Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Ask HN: Has Anyone Trained a personal LLM using their personal notes?

news.ycombinator.com

Post reply on HN
Print view View original

21–30 of 77 posts

Re: Ask HN: Has Anyone Trained a personal LLM using their personal notes?

#21

Post by iamcreasy »

KMnO4 wrote: post #11

Maybe not exactly what you’re asking, but I started doing talk therapy last year. It’s done virtually and I record the session with OBS. As soon as the recording finishes, the following happens: - The audio is preprocessed (chunked) and sent to Whisper to generate a transcript - The transcript is sent to GPT-4 to generate a summary, action items, concepts introduced with additional information - The next meeting’s da…

Did you discover anything interesting by being able to review all the therapy sessions?

Re: Ask HN: Has Anyone Trained a personal LLM using their personal notes?

#22

Post by weikju »

xyst wrote: post #19
KMnO4 wrote: post #11

Maybe not exactly what you’re asking, but I started doing talk therapy last year. It’s done virtually and I record the session with OBS. As soon as the recording finishes, the following happens: - The audio is preprocessed (chunked) and sent to Whisper to generate a transcript - The transcript is sent to GPT-4 to generate a summary, action items, concepts introduced with additional information - The next meeting’s da…

[flagged]

I read this as the OP being the patient, not the doctor. Pretty sure a patient is free to violate this confidentiality

Re: Ask HN: Has Anyone Trained a personal LLM using their personal notes?

#23

Post by cjbprime »

Going to wait for longer context local models. Fine tuning/training is lossy compression of your notes into the model weights -- there isn't much value in a vaguely-remembered copy of some of my notes. This is why other comments are pointing you towards Retrieval Augmented Generation instead, where the relevant notes are losslessly added to the prompt.

Re: Ask HN: Has Anyone Trained a personal LLM using their personal notes?

#24

Post by ethbr1 »

weikju wrote: post #22
xyst wrote: post #19

Earlier quoted context omitted.

[flagged]

I read this as the OP being the patient, not the doctor. Pretty sure a patient is free to violate this confidentiality

Parent was probably referring to OpenAI having access to therapy notes, once GP sent them, and no legal responsibility to keep them private.

Re: Ask HN: Has Anyone Trained a personal LLM using their personal notes?

#26

Post by pb060 »

Gianluca Nicoletti, an Italian journalist, writer and radio speaker, is training a LLM with all writings as a support for his autistic child for when he won’t be here anymore. The software will speak with his voice.

https://www.lospessore.com/13/07/2023/una-chatbot-per-contin...

Re: Ask HN: Has Anyone Trained a personal LLM using their personal notes?

#27

Post by jdthedisciple »

brotchie wrote: post #4

Played around with fine tuning, but ended up just experimenting with RAG. One thing I haven’t worked out yet is the agent reliably understanding if it should do a “point retrieval query” or an “aggregation query.” Point query: embed and do vector lookup with some max N and distance threshold. For example: “Who prepared my 2023 taxes?” Aggregation query: select a larger collection of documents (1k+) that possibly don’…

Interesting, been waiting for some free time to do this myself.

Mind sharing how you set up your RAG pipeline and which (presumabely FOSS) components you incorporated?

Re: Ask HN: Has Anyone Trained a personal LLM using their personal notes?

#28

Post by jdthedisciple »

CSMastermind wrote: post #15

It sounds like you want RAG instead of training or even fine tuning a model. Have you looked into the OpenAI APIs? They make it relatively easy to do assuming you have some limited programming knowledge.

I have recently briefly looked into Assistants API (if that's what you're referring to) but it seems relatively if I'm not mistaken.

Re: Ask HN: Has Anyone Trained a personal LLM using their personal notes?

#29

Post by serial_dev »

ethbr1 wrote: post #24
weikju wrote: post #22

Earlier quoted context omitted.

I read this as the OP being the patient, not the doctor. Pretty sure a patient is free to violate this confidentiality

Parent was probably referring to OpenAI having access to therapy notes, once GP sent them, and no legal responsibility to keep them private.

I'm sure OP knows this, thought about the risk, guessed the probabilities, assessed the nature of her therapy sessions, and decided the system she was building is worth the risk of her therapy content being available with an intuitive chat interface.

Not every therapy session is embarrassing, incriminating, or particularly interesting to anyone but you.

Re: Ask HN: Has Anyone Trained a personal LLM using their personal notes?

#30

Post by TuringNYC »

dleslie wrote: post #5

I want this for my photos. I'm not a good photographer, but I have taken tens of thousands of photos of my family. I would love to provide a prompt for a specific day and persons and have it create a photo that I never was able to take. I don't mind that it's not "real" because I find photography to be philosophically unreal as it is. I want it to look good, and inspire my mind to recreate the day however it can imag…

This is basically what all the headshot generator apps do. It is pretty simple to achieve if you can spin up GPU instances (https://huggingface.co/docs/diffusers/v0.13.0/en/training/te....)

However, I find it challenging to achieve on Macbooks, despite all the neural core horsepower I have. If anyone has achieved this with non-NVIDIA setups i'd love to hear!

Post reply on HN