Avoiding Negative Side Effects: Concrete Problems in AI Safety part 1
What it is
Robert Miles introduces the first of several videos on the paper 'Concrete Problems in AI Safety', focusing on how AI systems can cause accidental negative side effects. It explains the problem in accessible terms.
Why Hacker News recommends it
HN recommends Robert Miles' channel as a clear starting point for people curious about AI safety.
- 2 people recommended it
- 2 different months
- 1 strong recommendations
- first 2018, last 2023
What HN commenters said
“For those curious about AI safety I heavily recommend Robert Miles channel on YouTube.”
Starting point on Robert Miles' AI safety content.
jononor, 2023-01 · Strong recommendation · in “Not worried about AI that passes Turing test, but AI that fails it on purpose”
“is covered nicely in this youtube video, as well as the paper referenced there”
Covers lack of safe fallback policies in AI safety.
nmca, 2018-05 · Recommendation · in “Uber Self-Driving Car That Struck Pedestrian Wasn’t Set to Stop in an Emergency”
Excerpts from Hacker News comments, linked to the originals. Summaries and labels were written by a language model from those comments.
Topics: negative side effects, concrete problems in ai safety, ai risk, robert miles, alignment
Also recommended by the same people
talkHillel Wayne - Beyond Unit Tests: Taking Your Testing to the Next Level - PyCon 2018PyCon 2018 · 3 HN recommenders · 2018–2023
commentaryNaive empiricism, terrorism & Ebola.N N Taleb's Probability Questions · 2 HN recommenders · 2017–2021
explainerDo we have to accept Quantum weirdness? De Broglie Bohm Pilot Wave Theory explainedLooking Glass Universe · 3 HN recommenders · 2017–2020
explainerWhat Happened to Horses Is Happening to UsCGP Grey · 11 HN recommenders · 2014–2026
explainerWhy Would AI Want to do Bad Things? Instrumental ConvergenceRobert Miles AI Safety · 6 HN recommenders · 2019–2023
talkVeritasium: What Everyone Gets Wrong About AI and Learning – Derek Muller ExplainsPerimeter Institute for Theoretical Physics · 6 HN recommenders · 2025–2026
explainerIntelligence and Stupidity: The Orthogonality ThesisRobert Miles AI Safety · 6 HN recommenders · 2022–2026
talkWe're building a dystopia just to make people click on ads | Zeynep TufekciTED · 6 HN recommenders · 2017–2026