This week, I learned:

  • E2E is a cheap GPU hosting provider for India. About Rs 100/hr for a V100 16GB
  • Jetson NVIDIa is like Raspberry Pi with a GPU! But it’s expensive.
  • Sarvam.ai offers Indic text to speech
  • Jupyter Lite lets you run Jupyter notebooks in the browser
  • Piston lets you run Python code via a REST API
  • <link rel="modulepreload"> lets you load and compile modules early!
  • Ollama 0.2 can handle concurrent requests with only a little additional memory. (So can vLLM and DeepSpeed.)
  • Prompt engineering for code generators:
  • XML tags seem best to structure prompts across LLMs.
  • Instructor prompts by Ethan Mollick help teach better
  • Non-Negative matrix factorization apparantly aligns to intuition more than K-Means and hence would be a great fit for most cosine-similarity matrices (via Jaidev).
  • Segmind’s Hallo lets you animate a face to an audio clip
  • VoidEditor aims to be an open source Cursor alternative
  • Video of ChatGPT o1 + mini reproducing the methodology of a paper by writing the code - in 6 iterations. Here’s the repo. Prompts:
    1. You are a Python and Astrophysics expert who is tasked with helping me on my research project. Please read the following methods section of this research paper and re-create the Python code described.
    2. Thank you, this code looks really nice. I don’t have any actual data or noise cube ready at the moment, but could you please generate some test data that can be used in the code you just wrote: {CODE}
    3. Hi. thank you for writing the code! Unfortunately, it seems that I get an error when I try to run it. I’ve attached the error message below, can you please refine the code so that the error is resolved? {ERROR}
    4. Thank you, but when attempting to run the code that you provided, I received the following error: {ERROR}
    5. Hello, thank you for the code. but now I get the following error pasted below: {ERROR}
    6. Thank you, I think we are getting close to a final solutiom I still get an error, which I’ve pasted below: {ERROR}
  • Groq, SembaNova and Cerebras are fast inference models. All appear to be free
  • The skills required to vet the AI’s response is the same skillset used to vet a Pull Request. It’s a good way to teach code review. Source: My personal guide for developing software with AI
  • Prompt engineering tip: Tell LLMs another AI wrote code. Else they will agree with you!