Ryan Angilly
LightNews LightNews
angilly.bsky.social
Ryan Angilly
@angilly.bsky.social
31 followers 34 following 25 posts
Applied Research @ NVIDIA
Posts Replies Media Videos
Reposted by Ryan Angilly
bdagnino.com
Super excited about PydanticAI. Looking forward to taking it out for a spin.
December 2, 2024 at 4:36 PM
angilly.bsky.social
As an aside to the broader goal of the below thread, this is a question so many people have right now: “when do I start fine tuning?”

I’ve yet to see good answers.

We are still so early!!
ssp.sh Simon Späti 🏔️ @ssp.sh · Dec 2
awesome! Wdyt, to what size or amount of notes does RAG work, and when does "training" a model make more sense? I wonder as I have 7k+ notes with huge notes, that RAG might not be enough, but I'm not experienced in it, so I do not know.
December 2, 2024 at 1:27 PM
angilly.bsky.social
In Context Learning is underrated.
bdagnino.com Bruno. @bdagnino.com · Dec 2
🚀 [NEW POST] Show, Don’t Tell: How Dynamic Examples Boosted Accuracy from 61% to 97%

Ever spent hours fine-tuning prompts or testing document parsing libraries, only to end up with meh results? What if I told you that one simple change could drastically improve your results?
December 2, 2024 at 1:12 PM
Reposted by Ryan Angilly
tedunderwood.com
Did you know that attention across the whole input span was inspired by the time-negating alien language in Arrival? Crazy anecdote from the latest Hard Fork podcast (by @kevinroose.com and @caseynewton.bsky.social). HT nwbrownboi on Threads for the lead.
Transcript of Hard Fork ep 111: Yeah. And I could talk for an hour about transformers and why they are so important. But I think it's important to say that they were inspired by the alien language in the film Arrival, which had just recently come out. And a group of researchers at Google, one researcher in particular, who was part of that original team, was inspired by watching Arrival and seeing that the aliens in the movie had this language which represented entire sentences with a single symbol. And they thought, hey, what if we did that inside of a neural network? So rather than processing all of the inputs that you would give to one of these systems one word at a time, you could have this thing called an attention mechanism, which paid attention to all of it simultaneously. That would allow you to process much more information much faster. And that insight sparked the creation of the transformer, which led to all the stuff we see in Al today.
December 1, 2024 at 2:50 PM
angilly.bsky.social
Playing around with @anthropic.com MCP stuff, and found out the hard way that www.claudedesktop.com is not claude.ai/download 😬

Anyway it's working now!

#llm #genai
December 1, 2024 at 5:06 AM
Reposted by Ryan Angilly
tomasz-fm.bsky.social
Ever wondered how AI autocomplete works? In this thread I’ll walk you through how we work with LLMs at @continuedev.bsky.social to decipher user intent and provide them with useful completions.

Continue is open source so I’ll post links to relevant code on Github at the end of this thread.
November 30, 2024 at 5:06 PM
angilly.bsky.social
@dannynewman.bsky.social dude what do we do here?
November 27, 2024 at 2:50 PM
Reposted by Ryan Angilly
dannynewman.com
I should probably post something so I don’t look like a noob.
November 18, 2024 at 5:06 AM
angilly.bsky.social
Joined up and said I was interested in tech, science, programming but Discover feed is none of that!

How do I find my genAI nerds?!
November 21, 2024 at 2:58 PM