168 - How to Solve AI Alignment with Paul Christiano

Paul previously ran the language model alignment team at OpenAI, the creators of ChatGPT.

Today, we’re hoping to explore the solution-landscape to the AI Alignment problem, and hoping Paul can guide us on that journey.

In today’s episode, Paul answers many questions, but the overarching ones are:

1) How BIG is the AI Alignment problem?

2) How HARD is the AI Alighment problem?

3) How SOLVABLE is the AI Alignment problem?

Does humanity have a chance? Tune in to hear Paul’s thoughts.

TIMESTAMPS

0:00 Intro

9:20 Percentage Likelihood of Death by AI

11:24 Timing

19:15 Chimps to Human Jump

21:55 Thoughts on ChatGPT

27:51 LLMs & AGI

32:49 Time to React?

38:29 AI Takeover

41:51 AI Agency

49:35 Loopholes

51:14 Training AIs to Be Honest

58:00 Psychology

59:36 How Solvable Is the AI Alignment Problem?

1:03:48 The Technical Solutions (Scalable Oversight)

1:16:14 Training AIs to be Bad?!

1:18:22 More Solutions

1:21:36 Stabby AIs

1:26:03 Public vs. Private (Lab) AIs

1:28:31 Inside Neural Nets

1:32:11 4th Solution

1:35:00 Manpower & Funding

1:38:15 Pause AI?

1:43:29 Resources & Education on AI Safety

1:46:13 Talent  

1:49:00 Paul’s Day Job

1:50:15 Nobel Prize

1:52:35 Treating AIs with Respect

1:53:41 Uptopia Scenario

1:55:50 Closing & Disclaimers

RESOURCES

Alignment Research Center

https://www.alignment.org/

Paul Christiano’s Website

https://paulfchristiano.com/ai/