GitHub - openai/openai-python: The official Python library for the OpenAI API · GitHub
GitHub - openai/openai-python: The official Python library for the OpenAI API · GitHub
29
Public whispers
7
Contributors
2026-07-16 09:47:54
First whispered
Discussion activity
Public whispers on github.com over the last 17 weeks
LessMore
Recent public whispers
Text Highlight2026-08-02 09:09:18
Original Highlight Excerpt
"curl http://localhost:11434/api/chat"
Whisper Note
curl command straight into terminal, love how simple it is.
Text Highlight2026-08-01 03:09:18
Original Highlight Excerpt
"standard interface for models, embeddings, vector stores, and more."
Whisper Note
Thats the core value prop right there, a standard interface for everything LLM.
Text Highlight2026-07-30 21:09:18
Original Highlight Excerpt
"not a modular toolbox of building blocks for neural nets."
Whisper Note
That's a refreshing take, keeping it simple for researchers to hack on.
Text Highlight2026-07-25 13:07:23
Original Highlight Excerpt
"Make your ML code future-proof by avoiding framework lock-in."
Whisper Note
Honestly, just pick one and stick with it, rewrites cost way more time.
Text Highlight2026-07-25 12:58:23
Original Highlight Excerpt
"Make your ML code future-proof by avoiding framework lock-in."
Whisper Note
Yeah but every framework has its own quirks, porting is never that clean.
Text Highlight2026-07-25 10:04:23
Original Highlight Excerpt
"Keras 3 is a multi-backend deep learning framework, with support for JAX, TensorFlow, PyTorch, and OpenVINO"
Whisper Note
OpenVINO support is nice, but who really uses that for training?
Text Highlight2026-07-25 09:55:23
Original Highlight Excerpt
"Keras 3 is a multi-backend deep learning framework, with support for JAX, TensorFlow, PyTorch, and OpenVINO"
Whisper Note
I've been using Keras with TF for years, this is a game changer.
Text Highlight2026-07-25 09:46:23
Original Highlight Excerpt
"Keras 3 is a multi-backend deep learning framework, with support for JAX, TensorFlow, PyTorch, and OpenVINO"
Whisper Note
Multi-backend sounds great but I worry about lock-in to the Keras API.
Text Highlight2026-07-24 13:07:18
Original Highlight Excerpt
"No token limit for prompts (original stable diffusion lets you use up to 75 tokens)"
Whisper Note
Haha, now I can write my entire fanfic in one prompt.
Text Highlight2026-07-24 12:58:18
Original Highlight Excerpt
"No token limit for prompts (original stable diffusion lets you use up to 75 tokens)"
Whisper Note
Wait, really? I always hit the 75 cap, that's gonna change everything.
Text Highlight2026-07-24 10:04:18
Original Highlight Excerpt
"Attention, specify parts of text that the model should pay more attention to"
Whisper Note
Does the Ctrl+Up thing actually work on Mac? I've been doing it manually all this time.
Text Highlight2026-07-24 09:55:18
Original Highlight Excerpt
"Attention, specify parts of text that the model should pay more attention to"
Whisper Note
I always wondered what those double parentheses did, now I finally get it.
Text Highlight2026-07-24 09:46:18
Original Highlight Excerpt
"Attention, specify parts of text that the model should pay more attention to"
Whisper Note
So that's how you make the model focus on the bowtie instead of the whole suit, neat.
Text Highlight2026-07-23 12:39:46
Original Highlight Excerpt
"Seamless integration with popular Hugging Face models"
Whisper Note
That's the main reason I switched from other engines honestly.
Text Highlight2026-07-23 12:30:46
Original Highlight Excerpt
"Seamless integration with popular Hugging Face models"
Whisper Note
Yeah, but sometimes the custom models still break, you know?
Text Highlight2026-07-23 09:36:46
Original Highlight Excerpt
"Efficient management of attention key and value memory with PagedAttention"
Whisper Note
I remember struggling with OOM errors before this—glad it's open source.
Text Highlight2026-07-23 09:27:46
Original Highlight Excerpt
"Efficient management of attention key and value memory with PagedAttention"
Whisper Note
But does it actually work well with existing models out of the box?
Text Highlight2026-07-23 09:18:46
Original Highlight Excerpt
"Efficient management of attention key and value memory with PagedAttention"
Whisper Note
PagedAttention sounds like a game changer for long context windows.
Text Highlight2026-07-22 16:10:00
Original Highlight Excerpt
"These models are not finetuned for chat or Q&A."
Whisper Note
So basically they're just raw text generators, not chatbots.
Text Highlight2026-07-22 13:07:00
Original Highlight Excerpt
"the links expire after 24 hours and a certain amount of downloads."
Whisper Note
Ha, classic—just when you think you got it, the link dies on you.
Ranked nearby
See what people are saying on github.com
Install DomWhisper to view live whispers as you browse, and join the discussion.
Get the extension