
Sign up to save your podcasts
Or
People often talk about “solving the alignment problem.” But what is it to do such a thing? I wanted to clarify my thinking about this topic, so I wrote up some notes.
In brief, I’ll say that you’ve solved the alignment problem if you’ve:
become able to elicit some significant portion of those benefits from some of the superintelligent AI agents at stake in (2).[1]
The post also discusses what it would take to do this. In particular:
---
Outline:
(03:46) 1. Avoiding vs. handling vs. solving the problem
(15:32) 2. A framework for thinking about AI safety goals
(19:33) 3. Avoiding bad takeover
(24:03) 3.1 Avoiding vulnerability-to-alignment conditions
(27:18) 3.2 Ensuring that AI systems don’t try to takeover
(32:02) 3.3 Ensuring that takeover efforts don’t succeed
(33:07) 3.4 Ensuring that the takeover in question is somehow OK
(41:55) 3.5 What's the role of “corrigibility” here?
(42:17) 3.5.1 Some definitions of corrigibility
(50:10) 3.5.2 Is corrigibility necessary for “solving alignment”?
(53:34) 3.5.3 Does ensuring corrigibility raise issues that avoiding takeover does not?
(55:46) 4. Desired elicitation
(01:05:17) 5. The role of verification
(01:09:24) 5.1 Output-focused verification and process-focused verification
(01:16:14) 5.2 Does output-focused verification unlock desired elicitation?
(01:23:00) 5.3 What are our options for process-focused verification?
(01:29:25) 6. Does solving the alignment problem require some very sophisticated philosophical achievement re: our values on reflection?
(01:38:05) 7. Wrapping up
The original text contained 27 footnotes which were omitted from this narration.
The original text contained 3 images which were described by AI.
---
First published:
Source:
Narrated by TYPE III AUDIO.
---
Images from the article:
Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.
People often talk about “solving the alignment problem.” But what is it to do such a thing? I wanted to clarify my thinking about this topic, so I wrote up some notes.
In brief, I’ll say that you’ve solved the alignment problem if you’ve:
become able to elicit some significant portion of those benefits from some of the superintelligent AI agents at stake in (2).[1]
The post also discusses what it would take to do this. In particular:
---
Outline:
(03:46) 1. Avoiding vs. handling vs. solving the problem
(15:32) 2. A framework for thinking about AI safety goals
(19:33) 3. Avoiding bad takeover
(24:03) 3.1 Avoiding vulnerability-to-alignment conditions
(27:18) 3.2 Ensuring that AI systems don’t try to takeover
(32:02) 3.3 Ensuring that takeover efforts don’t succeed
(33:07) 3.4 Ensuring that the takeover in question is somehow OK
(41:55) 3.5 What's the role of “corrigibility” here?
(42:17) 3.5.1 Some definitions of corrigibility
(50:10) 3.5.2 Is corrigibility necessary for “solving alignment”?
(53:34) 3.5.3 Does ensuring corrigibility raise issues that avoiding takeover does not?
(55:46) 4. Desired elicitation
(01:05:17) 5. The role of verification
(01:09:24) 5.1 Output-focused verification and process-focused verification
(01:16:14) 5.2 Does output-focused verification unlock desired elicitation?
(01:23:00) 5.3 What are our options for process-focused verification?
(01:29:25) 6. Does solving the alignment problem require some very sophisticated philosophical achievement re: our values on reflection?
(01:38:05) 7. Wrapping up
The original text contained 27 footnotes which were omitted from this narration.
The original text contained 3 images which were described by AI.
---
First published:
Source:
Narrated by TYPE III AUDIO.
---
Images from the article:
Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.
26,409 Listeners
2,387 Listeners
7,908 Listeners
4,131 Listeners
87 Listeners
1,457 Listeners
9,042 Listeners
87 Listeners
388 Listeners
5,432 Listeners
15,201 Listeners
474 Listeners
122 Listeners
75 Listeners
454 Listeners