In the software industry we have the concept of responsible disclosure when one finds a security exploit in a published package.
Do we have responsible disclosure procedures for something that may represent a fundamental AI capability advancement? Who would you even disclose to? Slide into Yudkowsky’s DMs?
MIRI should have a form you can fill out (or an email address) specifically for people who think they’ve advanced AI and are worried about ending the world with it. MIRI should also have Cold-War-style hotlines to OpenAI, DeepMind, and the other major actors.
Does MIRI do much in the way of capabilities research? It is my understanding that they don’t. If MIRI doesn’t do capabilities research then it seems unlikely to me they would do much with an idea that is all about capabilities advancement.
I don’t think they do either. I was thinking they would provide alignment advice / troubleshooting services and would facilitate multipolar coordination in the event of a multiple slow-takeoff scenario.
In the software industry we have the concept of responsible disclosure when one finds a security exploit in a published package.
Do we have responsible disclosure procedures for something that may represent a fundamental AI capability advancement? Who would you even disclose to? Slide into Yudkowsky’s DMs?
MIRI should have a form you can fill out (or an email address) specifically for people who think they’ve advanced AI and are worried about ending the world with it. MIRI should also have Cold-War-style hotlines to OpenAI, DeepMind, and the other major actors.
Does MIRI do much in the way of capabilities research? It is my understanding that they don’t. If MIRI doesn’t do capabilities research then it seems unlikely to me they would do much with an idea that is all about capabilities advancement.
I don’t think they do either. I was thinking they would provide alignment advice / troubleshooting services and would facilitate multipolar coordination in the event of a multiple slow-takeoff scenario.
I guess the process would be to pass it on to whichever cababilities researchers they trust with it. There would be a few of them at this point.
So, why not go straight to those researchers instead of MIRI? Because MIRI are more legible responsible intermediaries I guess.
I am not sure I understand your question (sorry, I do not know what is Yudkowsky’DMs)
I basically disclosed, to all, that the way we all think we think, does work.
What kind of responsibility could that bear ?
Sorry, I was being a bit flip/insider-y. Probably inappropriately so.
I’m curious how much you’ve engaged with the AI Safety literature/arguments?
“Yudkowsky’s DM” --> Eliezer Yudkowsky’s [Twitter] Direct Messages.
I think I have expressed my views on the matter of responsibility quiet clearly in the conclusion.
I just checked Yudkowsky on Google. He founded this website, so good.
Here is not the place to argue my views on super-intelligence, but I clearly side with Russell and Norvig. Life is just too complex; luckily.
As for safety, the title of Jessica Taylor’s article is:
“Quantilizers: A Safer Alternative to Maximizers for Limited Optimization”.
I will just be glad to have proved that alternative to be effective.