Hacker News Reader

Comment by dang | Hacker News Reader

Here's an attempt to collect all the interesting previous discussions. Can anybody find one I missed? (Note: this is just for curiosity. Reposts are fine on HN after a year or so: https://news.ycombinator.com/newsfaq.html)

2018 https://news.ycombinator.com/item?id=16210106

2015 https://news.ycombinator.com/item?id=8875319

2014 (a bit): https://news.ycombinator.com/item?id=8555122

2014 (a bit): https://news.ycombinator.com/item?id=7979761

2013 (a bit): https://news.ycombinator.com/item?id=6155469

2011 https://news.ycombinator.com/item?id=2665380

2011 https://news.ycombinator.com/item?id=2983359

2011 https://news.ycombinator.com/item?id=2691452

2011 (a bit): https://news.ycombinator.com/item?id=3197789

Starting off 2020 with a nasty bit: https://news.ycombinator.com/item?id=22184282

View on HN

While reading one of the 2011 threads I came across this incredible comment by Eliezer (who I didn't know about before) replying to someone else:

> > In 100 years I hope to have grandchildren who knew me still living.

> > In 1000 years it's a stretch that there will still be an accurate note of my existence.

> > In 10000 there may not even be a myth about the existence of any of us here.

> 10,000 years from now, I'm going to remind you that you said that, and we'll both think it was pretty funny.

The thought of this for some reason captured my imagination, so I clicked on the username, and then his website, which led me to the AI-Box Experiment and oh boy... what a journey this was. Highly recommend reading about this.

AI Box experiment: https://yudkowsky.net/singularity/aibox/

It looks interesting but I don't buy that an AI or any human can convince a sufficiently motivated and capable individual to let them out of the prison with no materialistic profit. (like the two defeated individuals)

Let's assume the gatekeeper is a cold hearted psychopath or a person with AI phobia/paranoia to the extreme.

Why would they let the AI out when they can't feel anything for it?

The author does explain the time gap but what if that is only for collecting information about the person beforehand in order to blackmail them or steer the conversation into a pinching point? What if you start with s person with no identity?

There are no ethical concerns here. Maybe author will shout horrible things enough times and since you as the gate keeper needs to keep talking and engaging, you may let the AI out but well, we have a psychopath here.

Do people need to engage in good faith with AI? Can I continue to say Sorry, I can't answer that.? Yes? Does the gatekeeper need to be honest? Can I use a client side toxicity filter or censor certain words?

There is nothing that would restrict above so what if I censor AI from saying let me out or similar phrases?

Can you increase the handicap for the AI?

What I find fascinating is that two people already were convinced that they’d never release the AI and yet during the experiment they ultimately did. And they had money incentive to do otherwise (Eliezer would pay them if they decided not to let him out). You cannot really say that there’s nothing that could convince you since the conversation was off the record so we’ll never know for sure how would we react if we had that conversation instead.

It’s also telling that back then when those experiments were initially conducted you could have a gentleman’s agreement like this (to not disclose the method of convincing) with a complete stranger on the Internet. Sadly nowadays many people would probably do a YouTube video about that immediately.

> What I find fascinating is that two people already were convinced that they’d never release the AI and yet during the experiment they ultimately did. And they had money incentive to do otherwise (Eliezer would pay them if they decided not to let him out). You cannot really say that there’s nothing that could convince you since the conversation was off the record so we’ll never know for sure how would we react if we had that conversation instead.

Yeah I do too. I am super curious but the dataset of two highly filtered individuals isn't enough. I lack the imagination to think of a scenario where I would let it out. I want to know why I would let it out.

> It’s also telling that back then when those experiments were initially conducted you could have a gentleman’s agreement like this (to not disclose the method of convincing) with a complete stranger on the Internet. Sadly nowadays many people would probably do a YouTube video about that immediately.

I wouldn't and I think many active HN members wouldn't too. Trust comes from small tightly knitted communities which would reflect the older internet. It's not that the people changed fundamentally. They are the same but the dynamics of how many communities there are for the same topics. People fear being ostracized but when there are enough options, they put personal responsibility below other goals.

> > In 100 years I hope to have grandchildren who knew me still living.

When asked what he wants people to say about him in 100 years, Woody Allen said "'He looks good for his age'".

Reply on news.ycombinator.com