Safe Transition Talks
Safe Transition Talks
Alex van der Meer
#1 - Thomas Hickey: AGI Takeoff, Existential Risk, Regulation Ideas
1 hour 25 minutes Posted Jan 17, 2023 at 9:11 pm.
) Introduction
) Recursive self-improvement, how long until superintelligence
) What can be learned in the digital realm
) How fast can it learn in the real world
) Can AGI become better than us?
) Complex enough environment to create superintelligence?
) Can AGI Thomas take over the world?
) Is superintelligence irrelevant for safety?
) Existential risk from AI?
) How to decrease the chance of a bad outcome?
) Regulations
) ChatGPT and the best current models
) Solution to the treacherous turn?  
) AGI becomes religious?
) Starting point of the intelligence explosion?
) OpenAI Alignment approach blog post
) Is Open source bad for safety?
) How to contact me
0:00
1:25:45
Download MP3
Show notes
(See timestamps below)
Thomas Hickey is a Dutch student in both philosophy and artificial intelligence at Utrecht University. We talk about his bachelor thesis on A.G.I. or Artificial General Intelligence, on bottlenecks for recursive self-improvement. But also go into existential risk and what we can do about it.
CONTACT INFO:
Alex van der Meer
email: [email protected] but remove capital letters, (for spam)
SEE MORE OF ME:
- Twitter:
https://twitter.com/AlexvanderMeer5
- YouTube:
https://www.youtube.com/@safetransition9743
EPISODE LINKS:
Eliezer Yudkowsky, on why it is lethal not to have retries
https://intelligence.org/2022/06/10/agi-ruin/
OpenAI on their approach to alignment blog post
https://openai.com/blog/our-approach-to-alignment-research/
TIMESTAMPS:
On some podcast players you should be able to click the timestamp to jump to that time.
(
(
(
(
(
(
(
(
(
(
(
(
(
(
(
(
(
(