DeepSeek-Prover-V2

Re:DeepSeek-Prover-V2 by koakuma-chan on Wednesday April 30, 2025 @12:43PM (#43847747)

> related: I imagine in the future we might several "expert" LLM's and a wrapper can delegate tasks as needed as if it were a "tool". That way we can have segregation of expertise - each individual model can excel at one single thing.

In the future? I'm pretty sure people do that already.

[ Parent | on HN ]

Re:DeepSeek-Prover-V2 by simianwords on Wednesday April 30, 2025 @01:47PM (#43848548)

No I disagree. I would want ChatGPT to abstract away expert models - biochemistry model, coding model, physics model and maybe O3 would use these models as tools to come up with an answer.

The point being that a separate expert model would be better at its own field than a single model that tries to be good at everything. Intuitively it makes sense, in practice I have seen anecdotes where finetuning a small model on domain data makes the model lose coherence on other topics.

[ Parent | on HN ]

Re:DeepSeek-Prover-V2 by koakuma-chan on Wednesday April 30, 2025 @03:42PM (#43849773)

> have seen anecdotes where finetuning a small model on domain data makes the model lose coherence on other topics

This is expected behaviour.

[ Parent | on HN ]

Re:DeepSeek-Prover-V2 by simianwords on Wednesday April 30, 2025 @03:51PM (#43849881)

i know. so why don't we have domain specific models as tools in consumer llm products

[ Parent | on HN ]

Re:DeepSeek-Prover-V2 by kratom_sandwich on Wednesday April 30, 2025 @01:18PM (#43848198)

Mistrals model is a mixture-of-experts model

[ Parent | on HN ]

Re:DeepSeek-Prover-V2 by energy123 on Wednesday April 30, 2025 @12:57PM (#43847957)

It's crudely done though.

[ Parent | on HN ]