Info
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. Putting aside the science fiction, this channel is about AI Safety research - humanity's best attempt to foresee the problems AI might pose and work out ways to ensure that our AI developments are safe and beneficial.
Links
Stats
Joined January 30, 2012
8,924,133 total views
Featured video
Videos
Tech is Good, AI Will Be Different
76,000 views
AI Safety Career Advice! (And So Can You!)
80,000 views
Using Dangerous AI, But Safely?
156,000 views
AI Ruined My Year
273,000 views
Why Does AI Lie, and What Can We Do About It?
282,000 views
We Were Right! Real Inner Misalignment
269,000 views
Intro to AI Safety, Remastered
205,000 views
Quantilizers: AI That Doesn't Try Too Hard
90,000 views
Shorts
Yyup...
71,000 views
Full AI Escape Seems Possible
52,000 views
"Just Predicting Tokens"
76,000 views
People are Catching On
57,000 views
Why Smart AIs Cheat
71,000 views
Did ChatGPT Just Commit a Felony?
176,000 views
Is China Open to Making a Deal on AI?
37,000 views
Useful Websites: AISafety.com
15,000 views
AI can't DO my JOB quite yet
63,000 views
Keeping AI in a Box
103,000 views
AI Lie Detectors?
34,000 views
"Stop the AI Race" March in SF #ai #sanfrancisco
13,000 views
Why I Avoid Sci-Fi Specifics
62,000 views
Update: AI Billionaire Attacks Backfire
51,000 views
Robot Dog! Unitree Go2 review #shorts #robot #dog
134,000 views
Collaborations
Did ChatGPT Just Commit a Felony?
176,000 views