tutorial · HACKER NEWS RECOMMENDATION
The spelled-out intro to language modeling: building makemore
Andrej Karpathy · 2 HN recommenders · 2 recommendation months
Recommended by 2 Hacker News commenters across 2 months (2024–2024).
SignalTube analysis
Among 5 other tutorial videos tagged Machine learning & deep learning, the mean is 7.4 distinct HN recommenders. This video has 2 distinct HN recommenders, below that mean. Recommendations span 2 distinct months; the peer average is 5.8 months. This is a data-derived comparison, not a human review or quality rating.
50% of its 4 labeled comments are marked as recommendations or strong recommendations. HN mention years are 2024–2024; those years describe discussion history, not upload date. A verified runtime is not present in the current metadata snapshot. A verified YouTube publication date is not present in the current metadata snapshot.
- Channel / speaker
- Andrej Karpathy
- Verified runtime
- Not verified in the current YouTube metadata
- YouTube upload date
- Not verified
- Hacker News mention years
- 2024–2024
SAME TOPIC AND FORMAT
Compare with related videos
The comparison cohort uses other tutorial videos in Machine learning & deep learning. “Shared recommenders” counts HN users who recommended both videos in the source graph.
| Video | HN recommenders | Recommendation months | Positive label share | Shared recommenders | Runtime | Upload date |
|---|---|---|---|---|---|---|
| The spelled-out intro to language modeling: building makemoreCurrent video | 2 | 2 | 50% | — | Not verified in the current YouTube metadata | Not verified |
| Let's build GPT: from scratch, in code, spelled out.tutorial · Andrej Karpathy | 14 | 8 | 70% | No recorded overlap | Not verified | Not verified |
| A Hackers' Guide to Language Modelstutorial · Jeremy Howard | 8 | 8 | 77% | No recorded overlap | Not verified | Not verified |
| Tensorflow and deep learning - without a PhD by Martin Görnertutorial · Devoxx | 6 | 5 | 100% | No recorded overlap | Not verified | Not verified |
THREE SOURCE-BASED CONTEXT POINTS
Why Hacker News recommends it
Each note combines the dataset’s stance label and short rationale; comment bodies are not reproduced. Open the HN source for the original discussion.
The archive classifies this as a contextual reference in “The n-gram Language Model”. Its short rationale: Karpathy's bigram project that the new course generalizes.
The archive classifies this as a strong recommendation in “Show HN: Next-token prediction in JavaScript”. Its short rationale: Highly recommended pointer for next-token prediction.
The archive classifies this as a contextual reference in “GPT in 500 Lines of SQL”. Its short rationale: Moves from counting bigrams to a neural net at the one hour mark.