explainer · HACKER NEWS RECOMMENDATION
Transformers, the tech behind LLMs | Deep Learning Chapter 5
3Blue1Brown · 13 HN recommenders · 10 recommendation months
Recommended by 13 Hacker News commenters across 10 months (2024–2026).
SignalTube analysis
Among 14 other explainer videos tagged LLMs & generative AI, the mean is 2.2 distinct HN recommenders. This video has 13 distinct HN recommenders, about 5.9× that mean. Recommendations span 10 distinct months, longer than the peer average of 1.9 months. This is a data-derived comparison, not a human review or quality rating.
81% of its 16 labeled comments are marked as recommendations or strong recommendations. HN mention years are 2024–2026; those years describe discussion history, not upload date. Its verified runtime is 27 minutes 14 seconds. YouTube lists its publication date as 2024-04-01.
- Channel / speaker
- 3Blue1Brown
- Verified runtime
- 27m 14s
- YouTube upload date
- 2024-04-01
- 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 |
|---|---|---|---|---|---|---|
| Transformers, the tech behind LLMs | Deep Learning Chapter 5Current video | 13 | 10 | 81% | — | 27m 14s | 2024-04-01 |
| Attention in transformers, step-by-step | Deep Learning Chapter 6explainer · 3Blue1Brown | 5 | 4 | 63% | 2 (15%) | 26m 10s | 2024-04-07 |
| Attention Is All You Needexplainer · Yannic Kilcher | 4 | 4 | 80% | No recorded overlap | 27m 7s | 2017-11-28 |
| Large Language Models from scratchexplainer · Graphics in 5 Minutes | 3 | 2 | 60% | No recorded overlap | 8m 25s | 2022-07-17 |
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 strong recommendation in “"They're made out of weights"”. Its short rationale: Great visual introduction to transformers; start from chapter 1 for background.
The archive classifies this as a recommendation in “Claude Token Counter, now with model comparisons”. Its short rationale: Informative on how LLMs handle tokens.
The archive classifies this as a recommendation in “Understanding Neural Network, Visually”. Its short rationale: Helpful for visualizing transformers.