Less Wrong Q&A with Eliezer Yudkowsky: Ask Your Questions

MichaelGR

As promised, here is the "Q" part of the Less Wrong Video Q&A with Eliezer Yudkowsky.

The Rules

1) One question per comment (to allow voting to carry more information about people's preferences).

2) Try to be as clear and concise as possible. If your question can't be condensed to a few paragraphs, you should probably ask in a separate post. Make sure you have an actual question somewhere in there (you can bold it to make it easier to scan).

3) Eliezer hasn't been subpoenaed. He will simply ignore the questions he doesn't want to answer, even if they somehow received 3^^^3 votes.

4) If you reference certain things that are online in your question, provide a link.

5) This thread will be open to questions and votes for at least 7 days. After that, it is up to Eliezer to decide when the best time to film his answers will be. [Update: Today, November 18, marks the 7th day since this thread was posted. If you haven't already done so, now would be a good time to review the questions and vote for your favorites.]

Suggestions

Don't limit yourself to things that have been mentioned on OB/LW. I expect that this will be the majority of questions, but you shouldn't feel limited to these topics. I've always found that a wide variety of topics makes a Q&A more interesting. If you're uncertain, ask anyway and let the voting sort out the wheat from the chaff.

It's okay to attempt humor (but good luck, it's a tough crowd).

If a discussion breaks out about a question (f.ex. to ask for clarifications) and the original poster decides to modify the question, the top level comment should be updated with the modified question (make it easy to find your question, don't have the latest version buried in a long thread).

Update: Eliezer's video answers to 30 questions from this thread can be found here.

As promised, here is the "Q" part of the Less Wrong Video Q&A with Eliezer Yudkowsky.

The Rules

1) One question per comment (to allow voting to carry more information about people's preferences).

3) Eliezer hasn't been subpoenaed. He will simply ignore the questions he doesn't want to answer, even if they somehow received 3^^^3 votes.

4) If you reference certain things that are online in your question, provide a link.

Suggestions

It's okay to attempt humor (but good luck, it's a tough crowd).

Update: Eliezer's video answers to 30 questions from this thread can be found here.

I'm sorry, but I don't really have a proper lesson plan laid out - although the ongoing work of organizing LW into sequences may certainly help with that. It would depend on the specific issue and what I thought needed to be understood about that issue.

If they drew my feedback cycle of an intelligence explosion and then drew a different feedback cycle and explained why it fit the historical evidence equally well, then I would certainly sit up and take notice. It wouldn't matter if they'd done it on their own or by reading my stuff.

E.g. Chalmers at the Singularity Summit is an example of an outsider who wandered in and started doing a modular analysis of the issues, who would certainly have earned the right of serious consideration and serious reply if, counterfactually, he had reached different conclusions about takeoff... with respect to only the parts that he gave a modular analysis of, though, not necessarily e.g. the statement that de novo AI is unlikely because no one will understand intelligence. If Chalmers did a modular analysis of that part, it wasn't clear from the presentation.

Roughly, what I expect to happen by default is no modular analysis at all - just snap consideration and snap judgment. I feel little need to explain such.

It must be possible to engage at least some of these people in some sort of conversation to understand their positions, whether a public dialog as with Scott Aaronson or in private.

19Steve_Rayhawk17y

You, or somebody anyway, could still offer a modular causal model of that snap consideration and snap judgment. For example: * What cached models of the planning abilities of future machine intelligences did the academics have available when they made the snap judgment? * What fraction of the academics are aware of any current published AI architectures which could reliably reason over plans at the level of abstraction of "implement a proxy intelligence"? * * What fraction of them have thought carefully about when there might be future practical AI architectures that could do this? * * What fraction use a process for answering questions about the category distinctions that will be known in the future, which uses as an unconscious default the category distinctions known in the present? * What false claims have been made about AI in the past? What decision rules might academics have learned to use, to protect themselves from losing prestige for being associated with false claims like those? * How much do those decision rules refer to modular causal analyses of the object of a claim and of the fact that people are making the claim? * How much do those decision rules refer to intuitions about other peoples' states of mind and social category memberships? * How much do those decision rules refer to intuitions about other peoples' intuitive decision rules? * Historically, have peoples' own abilities to do modular causal analyses been good enough to make them reliably safe from losing prestige by being associated with false claims? What fraction of academics have the intuitive impression that their own ability to do analysis isn't good enough to make them reliably safe from losing prestige by association with a false claim, so that they can only be safe if they use intuitions about the states of mind and social category memberships of a claim's proponents? * Of those AI academics who believe that a machine intelligence cou

1timtyler17y

Chalmers reached some odd conclusions. Probably not as odd as his material about zombies and consciousness, though.