lecture · HACKER NEWS RECOMMENDATION
LSTM is dead. Long Live Transformers!
Seattle Applied Deep Learning · 4 HN recommenders · 4 recommendation months
Recommended by 4 Hacker News commenters across 4 months (2020–2023).
SignalTube analysis
Among 6 other lecture videos tagged LLMs & generative AI, the mean is 5.2 distinct HN recommenders. This video has 4 distinct HN recommenders, below that mean. Recommendations span 4 distinct months; the peer average is 4.3 months. This is a data-derived comparison, not a human review or quality rating.
80% of its 5 labeled comments are marked as recommendations or strong recommendations. HN mention years are 2020–2023; those years describe discussion history, not upload date. Its verified runtime is 28 minutes 48 seconds. YouTube lists its publication date as 2019-12-03.
- Channel / speaker
- Seattle Applied Deep Learning
- Verified runtime
- 28m 48s
- YouTube upload date
- 2019-12-03
- Hacker News mention years
- 2020–2023
SAME TOPIC AND FORMAT
Compare with related videos
The comparison cohort uses other lecture 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 |
|---|---|---|---|---|---|---|
| LSTM is dead. Long Live Transformers!Current video | 4 | 4 | 80% | — | 28m 48s | 2019-12-03 |
| Deep Dive into LLMs like ChatGPTlecture · Andrej Karpathy | 10 | 8 | 56% | No recorded overlap | 211m 24s | 2025-02-05 |
| Sparks of AGI: early experiments with GPT-4lecture · Sebastien Bubeck | 7 | 4 | 35% | No recorded overlap | 48m 32s | 2023-04-06 |
| Let's build the GPT Tokenizerlecture · Andrej Karpathy | 5 | 5 | 63% | No recorded overlap | 133m 35s | 2024-02-20 |
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 “Ask HN: Can someone ELI5 Transformers and the “Attention is all we need” paper”. Its short rationale: SDE-level explanation of transformers in NLP context, well complimented.
The archive classifies this as a contextual reference in “We aren't close to creating a rapidly self-improving AI”. Its short rationale: Source for commenter's understanding of attention and parallelism.
The archive classifies this as a recommendation in “Understanding and Coding the Self-Attention Mechanism of Large Language Models”. Its short rationale: Explains RNN drawbacks and how transformers solve them.