, 2025 @01:48PM (#42900977)
Author here. Yea, in this fashion. And it can create the feedback using llm as a backward engine