Deep Dive into LLMs like ChatGPT
3:31:24
YouTubeAndrej Karpathy
Deep Dive into LLMs like ChatGPT
This is a general audience deep dive into the Large Language Model (LLM) AI technology that powers ChatGPT and related products. It is covers the full training stack of how the models are developed, along with mental models of how to think about their "psychology
已浏览 437.1万 次11 个月之前
Andrej Karpathy: Most Viewed Videos
The spelled-out intro to neural networks and backpropagation: building micrograd
2:25:52
The spelled-out intro to neural networks and backpropagation: building micrograd
YouTubeAndrej Karpathy
已浏览 309.3万 次2022年8月16日
How I use LLMs
2:11:12
How I use LLMs
YouTubeAndrej Karpathy
已浏览 216.3万 次10 个月之前
The spelled-out intro to language modeling: building makemore
1:57:45
The spelled-out intro to language modeling: building makemore
YouTubeAndrej Karpathy
已浏览 105.6万 次2022年9月7日
短视频
Let's build the GPT Tokenizer
2:13:35
已浏览 97.5万 次
Let's build the GPT Tokenizer
Andrej Karpathy
Andrej Karpathy: Software Is Changing (Again)
39:32
已浏览 224.7万 次
Andrej Karpathy: Software Is Changing (Again)
Y Combinator
热门视频
Let's build GPT: from scratch, in code, spelled out.
1:56:20
Let's build GPT: from scratch, in code, spelled out.
YouTubeAndrej Karpathy
已浏览 668.3万 次2023年1月17日
[1hr Talk] Intro to Large Language Models
59:48
[1hr Talk] Intro to Large Language Models
YouTubeAndrej Karpathy
已浏览 326.2万 次2023年11月23日
Andrej Karpathy — “We’re summoning ghosts, not building animals”
2:26:08
Andrej Karpathy — “We’re summoning ghosts, not building animals”
YouTubeDwarkesh Patel
已浏览 104.3万 次2 个月之前
Latest From Andrej Karpathy
Let's reproduce GPT-2 (124M)
4:01:26
Let's reproduce GPT-2 (124M)
YouTubeAndrej Karpathy
已浏览 96.6万 次2024年6月9日
Building makemore Part 5: Building a WaveNet
Building makemore Part 5: Building a WaveNet
YouTubeAndrej Karpathy
已浏览 24.3万 次2022年11月21日
Building makemore Part 4: Becoming a Backprop Ninja
1:55:24
Building makemore Part 4: Becoming a Backprop Ninja
YouTubeAndrej Karpathy
已浏览 31.4万 次2022年10月11日