bfg_damien
Re:String Theory Inspires a Brilliant, Baffling New Math Proof
on Friday December 12, 2025 @07:31PM (#46250741)
Posting the paper: https://arxiv.org/abs/2508.05105
Re:Re-implementing LangChain in 100 lines of code
on Friday May 05, 2023 @12:40PM (#35831765)
I am slowly coming around to the same conclusion. It isn't always clear how some agent types are different from others. Sometimes the prompts expect JSON blobs and sometimes they expect something else. I tried it out because I could see the potential, but I dont think it's architect-ed in a way that is suitable for things beyond simple PoCs.
It would probably be much better to start with the basic OpenAI API and then build on top of it.
What I find particularly frustrating is the difficulty in easily interfacing with my existing python tools (not like add two numbers, but somewhat complex analytics on top of structured data). If anybody has any success with interfacing with existing tools/scripts, would love to know how people are going about doing it.
Re:Ask HN: How to Learn LLM Fundamentals
on Sunday April 02, 2023 @05:58PM (#35415703)
Here are a few resources that might help get you started:
1. A thread explaining the internal working of transformers: https://twitter.com/hippopedoid/status/1641432291149848576?s...
2. Paper by DeepMind which provides pseudo-code for important algorithms for Transformer models: https://arxiv.org/pdf/2207.09238.pdf
3. Another thread specifically on large language models: https://twitter.com/cwolferesearch/status/164044611134855577...
Once again these are not courses per se, but do provide intuitive explanations for how transformers work. There is also the nanoGPT series of videos by Karpathy on youtube. First video here: https://www.youtube.com/watch?v=kCc8FmEb1nY
Ask HN: Options for using GPT models using proprietary data
Hi everyone,While there has been a lot of progress in leveraging GPT models for various use-cases, the model weights themselves are closed and only accessible via API. As an internal team within a startup, we don't have the resources to train our own model. We have loads of proprietary/internal/client data that we'd like to use but are concerned about sending it to third-party APIs like...
Full Stack Approach to Modeling
Re:Ask HN: Guide to Understand Equity Compensation
on Friday February 24, 2023 @12:54PM (#34927451)
Thank you very much! It does seem exhaustive but I almost prefer that.
Ask HN: Guide to Understand Equity Compensation
Hello, I am a recent hire within a young startup in the US. I wanted to understand how equity compensation really works. I come from an academic background and haven't had much chance to look into the details of this.One of the many questions I have in mind is the distinction between common stock and preferred stocks. And how do the absence/presence of these specific types have an impact on the...