From the original source:
YouTube — Andrej Karpathy
Read full article at YouTube — Andrej KarpathyThis material was compiled from public sources. If its publication affects your rights → Request removal
Building makemore Part 2: MLP
Hi everyone. Today we are continuing our implementation of makemore. Now in the last lecture we implemented the bigram language model and we implemented both using counts and also using a super simple neural network that had a single linear layer. Now this is the Jupyter…
AI Summary & Key Takeaways
- Hi everyone
- Today we are continuing our implementation of makemore
- Now in the last lecture we implemented the bigram language model and we implemented both using counts and also using a super simple neural network that had a single linear layer
Event timeline
- Knowledge base
Building makemore Part 5: Building a WaveNet
- Knowledge base
Building makemore Part 4: Becoming a Backprop Ninja
Related stories
Stop paying for AI, run everything locally (here’s how)
Big labs are not going to talk about this but continual learning the idea of improving the models for your [music] own use cases for your own workflows. Big labs have no incentive of providing users with that [music] because they're training their models for the normal…
Sam Altman Reveals OpenAI's FINAL PLAN (It's Insane)
Sam Alman, the CEO of OpenAI, the company behind ChatGpt, just told his own employees that there are only three ways this whole AI race can end. And one of those endings is a single company getting so powerful that it can literally melt everyone else's GPUs. This is not a…
Learn to build to better AI Agents through better Context
Learn More: https://bit.ly/4yy5iWP The longer an agent works, the more repeated, contradictory, or stale information builds up in its context. Models perform worse as their context grows, a problem Jeff Huber and his team at Chroma named Context Rot. In our new course, Context…
Giannis x Google Search: Miami Pickup Hoops
Live from the 305. I've been in Miami for a minute. I haven’t seen no streetball. [a player shouting] Let's go! That's what I'm talking about. [Giannis continues] Let's see what Google Search can do. [Giannis voicing the query] Okay. [Giannis continues] José Martí. Okay. Yes,…