Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

MIRI's Approach – Machine Intelligence Research Institute

intelligence.org

Post reply on HN
Print view View original

31–40 of 78 posts

Re: MIRI's Approach – Machine Intelligence Research Institute

#31

Post by JoshTriplett »

reasonattlm wrote: post #10

MIRI is one of the success stories to emerge from the transhumanist community of the 80s to 00s. Others include the Methuselah Foundation, SENS Research Foundation, Future of Humanity Institute, and so on. When it comes to prognosticating on the future of strong AI MIRI falls on the other side of the futurist community from where I stand. I see the future as being one in which strong AI emerges from whole brain emula…

Note that MIRI's current position no longer suggests the development of actual artificial consciousness, just the development of human-equivalent optimization processes. In other words, they argue that you can develop a process capable of solving human-level and harder problems without giving it self-awareness. And that seems like a feature: if you avoid building self-aware machine intelligences, you don't have to worry about what they want; you can build them to only care about what existing sapient beings want.

Re: MIRI's Approach – Machine Intelligence Research Institute

#32

Post by sampo »

pjscott wrote: post #17
idlewords wrote: post #15

Are there any examples of substantive AI work to come out of MIRI? And have they succeeded at all at engaging the actual AI research community? The last time I looked at them, they were consumed with grandiose philosophical projects like "axiomatize ethics" and provably non-computable approaches like AIXI, not to mention the Harry Potter fanfic. But I'm asking this question in good faith - have things changed at MIRI…

If you'd like to give them another look, here's an up-to-date list of their publications: https://intelligence.org/all-publications/

Counting only articles and conference papers that look like they are in at least somewhat established journals or conferences, I quickly count:

    2015: 4
    2014: 6
    2013: 1
    2012: 5
    2011: 1
    2010: 4
That would be about the level of 1 or 2 very mediocre early career scientists. And very little for MIRI's 8 people staff and 13 Research Associates.

MIRI publishes a lot more, but they mostly operate outside of traditional scientific journals, a lot of MIRI technical reports published on their website.

Re: MIRI's Approach – Machine Intelligence Research Institute

#33

Post by ikeboy »

dmfdmf wrote: post #29
ikeboy wrote: post #25

Earlier quoted context omitted.

>humans are not threatened by the former So you categorically reject the scenario of a machine "processing meaningless symbols" being harmful in any way? How does that follow from the Chinese Room experiment?

> So you categorically reject the scenario of a machine "processing meaningless symbols" being harmful in any way? How does this follow from what I said? > How does that follow from the Chinese Room experiment? The implicit (philosophic) question behind the Chinese Room experiment is; where does meaning come from? What imbues meaning to the meaningless symbols that computers process\? This is an old, unanswered philo…

> How does this follow from what I said?

You said "humans are not threatened by the former". Not threatened implies that they can't be harmful.

>The implicit (philosophic) question behind the Chinese Room experiment is; where does meaning come from? What imbues meaning to the meaningless symbols that computers process\? This is an old, unanswered philosophic question. I implied it in my answer but I will make it explicit; it comes from our perceptual awareness of existence via the senses.

I don't see why that would imply anything at all about the safety of machines.

Re: MIRI's Approach – Machine Intelligence Research Institute

#34

Post by schoen »

fitzwatermellow wrote: post #28

We can't comprehend the danger that could be caused by strong AI because we don't understand how to make worlds. Embedded within the fabric of the cosmos are the instructions for materializing a black hole from dark matter and energy. And though the recipe may be hidden from our mortal minds it's possible they may be discovered by a de novo thinking machine. A software system with infinite IQ but the moral sense of a…

You could do quite a lot of damage with the regular old laws of nature that we understand already, if you were really good at applying them. For example, you could make autonomous robot weapons, or extremely virulent pathogens with a long incubation period. Or do some geoengineering (you don't even have to be good at it, you just have to do something with a big impact). There's absolutely no need to "bend the laws that govern space and time"!

Edit: or launch a planetary defense mission in reverse, to increase the probability of asteroid impact events.

Re: MIRI's Approach – Machine Intelligence Research Institute

#36

Post by gone35 »

reasonattlm wrote: post #10

MIRI is one of the success stories to emerge from the transhumanist community of the 80s to 00s. Others include the Methuselah Foundation, SENS Research Foundation, Future of Humanity Institute, and so on. When it comes to prognosticating on the future of strong AI MIRI falls on the other side of the futurist community from where I stand. I see the future as being one in which strong AI emerges from whole brain emula…

"[...] starting around 2030 as processing power becomes cheap enough [...]"

