explainer · HACKER NEWS RECOMMENDATION
Attention in transformers, step-by-step | Deep Learning Chapter 6
3Blue1Brown · 5 HN recommenders · 4 recommendation months
Recommended by 5 Hacker News commenters across 4 months (2024–2026).
SignalTube analysis
Among 14 other explainer videos tagged LLMs & generative AI, the mean is 2.8 distinct HN recommenders. This video has 5 distinct HN recommenders, about 1.8× that mean. Recommendations span 4 distinct months; the peer average is 2.4 months. This is a data-derived comparison, not a human review or quality rating.
63% of its 8 labeled comments are marked as recommendations or strong recommendations. HN mention years are 2024–2026; 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
- 3Blue1Brown
- Verified runtime
- Not verified in the current YouTube metadata
- YouTube upload date
- Not verified
- Hacker News mention years
- 2024–2026
SAME TOPIC AND FORMAT
Compare with related videos
The comparison cohort uses other explainer videos in LLMs & generative AI. “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 |
|---|---|---|---|---|---|---|
| Attention in transformers, step-by-step | Deep Learning Chapter 6Current video | 5 | 4 | 63% | — | Not verified in the current YouTube metadata | Not verified |
| Transformers, the tech behind LLMs | Deep Learning Chapter 5explainer · 3Blue1Brown | 13 | 10 | 81% | 2 (40%) | Not verified | Not verified |
| Attention Is All You Needexplainer · Yannic Kilcher | 4 | 4 | 80% | No recorded overlap | Not verified | Not verified |
| Large Language Models from scratchexplainer · Graphics in 5 Minutes | 3 | 2 | 60% | 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 recommendation in “Can I Buy Your KV Cache?”. Its short rationale: Gentler introduction to attention, part of a series.
The archive classifies this as a strong recommendation in “Claude Opus 4.8”. Its short rationale: Amazing series on how tokens become vectors and mutate through attention.
The archive classifies this as a contextual reference in “3Blue1Brown Follow-Up: From Hypothetical Examples to LLM Circuit Visualization”. Its short rationale: Tutorial on self-attention for next token prediction, used as comparison baseline.