iiinova — where your digital self keeps evolving

Reposted by Rick Lamers

Rupert Manfredi @ruperts.world · 09/12/2024

Haven't heard of web applets? It's a web-based protocol for building software that both humans & AI can understand and use together. github.com/unternet-co/...

github.com

GitHub - unternet-co/web-applets: The home of the Web Applets spec, demo and SDK

The home of the Web Applets spec, demo and SDK. Contribute to unternet-co/web-applets development by creating an account on GitHub.

031

Reposted by Rick Lamers

Jonathan Ross @jonathan-ross.bsky.social · 06/12/2024

(1/5) "The reports of the LLM scaling laws' demise have been greatly exaggerated." techcrunch.com/2024/12/06/m...

143

Rick Lamers @ricklamers.bsky.social · 29/11/2024

"Babe, I'm curve fitting to my hand drawn loss curve, look, look"

000

Rick Lamers @ricklamers.bsky.social · 29/11/2024

I slept on Windsurf Editor longer than I should have, try it, it's amazing. Much more agentic than Cursor 🤖 codeium.com/windsurf

000

Rick Lamers @ricklamers.bsky.social · 28/11/2024

I was inspired to create a web app that demonstrates the universal approximation power of neural networks using TensorFlow(.js), try it and hack around with the source code!

110

Rick Lamers @ricklamers.bsky.social · 28/11/2024

The Universal Approximation Theorem for neural networks by Michael Nielsen in his custom Magic Paper app, just brilliant. youtu.be/Ijqkc7OLenI

youtu.be

The Universal Approximation Theorem for neural networks

YouTube video by Michael Nielsen

010

Reposted by Rick Lamers

Jonathan Ross @jonathan-ross.bsky.social · 28/11/2024

(1/5) The question I get asked a lot is, “Should I be afraid of AI?” There was this guy who got in a lot of trouble once, his name was Galileo.

293

Reposted by Rick Lamers

Simon Willison @simonwillison.net · 25/11/2024

Anthropic released an interesting thing today: an attempt at a standard protocol for LLM tools to talk to services that provide tools and extra context to be used other the models modelcontextprotocol.io

modelcontextprotocol.io

Introduction - Model Context Protocol

Get started with the Model Context Protocol (MCP)

1837652

Rick Lamers @ricklamers.bsky.social · 24/11/2024

You probably haven't heard of PydanticAI yet, but I'm sure you have heard of Pydantic. Check it out, it's a VERY neat way to build agentic LLM-backed programs using all the goodness types and structured outputs give you. The agent framework you won't hate? Groq + PydanticAI = 🚀

github.com

add Groq client support by ricklamers · Pull Request #84 · pydantic/pydantic-ai

Added GroqModel class to interact with Groq API. Implemented structured and text-based responses for Groq models. Added example and tests for Groq model integration. Updated dependencies to include...

100

Rick Lamers @ricklamers.bsky.social · 24/11/2024

Karazhan (raid) according to FLUX 1 Schnell

000

Rick Lamers @ricklamers.bsky.social · 23/11/2024

Image generation is just TOO MUCH FUN! Fast prompt generation with Groq ✅ Fast image generation with Fal.ai ✅ Open Source (MIT) ✅ ⚙️ pip install pyimagen

153

Reposted by Rick Lamers

Eugene Yan @eugeneyan.com · 23/11/2024

Evals are "too damn expensive" until you: • can't migrate underlying models safely • can't add new features with confidence • can't ship without HITL evals, which takes >100x longer • product development and iteration grinds to a halt • lose customer trust due to poor user experience

3215

Rick Lamers @ricklamers.bsky.social · 19/11/2024

Power of open! Groq hosted open source models + open Bsky platform data (through their API search). Search for your favorite topic on Bsky and get instant answers plus post links! Link: groq-bsky.vercel.app

120

Rick Lamers @ricklamers.bsky.social · 19/11/2024

Important reason to move to Bluesky: you can hack on it because the data is much easier to access 🔥

010

Rick Lamers @ricklamers.bsky.social · 19/11/2024

This meme holds surprisingly well. AWS ushered in an era where infra was no longer a differentiating factor, all startups built on cloud and moats continued to exist (network effects, momentum, proprietary data, etc.). AI APIs = new cloud layer.

120

Rick Lamers @ricklamers.bsky.social · 19/11/2024

"if you can compress data well, you understand its patterns" Low loss on training error + highly compressible hypothesis = strong generalization

110

Rick Lamers @ricklamers.bsky.social · 19/11/2024

I love how bolt.new invites you to try new stacks, like building with Remotion for programmatic video generation.

110

Reposted by Rick Lamers

karpathy @karpathy.bsky.social · 27/05/2023

How can you not be jealous when you copy paste a long passage of text to GPT-4, ask it to eg summarize and see tokens flowing moments later

212305

Rick Lamers @ricklamers.bsky.social · 29/05/2023

OpenAI has been slow to roll out ChatGPT Code Interpreter access to everyone (including me). So I thought it would be fun to code my own version, you can use it today and it's Open Source! github.com/ricklamers/gpt-code-ui

100

Rick Lamers @ricklamers.bsky.social · 26/05/2023

Great example of why mathematical understanding of eg matrix decompositions is key for optimizing existing methods. You might not need math to utilize other people’s work in machine learning but be prepared to bring a mathematical toolkit if you’re looking to innovate.

lightning.ai

Parameter-Efficient LLM Finetuning With Low-Rank Adaptation (LoRA) - Lightning AI

In the rapidly evolving field of AI, using large language models in an efficient and effective manner is becoming more and more important. In this article, you will learn how to tune an LLM with Low-Rank Adaptation (LoRA) computationally efficiently!

000