This shows you the differences between two versions of the page.
Both sides previous revision Previous revision Next revision | Previous revision | ||
responses_to_ai:affordances:lab_affordances [2023/02/16 08:41] zachsteinperlman ↷ Page moved from uncategorized:lab_affordances to responses_to_ai:affordances:lab_affordances |
responses_to_ai:affordances:lab_affordances [2023/07/23 20:54] (current) katjagrace [List] |
||
---|---|---|---|
Line 5: | Line 5: | ||
This is a list of actions AI labs could take that may be strategically relevant (or consequences or characteristics of possible actions). | This is a list of actions AI labs could take that may be strategically relevant (or consequences or characteristics of possible actions). | ||
- | ===== Details | + | ===== List ===== |
* Deploy an AI system | * Deploy an AI system | ||
- | * Pursue capabilities | + | * Pursue |
* Pursue risky (and more or less alignable systems) systems | * Pursue risky (and more or less alignable systems) systems | ||
* Pursue systems that enable risky (and more or less alignable) systems | * Pursue systems that enable risky (and more or less alignable) systems | ||
* Pursue weak AI that's mostly orthogonal to progress in risky stuff for a specific (strategically significant) task or goal | * Pursue weak AI that's mostly orthogonal to progress in risky stuff for a specific (strategically significant) task or goal | ||
* This could enable or abate catastrophic risks besides unaligned AI | * This could enable or abate catastrophic risks besides unaligned AI | ||
- | * Do alignment (and related) research (or: decrease the [[|alignment tax]] by doing technical research) | + | * Do alignment (and related) research (or: decrease the [[https:// |
* Including interpretability and work on solving or avoiding alignment-adjacent problems like [[https:// | * Including interpretability and work on solving or avoiding alignment-adjacent problems like [[https:// | ||
* Advance global capabilities | * Advance global capabilities | ||
Line 36: | Line 36: | ||
* Make demos or public statements | * Make demos or public statements | ||
* Release or deploy AI systems | * Release or deploy AI systems | ||
- | * Improve their culture or [[https:// | + | * Improve their culture or operations |
* Improve operational security | * Improve operational security | ||
* Affect attitudes of effective leadership | * Affect attitudes of effective leadership | ||
* Affect attitudes of researchers | * Affect attitudes of researchers | ||
- | * Make a plan for alignment (e.g., [[https:// | + | * Make a plan for alignment (e.g., [[https:// |
- | * Make a plan for what to do with powerful AI (e.g., | + | * Make plans for what to do with powerful AI (e.g. a process for producing powerful aligned AI given some type of advanced AI system, or a specification |
* Improve their ability to make themselves (selectively) transparent | * Improve their ability to make themselves (selectively) transparent | ||
* Try to better understand the future, the strategic landscape, risks, and possible actions | * Try to better understand the future, the strategic landscape, risks, and possible actions | ||
Line 50: | Line 50: | ||
* Capture scarce resources | * Capture scarce resources | ||
* E.g., language data from language model users | * E.g., language data from language model users | ||
+ | |||
+ | //Primary author: Zach Stein-Perlman// |