HackerTubewatch
Surprise me

Home › Channels

Robert Miles AI Safety : the videos Hacker News recommends

Not the channel's most viewed videos: the ones HN commenters kept linking with real commentary. The top pick, "Why Would AI Want to do Bad Things? Instrumental Convergence", hN commenters repeatedly recommend it as the clearest introduction to why smart AI might behave badly by default.

9 videos on HackerTube.

  1. 6 HN recommenders 6 months 2019–2023
    explainer
    HN commenters repeatedly recommend it as the clearest introduction to why smart AI might behave badly by default.
  2. 6 HN recommenders 6 months 2022–2026
    explainer
    HN people use it as the standard short explanation for why AI can understand human ethics without sharing them, and often recommend the whole channel.
  3. 6 HN recommenders 5 months 2022–2023
    talk
    The default link for newcomers wanting an approachable, entertaining introduction to AI risk and alignment.
  4. 5 HN recommenders 5 months 2020–2023
    explainer
    HN points to it as an accessible rebuttal to the claim that AI risk is just corporate risk.
  5. 3 HN recommenders 4 months 2019–2026
    explainer
    HN points to it as a reasoned rebuttal to the claim that AI risk is just Pascal's wager.
  6. 3 HN recommenders 3 months 2019–2023
    explainer
    Seen as the clearest introduction to the idea behind RLHF, and also borrowed by commenters as a metaphor for human motivation.
  7. 2 HN recommenders 2 months 2018–2023
    explainer
    HN recommends Robert Miles' channel as a clear starting point for people curious about AI safety.
  8. 2 HN recommenders 2 months 2022–2024
    explainer
    HN commenters link it as a compact rebuttal to dismissive arguments and as a way to see why people consider AI safety important.
  9. 1 HN recommenders 1 months 2023
    explainer
    Pointed to as evidence that AI misalignment is an empirically demonstrated problem, for people who dismiss it.

Questions

Which Robert Miles AI Safety video does Hacker News recommend most?

Why Would AI Want to do Bad Things? Instrumental Convergence: recommended in 6 different months by 6 HN users between 2019 and 2023.

Is this every Robert Miles AI Safety video?

No. Only videos that at least three different HN users linked, in at least three different months, with at least a sentence of their own commentary. That filter is what makes the list useful.

Video list and Hacker News comment labels from HackerTube (prompted by @karpathy), released under ODC-By 1.0, built on the open-index/hacker-news archive. Hacker News data is provided by Y Combinator; comments remain the work of their authors. Video titles, channel names and thumbnails belong to their creators and are shown via YouTube. HackerTube Watch is an unofficial edition. Data export of 2026-10-31.

Keyboard shortcuts

/
Search
j k
Next / previous video
r
Surprise me
l
Like (video page)
w
Watch later (video page)
?
This help
Esc
Close