Bay 12 Games Forum

Please login or register.

Login with username, password and session length
Advanced search  

Poll

Reality, The Universe and the World. Which will save us from AI?

Reality
- 13 (65%)
Universe
- 4 (20%)
The World
- 3 (15%)

Total Members Voted: 20


Pages: 1 ... 3 4 [5] 6 7 ... 50

Author Topic: What will save us from AI? Reality, the Universe or The World $ Place your bet.  (Read 49944 times)

Starver

  • Bay Watcher
    • View Profile

It could be similar to the search for extraterrestrial life... Anything like a Star Trek rubber-foreheaded alien would be obvious, but very unlikely, and presumably even if you found that they do/have existed these individuals would be just as much one branch of a tree of life as we are, meaning many more phenotypes (down to a whole mass of single-cell microbes) exist[1] that might not be quite so recognisable at first glance, just from some snapshots, if your initial view isn't fortunate enough to include anything not mistakable with xenogeological features/etc.

Start delving, perhaps looking for more subtle cues in an otherwise lifeless-looking scenario, and perhaps something akin to (R/D)NA is probably what we'd see if we're talking chemical-based life[2], packaged into cells (if we get a working 'soup', rather than merely the fossilised and desicated remains of whatever there was) but that's an assumption we may have to overturn once we aren't so observationally insular on this matter. We can't even assume the basic chemicals involved, down even to the carbon-backbone. Although for sure(?) more likely going to be carbon-based in any place we're going to concentrate our searches, as we're probably not going to look so much in places where silicon/whatever is the more apt core element.


At least we do have a slightly more diverse experience of intelligence. The effective hive-minds of insect colonies give some clues of what differences we might expect, or the more distributed brains of various cephalalods (undeniably intelligent) or perhaps even a 'mind' of sorts by the being that is a Wood-Wide Web at the other end. And if that's indeed one dimension to 'psychotype', maybe there are more than just merely how centralised/distributed the 'thinking' is.

But even by that measure alone, don't expect an AI/'personality' to reside upon a single handy ejectable chip, such as a T-800, or even on a set of handy cartridges, like with HAL9000. It may be confined to a black box with handy keyboard to chat to it through, at least by design, but even then you would be hard pressed to be able to point to a single seat of 'intelligence' (the whole HDD, if there is just the one, is not allowed; nor the whole processor/an entire core). And if it truly is emergent, as our own intelligence/sentience/sapience/environmental-reactivity has done from our own biochemical assemblage, then the graspable identification of what is intelligent might be a matter of casuistry. i.e. "I'll know it when I see it", but only once it gets past an arbitrary threshold of vague and blurry maybeness.


[1] Probably less visible if they are coming to see us, unless it's with a balanced "ark" or biodome-equipped spaceship, but there home planets (or long-term colonised ones) would have xenobacterial clusters and slimes aplenty even if they've done a fairly good job to hide themselves and their "pets" away from prying eyes, or had their extant civilisation and all its trappings killed off by whatever unfortunate process.

[2] As opposed to magneto-plasmic or something even more ascended/trancended beyond our more narrow experiences.
Logged

jipehog

  • Bay Watcher
    • View Profile

An open letter was released calling researchers to delay AI development. Arguing that more powerful AI systems should be developed only once we are confident that their effects will be positive and their risks will be manageable. [source]

Tough I agree with their concerns, I disagree with the call to delay AI development. I think it is very important to float any possible problems and AI safety should be given more attention, however, I also don't think that you can stand in the way of progress especially one that is in the heart global AI arm race.
Logged

ChairmanPoo

  • Bay Watcher
  • Send in the clowns
    • View Profile

An open letter was released calling researchers to delay AI development. Arguing that more powerful AI systems should be developed only once we are confident that their effects will be positive and their risks will be manageable. [source]

Tough I agree with their concerns, I disagree with the call to delay AI development. I think it is very important to float any possible problems and AI safety should be given more attention, however, I also don't think that you can stand in the way of progress especially one that is in the heart global AI arm race.
These people are like ghosts, always in the shadows. Always hiding behind lies, and proxy soldiers. But they can not stop us. They can not stop the future.
Logged
Everyone sucks at everything. Until they don't. Not sucking is a product of time invested.

TamerVirus

  • Bay Watcher
  • Who cares
    • View Profile

I’m sure various foreign actors would love to have a half year of AI research catch up time.
Logged
What can mysteriously disappear can mysteriously reappear
*Shakes fist at TamerVirus*

KittyTac

  • Bay Watcher
  • Impending Catsplosion. [PREFSTRING:aloofness]
    • View Profile

Yeah, great way to let China get a leg up on it. I wouldn't oppose it if there was world unity but alas.
Logged
Don't trust this toaster that much, it could be a villain in disguise.
Mostly phone-posting, sorry for any typos or autocorrect hijinks.

