HeyJaredRobert Miles AI Safety
Videos about Artificial Intelligence Safety Research, for everyone. AI is leaping forward right now, it's only a matter of time before we develop true Artificial General Intelligence, and there are a lot of different ways that this could go badly wrong for us.
- Indexed videos, last 90 days
- 18
- Latest publication
- Sep 29, 2026
- Audience
- ~172K subscribers
- Earliest in this view
- Jul 4, 2026
Latest videos
Bio Risk is Not Like Cyber Risk (opens the original)
Read excerpt
What happens when AI makes it easy for lots of people to do bioengineering? We're going to need much better broad spectrum pandemic preparedness. Or a way to restrict AI development/deployment.
Yyup... (opens the original)
Read excerpt
Accidentally impossible tasks is maybe the least absurd thing about this story, it's insane: https://www.youtube.com/watch?v=87DyyMV0kCY More to come on this obviously
Full AI Escape Seems Possible (opens the original)
Read excerpt
https://palisaderesearch.org/blog/self-replication
"Just Predicting Tokens" (opens the original)
Read excerpt
A sufficiently good next token predictor is a superintelligence
People are Catching On (opens the original)
Read excerpt
Read the open letter: https://www.pacingthefrontier.com/ Thanks to NewsNation for being the first news org to upload a video, and thus the only one I could find when making this video: https://youtu.be/K0jrkQalga0
Publishing over time
Last 90 days. Choose a month to open its work.
Recurring subjects
Named in the text we hold. One piece can cover several.
Audience
~172K subscribers
Measured Sep 19, 2026
Source's subscribers, not the number who saw an individual piece.
About this data
Counts cover the work we have indexed. Tone needs enough text and a confident classification. Excerpts and episode notes are not full articles or transcripts.
Identity or attribution wrong? Suggest a correction.