talk · HACKER NEWS RECOMMENDATION
John Schulman - Reinforcement Learning from Human Feedback: Progress and Challenges
UC Berkeley EECS · 2 HN recommenders · 2 recommendation months
Recommended by 2 Hacker News commenters across 2 months (2023–2023).
SignalTube analysis
Among 37 other talk videos tagged Machine learning & deep learning, the mean is 2.8 distinct HN recommenders. This video has 2 distinct HN recommenders, below that mean. Recommendations span 2 distinct months; the peer average is 2.5 months. This is a data-derived comparison, not a human review or quality rating.
40% of its 5 labeled comments are marked as recommendations or strong recommendations. HN mention years are 2023–2023; 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
- UC Berkeley EECS
- Verified runtime
- Not verified in the current YouTube metadata
- YouTube upload date
- Not verified
- Hacker News mention years
- 2023–2023
SAME TOPIC AND FORMAT
Compare with related videos
The comparison cohort uses other talk 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 |
|---|---|---|---|---|---|---|
| John Schulman - Reinforcement Learning from Human Feedback: Progress and ChallengesCurrent video | 2 | 2 | 40% | — | Not verified in the current YouTube metadata | Not verified |
| USENIX Security '18-Q: Why Do Keynote Speakers Keep Suggesting That Improving Security Is Possible?talk · USENIX | 10 | 10 | 50% | No recorded overlap | Not verified | Not verified |
| Bay Area Vision Meeting: Unsupervised Feature Learning and Deep Learningtalk · Google TechTalks | 9 | 7 | 82% | No recorded overlap | Not verified | Not verified |
| [1hr Talk] Intro to Large Language Modelstalk · Andrej Karpathy | 9 | 6 | 45% | 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 “AI Safety and the Age of Dislightenment”. Its short rationale: Schulman on hallucination and models' knowledge of uncertainty.
The archive classifies this as a contextual reference in “The False Promise of Imitating Proprietary LLMs”. Its short rationale: Schulman on the problem with behavior cloning.
The archive classifies this as a recommendation in “Don Knuth Plays with ChatGPT”. Its short rationale: Schulman explains RL's role in reducing hallucination.