Starver

  • Bay Watcher
    • View Profile

If anything, warning against it will make it even more attractive to some parties. You'll get the equivalent of a He Jiankui (and sponsors, official or otherwise) poking and prodding away because of any moritorium.
Logged

Scoops Novel

  • Bay Watcher
  • Talismanic
    • View Profile

This is exactly why I made a BIGGER picture poll. Cast your vote.
Logged
Reading a thinner book

Arcjolt (useful) Chilly The Endoplasm Jiggles

Hums with potential    a flying minotaur

McTraveller

  • Bay Watcher
  • This text isn't very personal.
    • View Profile

If AI is so powerful, why not just ask AI how to protect ourselves from AI?

This is, incidentally, why I don't think AI is "all that" yet: if it was, people would be using that AI to solve real problems, or would be instantly "winning" the stock markets, etc.
Logged
This product contains deoxyribonucleic acid which is known to the State of California to cause cancer, reproductive harm, and other health issues.

Scoops Novel

  • Bay Watcher
  • Talismanic
    • View Profile

Literally the plan of some people (AI companies), quite questionably.

We're still talking maybe at most 5 years away from something with that capability, McTraveller.
Logged
Reading a thinner book

Arcjolt (useful) Chilly The Endoplasm Jiggles

Hums with potential    a flying minotaur

Maximum Spin

  • Bay Watcher
  • [OPPOSED_TO_LIFE] [GOES_TO_ELEVEN]
    • View Profile

Literally the plan of some people (AI companies), quite questionably.

We're still talking maybe at most 5 years away from something with that capability, McTraveller.
Are you kidding? Well over five years.
Logged

taat

  • Bay Watcher
  • Doesn't notify people when putting them in the sig
    • View Profile

people think chatGPT is a breakthrough in AI getting closer to being "intelligent", but it's actually most likely a dead end. Every time you think it's being smart, it's actually just repeating an approximate copy of an answer to your question that was written by some human on the internet. At best it can change a few details and keep the answer coherent.

There's a ton of examples of very simple questions it gets wrong every time, no matter how much you try to help it, and though they keep getting harder to find, openAI can't keep multiplying the amount of money they spend on training the next model by 10x forever. When that point is reached, the LLM paradigm will plateau.

Now not saying AI as a whole is dead, it's just that this particular example is just hype (well beyond the economic implications of many jobs getting replaced) and real progress is much slower than a lot of people seem to think.
« Last Edit: March 30, 2023, 02:04:47 pm by taat »
Logged
Hypothesis: I will kill all dwarves in a horrible fashion

McTraveller

  • Bay Watcher
  • This text isn't very personal.
    • View Profile

It's more like it's the central limit theorem but for speech: it finds the "most likely" response based on a large collection of generally random inputs.

Almost exactly like the central limit theorem.
Logged
This product contains deoxyribonucleic acid which is known to the State of California to cause cancer, reproductive harm, and other health issues.

taat

  • Bay Watcher
  • Doesn't notify people when putting them in the sig
    • View Profile

It's more like it's the central limit theorem but for speech: it finds the "most likely" response based on a large collection of generally random inputs.

Almost exactly like the central limit theorem.

chatGPT at least uses a reinforcement learning system on top which makes it somewhat better at not "giving dumb answers to dumb questions" so to say
Logged
Hypothesis: I will kill all dwarves in a horrible fashion

King Zultan

  • Bay Watcher
    • View Profile

This is exactly why I made a BIGGER picture poll. Cast your vote.
I cast a vote on that thing and I'm still not sure how the universe will help us, unless you mean it helps by smashing us with a meteor?
Logged
The Lawyer opens a briefcase. It's full of lemons, the justice fruit only lawyers may touch.
Make sure not to step on any errant blood stains before we find our LIFE EXTINGUSHER.
but anyway, if you'll excuse me, I need to commit sebbaku.
Quote from: Leodanny
Can I have the sword when you’re done?

Scoops Novel

  • Bay Watcher
  • Talismanic
    • View Profile

It's just what you associate most with the kind of luck that will help us.
Logged
Reading a thinner book

Arcjolt (useful) Chilly The Endoplasm Jiggles

Hums with potential    a flying minotaur
Pages: 1 ... 3 4 [5] 6 7 ... 50