Vinayak Nayak

Silence is strength
Data Sciences Engineer at Okkular

[Marius Vach @rasmus1610]

https://t.co/0iRba71vWD

[Vinayak Nayak @ElisonSherton]

@rasmus1610 @vishalahuja

[Vinayak Nayak @ElisonSherton]

@rasmus1610 @DSPyOSS Now I see your reply on discord to my question makes complete sense.

I was doing multistep classification and you helped me with a suggestion, now this module is going to make it 100% fault tolerant. Thanks!

[Marius Vach @rasmus1610]

I love this @DSPyOSS pattern for keeping a RAG pipeline faithful.

This way you *engineer* your system to spit out "I don't know" if the context doesn't contain the necessary information.

No need to threaten the LLM's grandma.

[Omar Khattab @lateinteraction]

I can’t believe I’m recommending a totally random AI summary I came across online but…

This 6-min NotebookLM video is an excellent summary of my perspective on the bitter lesson and what it means for AI engineers.

Link below.

[Marius Vach @rasmus1610]

✌️New blog post

We'll look at @DSPyOSS SIMBA optimizer and how it works.

It's a great start for understanding self-introspective prompt optimization and DSPy's newest optimizer GEPA, which will come out soon.

(link in first response)

[Connor Shorten @CShorten30]

GEPA is a SUPER exciting advancement for @DSPyOSS and a new generation of optimization algorithms re-imagined with LLMs! 🧩🚀

Starting with the title of the paper, the authors find that Reflective Prompt Evolution can outperform Reinforcement Learning!! 🤯

Using LLMs to write and refine prompts (for another LLM to complete a task) is outperforming (!!) highly targeted gradient descent updates using cutting-edge RL algorithms! ⚖️

GEPA makes three key innovations on how exactly we use LLMs to propose prompts for LLMs -- (1) Pareto Optimal Candidate Selection, (2) Reflective Prompt Mutation, and (3) System-Aware Merging for optimizing Compound AI Systems. 🧠🧠

The authors further present how GEPA can be used for training at test-time, one of the most exciting directions AI is evolving in! 🚀

Here is my review of the paper! I hope you find it useful! 🎙️

[DSPy @DSPyOSS]

We heard that y'all want visuals.

OK. Here's a (rather hideous!) visual with our philosophy on where you should invest in AI systems.

Our job is to give you the top block as composable pieces, so you can iterate fast on engineering the three foundational layers below it.

[Vinayak Nayak @ElisonSherton]

@MaximeRivest Wow, that's amazing! Can you share some details like how many classes were there in your task? Were they quite diverse or had overlaps in between them etc.

99% consistency is amazing!

[Aman Arora @amaarora]

Note: There will be no blog next week, I am working on a Kaggle competition. Hopefully, I will be able to make progress and write about it too. (🤞)

[PyTorch @PyTorch]

✨ Low Numerical Precision in PyTorch ✨
Most DL models are single-precision floats by default.
Lower numerical precision - while reasonably maintaining accuracy - reduces:

a) model size
b) memory required
c) power consumed

Thread about lower precision DL in PyTorch ->
1/11

[Vinayak Nayak @ElisonSherton]

@amaarora Amazing News! All the very best :)

[Aman Arora @amaarora]

Starting 01 Mar, 2023 I’ll be going back to blogging 1 post a week every Monday at 9am AEST.

These blogs will be about AI research, new technologies, updates, frameworks, Kaggle competitions and more.

If you have a topic that you’d like me to cover, please let me know. :)

[Quentin Lhoest 🤗 @lhoestq]

🤗Datasets 2.10 🔥 is out and faster than ever for shuffled datasets:

⚡️Speed x2 with a @PyTorch DataLoader
⚡️Speed x100 for saving/loading on disk

How ?

See how we did that, as well as 6 amazing new features 🧵👇

[Lavanya @lavanyaai]

The future of ML is being built on W&B.

Come find out how at our MLOps conference, Fully Connected on March 15!

🐝 Register at https://t.co/X9Q19TeBsY

Featuring speakers from @StabilityAI, @Spotify, @NVIDIAAI, Openai; people like @jeremyphoward, @sh_reya, @HamelHusain & more!

[meowbooks @meowbooksj]

Since the topic of model naming was brought up, here's a relevant #ThrowbackThursday now with the watermark redone to be less conspicuous.

[Library Mindset @librarymindset]

5)Art of War

[Library Mindset @librarymindset]

4)On The Shortness of Life

[Library Mindset @librarymindset]

12 Books To Read In 2023

1)

[Charly Wargnier @DataChaz]

📢 New #ChatGPT extension!

`ChatGPT Writer` is a Chrome extension for Gmail that uses ChatGPT to generate emails or replies based on your prompt! 🤯

See my demo video below 👇

Get it here:
🔗 https://t.co/iHz628k4Du
🌐 https://t.co/V2V1PeVJGN

@LinkedIn/@Outlook coming soon!