min76

Ask HN: What low risk passive income makes you feel secure?

Posted by min76 on Sunday December 31, 2023 @06:53AM
from the ask-hn dept.

I don't want to start yet another net worth for retirement/semi retirement thread. Because, 1. There is no right answer. 2. Text bookish answers like 40 or X times annual expenses don't take retained earnings and inflation into consideration.Lets put it this way. What passive income (pre tax) makes you comfortable, if you were to put all your current net worth ( Which excludes the house you...

( Read More... | 20 comments | 11 points | on HN )

Re:Ask HN: Coping with Career Dread on Sunday December 31, 2023 @06:24AM (#38823287)

I guess a lot of us are in the same boat. As others mentioned, the best option is to start something on your own.

Re:Ask HN: How do I train a custom LLM/ChatGPT on my own documents in ... on Monday December 25, 2023 @10:17AM (#38763274)

I have a related question. I have a fair idea of the LLM ecosystem. (Thanks to this very nice blog called Emerging Architectures for LLM Applications). The problem is, there are way too options in each component. ( For E.g, too many vector store implementations, ingestion engines etc) What is the easiest way to get started? Primarily around RAG on my own pdf files. Also, what is the best/easiest option for hosting?. That blog lists vercel,streamlit, streamship and modal. I know vercel at a high level and found it very good. I am not well versed with javascript/typescript though. I believe the best option for UI generation is to use one of their templates.

Ask HN: The easiest way to build an LLM application?

Posted by min76 on Monday December 25, 2023 @10:15AM
from the ask-hn dept.

I have a fair idea of the LLM ecosystem. (Thanks to this very nice blog called Emerging Architectures for LLM Applications). The problem is, there are way too options in each component. ( For E.g, too many vector store implementations, ingestion engines etc) What is the easiest way to get started? Primarily around RAG on my own pdf files.Also, what is the best/easiest option for hosting?. That...

( Read More... | no comments | on HN )

Re:Ask HN: How do I train a custom LLM/ChatGPT on my own documents in ... on Monday December 25, 2023 @12:41AM (#38760142)

Well said. The problem is, there are way too many alternatives. Any idea how llamaindex's ingestion engine compares to unstructured.io? ( Which is used in langchain)

Re:If only someone told me this before my first startup on Monday December 25, 2023 @12:12AM (#38760021)

14. Don't get ever distracted by hype, e.g. crypt0. I lost 1.5 years of my life this way. Currently there is a lot of hype around LLM. Do people think, it will go the same way?. I understand we cannot compare. But usually we get carried away assuming its different this time.

(Btw very nice thread. Thanks)