Surely you are not relying on an (arguably naïve) extrapolation of Moore Law-type progress? Recall we are fast reaching the end of it.

Re: MIRI's Approach – Machine Intelligence Research Institute

#37

Post by rl3 »

It's worth noting that in Bostrom's Superintelligence, biology is included among potential paths to superintelligence. Personally, I think it's a bit of an overlooked path.

Granted, most of what Bostrom refers to in context of the biological path is mostly related to human augmentation, genetics, selective breeding - things of that nature. What I'm referring to is biology serving as a raw computational substrate.

While biology (or at least brain tissue) is dramatically slower in terms of raw latency when compared to microprocessors, it's arguably a far cheaper and vastly more dense form of computation. It also has the natural algorithm for intelligence that we keep trying to deduce and transpose into silicon - well, at least the raw form of it - built in by default.

Assuming ethics are thrown out the window and human brain tissue is grown in vitro at scale, then it probably would make sense to hook it up to a supercomputer for good measure. At the very least, we have the technological foundations[1][2] for such an experiment at present day, it's just a matter of scaling things up.

If I were to hazard a guess, human brain tissue grown to significant scale would probably not magically achieve sentience, or exhibit any complex anthropomorphic traits. On the contrary, it would probably have more in common with a simple neural network implemented on silicon, at least in terms of its capacity for self-awareness. Conversely, it would stand to reason that an entity with a higher degree of self-awareness, implemented in silicon, should rank higher in terms of ethical considerations than living tissue.

Obviously the aforementioned experiment would be completely unethical, but it's interesting to ponder it as a hypothetical - that today we may have the capability to bootstrap a superintelligent machine using biology as a computational shortcut. But we can't, because ethics. Instead, we're waiting for the inevitable increase in computational power to arrive so that we can do essentially the same thing, just in digital form.

[1] http://www.nytimes.com/2014/10/13/science/researchers-replic...

[2] http://neural.bme.ufl.edu/page12/page1/assets/NeuroFlght2.pd...

Re: MIRI's Approach – Machine Intelligence Research Institute

#38

Post by sanxiyn »

idlewords wrote: post #15

Are there any examples of substantive AI work to come out of MIRI? And have they succeeded at all at engaging the actual AI research community? The last time I looked at them, they were consumed with grandiose philosophical projects like "axiomatize ethics" and provably non-computable approaches like AIXI, not to mention the Harry Potter fanfic. But I'm asking this question in good faith - have things changed at MIRI…

You don't consider AIXI part of the actual AI research community?

Also, AIXI is non-computable, but AIXItl is.

Re: MIRI's Approach – Machine Intelligence Research Institute

#39

Post by visarga »

guelo wrote: post #23
blennon wrote: post #14

Earlier quoted context omitted.

I agree with you in terms of approach that AI will emerge first from brain emulation. I disagree with you on the timeline. I know you say 'starting around 2030', but I think that's a little ambitious. While I'm an AI/machine learning practitioner now, my recent Ph.D. work was on computational modeling of the nervous system; namely the cerebellum. The reason I say 2030 is ambitious, is because there are still a lot of…

Seems like it would be quicker to obtain full knowledge of how DNA and cell replication work. Then the simulation could grow a brain without having to fully understand it.

We could grow neurons on silicon chips, or use small tubes that attract axons and dendrites to grow through them (seen a paper about it once) and use them as an I/O interface to a lab-grown brain. We can already grow 5mm size mini brains with human neural cells. It might be more energy efficient and we could take brains to a whole new level.

Re: MIRI's Approach – Machine Intelligence Research Institute

#40

Post by Dylan16807 »

dmfdmf wrote: post #29
ikeboy wrote: post #25

Earlier quoted context omitted.

>humans are not threatened by the former So you categorically reject the scenario of a machine "processing meaningless symbols" being harmful in any way? How does that follow from the Chinese Room experiment?

> So you categorically reject the scenario of a machine "processing meaningless symbols" being harmful in any way? How does this follow from what I said? > How does that follow from the Chinese Room experiment? The implicit (philosophic) question behind the Chinese Room experiment is; where does meaning come from? What imbues meaning to the meaningless symbols that computers process\? This is an old, unanswered philo…

You know we can give a computer senses super-easily, right?
Post reply on HN