
State of GPT | BRK216HFS
Microsoft Developer786K views
Andrej Karpathy explains how GPT assistants are trained (pretraining, fine-tuning, RLHF) and how to use them well.
267,244 videos · Algorithms, systems, security, machine learning and building software.

786K views
Andrej Karpathy explains how GPT assistants are trained (pretraining, fine-tuning, RLHF) and how to use them well.
1:31:13580K views
A code-first hacker's guide to language models: what they are, how to use them well, fine-tuning and running them locally.

88.4K views
John Schulman explains RLHF: why reinforcement learning helps with truthfulness and hallucination, and the open problems.
47:37
47:02
59:24
1:02:06
12:49
32:07
40:24
36:05
39:35
47:17
1:15:16
55:52
6:23
48:03
45:26
46:52
54:44
1:01:39
1:08:42
56:39
47:26
51:45
1:01:55
27:45
27:56
1:08:26
22:00
50:39
5:26
1:00:09
14:52
57:12
44:36