explainer · HACKER NEWS RECOMMENDATION
Training AI Without Writing A Reward Function, with Reward Modelling
Robert Miles AI Safety · 3 HN recommenders · 3 recommendation months
Recommended by 3 Hacker News commenters across 3 months (2019–2023).
SignalTube analysis
Among 13 other explainer videos tagged AI safety, AGI & impact, the mean is 3.5 distinct HN recommenders. This video has 3 distinct HN recommenders, close to that mean. Recommendations span 3 distinct months; the peer average is 3.5 months. This is a data-derived comparison, not a human review or quality rating.
50% of its 6 labeled comments are marked as recommendations or strong recommendations. HN mention years are 2019–2023; 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
- Robert Miles AI Safety
- Verified runtime
- Not verified in the current YouTube metadata
- YouTube upload date
- Not verified
- Hacker News mention years
- 2019–2023
SAME TOPIC AND FORMAT
Compare with related videos
The comparison cohort uses other explainer videos in AI safety, AGI & impact. “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 |
|---|---|---|---|---|---|---|
| Training AI Without Writing A Reward Function, with Reward ModellingCurrent video | 3 | 3 | 50% | — | Not verified in the current YouTube metadata | Not verified |
| What Happened to Horses Is Happening to Usexplainer · CGP Grey | 11 | 11 | 55% | No recorded overlap | Not verified | Not verified |
| Why Would AI Want to do Bad Things? Instrumental Convergenceexplainer · Robert Miles AI Safety | 6 | 6 | 75% | No recorded overlap | Not verified | Not verified |
| Intelligence and Stupidity: The Orthogonality Thesisexplainer · Robert Miles AI Safety | 6 | 6 | 83% | 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 strong recommendation in “What We Know About LLMs (A Primer)”. Its short rationale: Best presentation of the original 2017 RLHF paper.
The archive classifies this as a contextual reference in “Ask HN: How To Overcome Information Addiction?”. Its short rationale: the source snapshot has no short rationale for this mention.
The archive classifies this as a contextual reference in “Setting goals for 2021 – A brief guide about personal goal setting”. Its short rationale: the source snapshot has no short rationale for this mention.