Neural Networks: Zero to Hero by Andrej Karpathy
Hacker ApprovedRanked 3 of 17 online courses by recommenders
Free video lecture series that builds neural networks from backpropagation up to a GPT-2 clone, praised for intuition. Caveat: some find it oversimplified.
Free video lecture series that builds neural networks from backpropagation up to a GPT-2 clone, praised for intuition. Caveat: some find it oversimplified.
31 people gave an opinion
- recommend it
- 29
- criticize it
- 2
- approval share
- 94%
Recommended in 9 of 13 months
- November 2025: not recommended
- December 2025: recommended
- January 2026: recommended
- February 2026: recommended
- March 2026: recommended
- April 2026: not recommended
- May 2026: recommended
- June 2026: recommended
- July 2026: recommended
- August 2026: recommended
- September 2026: not recommended
- October 2026: recommended
- November 2026: not recommended (month in progress)
Why it carries the badge
- 29 people recommend itNeeds 10 or more, met.
- 15 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 9 of 13 monthsNeeds 4 or more, met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Strong starting point for learners
“all the skills you need to learn how to do this can be learned watching Andrej Karpathy’s zero to hero series”
Comment from 24 Aug 2026 in “I were 17, I'd learn how to build LLMs from scratch” “Supplement with the Karpathy 'Zero to Hero' video series if it suits your preferred learning style.”
Comment from 8 Jul 2026 in “IEEE Rolls Out Large Language Models Training Course” “I think Karpathys nn zero to hero is a good starting point.”
Comment from 28 Jul 2026 in “You Could Have Come Up with Kimi Delta Attention” - Comment from 1 Oct 2026 in “The last time my family was replaced by technology”
- Comment from 6 Jan 2026 in “MyTorch – Minimalist autograd in 450 lines of Python”
- Comment from 24 Aug 2026 in “I were 17, I'd learn how to build LLMs from scratch”
Builds intuition for core concepts
“Does a great job of helping you build intuition for why things like gradient descent and normalization work”
Comment from 4 Jan 2026 in “Neural Networks: Zero to Hero” “This series of videos was by far the best, most “intuition building”, highest signal-to-noise ratio”
Comment from 4 Jan 2026 in “Neural Networks: Zero to Hero” “Karpathy has a unique talent for making complex topics feel approachable without dumbing them down.”
Comment from 1 Mar 2026 in “Microgpt” - Comment from 25 Aug 2026 in “I were 17, I'd learn how to build LLMs from scratch”
Approachable with little math
“Anyone who watches the videos and follows along will indeed come up to speed on the basics of neural nets”
Comment from 5 Jan 2026 in “Neural Networks: Zero to Hero” “lectures are as approachable as one could possible make them, no fancy math”
Comment from 4 Jan 2026 in “Neural Networks: Zero to Hero” “I found the Karpathy videos very approachable.”
Comment from 4 Jan 2026 in “Neural Networks: Zero to Hero” Covers backprop through GPT-2 clone
“It starts with the fundamentals of how backpropagation works then advances to building a few simple models and ends with building a GPT-2 clone.”
Comment from 22 Dec 2025 in “The Illustrated Transformer” “You end up with a GPT-2.0 equivalent if you follow them to the end.”
Comment from 26 Oct 2026 in “Sebastian Raschka's from-scratch video course on building reasoning models” “found it very useful. Especially the back-propagation lectures.”
Comment from 4 Jan 2026 in “Neural Networks: Zero to Hero”
What people warn about
Each mark is one comment
Oversimplified, strips away depth
“It's a useful series of videos no doubt, but his goal is to strip things down to basics”
Comment from 5 Jan 2026 in “Neural Networks: Zero to Hero” “Karpathy has a great intuitive style, but sometimes it's too dumbed down”
Comment from 4 Jan 2026 in “Neural Networks: Zero to Hero”
Other online courses people recommend
The four most recommended other online courses, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| Math Academy | 35 | 1 | 97% | 12 | 9 mo6 owners | Approved |
| Nand2Tetris | 31 | 3 | 91% | 10 | — | Approved |
| Neural Networks: Zero to Hero by Andrej KarpathyThis page | 29 | 2 | 94% | 9 | — | Approved |
| CS193p SwiftUI course by Paul Hegarty | 13 | 1 | 93% | 2 | 11.9 yrs5 owners | — |
| CS336: Language Modeling from Scratch | 12 | 1 | 92% | 5 | — | Approved |
What people said
34 of the 38 comments that mention it, newest first. Each links to the original comment.
“You end up with a GPT-2.0 equivalent if you follow them to the end.”
“Karpathy has a good set of tutorials on this.”
“It will improve your understanding of the basics.”
“all the skills you need to learn how to do this can be learned watching Andrej Karpathy’s zero to hero series”
“Start with Karpathy and then go to CS 336”
“I think Karpathys nn zero to hero is a good starting point.”
“Supplement with the Karpathy 'Zero to Hero' video series if it suits your preferred learning style.”
“you can build your own (inefficient) tensor library without too much effort as e.g. Andrej Karpathy has shown”
“No resource for this is better than Karpathy's "Zero to Hero" series on YouTube.”
“his "zero to hero" videos, nanoGPT, etc, are all great”
“Karpathy has a unique talent for making complex topics feel approachable without dumbing them down.”
“Those little black boxes of AI can be significantly demystified by, for example, watching a bunch of videos”
“The first one or two episodes will get you rolling..”
“I don't find that it helps with large scale development.”
“That give a useful background into understanding what the tool can do”
“yes Karpathy is for sure the better route”
“It's a useful series of videos no doubt, but his goal is to strip things down to basics”
“Anyone who watches the videos and follows along will indeed come up to speed on the basics of neural nets”
“it's really just "From Zero to LLMs"”
“Does a great job of helping you build intuition for why things like gradient descent and normalization work”
“IMO that's a bit of a strange video for Karpathy to start with, perhaps even to include at all.”
“Karpathy videos posted here are GOLD.”
“found it very useful. Especially the back-propagation lectures.”
“Karpathy has a great intuitive style, but sometimes it's too dumbed down”
“lectures are as approachable as one could possible make them, no fancy math”
“I found the Karpathy videos very approachable.”
“This series of videos was by far the best, most “intuition building”, highest signal-to-noise ratio”
“Karpathy's material is excellent!”
“the karpathy vids are very cool but having watched it”
“acclaimed, often cited course by a preeminent AI Researcher”
“I would recommend to first complete the series or atleast the "micrograd" video.”
“I am sure this is great as well”
“some of the most effective CS pedagogy I've ever encountered”
“It starts with the fundamentals of how backpropagation works then advances to building a few simple models and ends with building a GPT-2 clone.”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.