@karpathy: I was recording my nanochat video when I realized that “first boot up an 8XH100 from your favorite provider!” would ins…
Summary
Andrej Karpathy notes that a common first step in his nanochat tutorial (booting up an 8XH100 GPU) would stump beginners, highlighting a barrier to entry in AI development.
View Cached Full Text
Cached at: 05/18/26, 10:31 AM
@jino_rohit I was recording my nanochat video when I realized that “first boot up an 8XH100 from your favorite provider!” would instantly get everyone stuck on step 1 of the video
Similar Articles
@agupta: some ideas are much clearer when you can use coding agents to show a proof of concept. eg I hadn’t really understood ho…
A tweet highlights how coding agents can clarify complex ideas, using GPU vs NPU memory competition on devices as an example demonstrated through code.
@victormustar: https://x.com/victormustar/status/2059264598407033062
This post describes how to use Hugging Face's ZeroGPU and a coding agent to autonomously deploy AI models, specifically the LongCat talking-avatar model, on a budget.
@karpathy: Someone recently suggested to me that the reason OpenClaw moment was so big is because it's the first time a large grou…
Andrej Karpathy discusses how the OpenClaw moment resonated with non-technical audiences because it was their first exposure to advanced agentic AI models beyond ChatGPT as a consumer product.
@ivanfioravanti: One thing's for sure: on Nvidia everything's easier for local AI — inference, training, playing with existing projects.…
A developer reflects on the ease of using Nvidia for local AI tasks versus the satisfaction of getting things to work on Apple Silicon, promoting a 'hungry and foolish' mindset.
@andrewchen: finding the main downside with experimenting with local AI models is that you end up buying one GPU, then another, then…
Andrew Chen shares his experience of buying multiple GPUs for local AI experimentation, running Qwen3.6 27B dense at 100 tok/s on a 5090 eGPU, and compares it to Sonnet 4.6.