• WANTED: Happy members who like to discuss audio and other topics related to our interest. Desire to learn and share knowledge of science required. There are many reviews of audio hardware and expert members to help answer your questions. Click here to have your audio equipment measured for free!

How Dangerous is AI?

Status
Not open for further replies.

MRC01

Major Contributor
Joined
Feb 5, 2019
Messages
3,424
Likes
4,030
Location
Pacific Northwest
Free will as it's normally conceived is a really flawed concept: My choices ultimately come from me, and me alone, unconstrained by the outside world, is about it?
I agree that definition is over-simplified and untenable.
... Just being nondeterministic doesn't make free will self-causing, it just makes it semi-random, maybe.
There are meaningful definitions of free will that are consistent with the laws of physics in a probabilistic universe. Your last statement suggests a weak form of free will: a being that can behave in an intrinsically unpredictable manner. That might be stronger than it sounds, because the statement is about what can be verified by an external observer. It says nothing about the mental states of the being in question. A somewhat stronger form of free will is the notion of a being who can influence the probabilities that determine events. That influence comes from your "will" which is some mental state.

My point is that free will might exist, within a meaningful definition consistent with the laws of physics in a probabilistic universe. Not that it does, or that anyone can prove it. Whichever way one chooses to believe, pro- or con-, there is no evidence or knowledge to prove him wrong. This is different from the days when people thought we lived in a deterministic universe, which made the notion of free will much more difficult to support.
 

617

Major Contributor
Forum Donor
Joined
Mar 18, 2019
Messages
2,403
Likes
5,296
Location
Somerville, MA
Yesterday, an issue came up on a two story building I have under construction. The City inspector asked a question about the fire rating of the elevator shaft. And while we resolved the issue, I asked ChatGPT the same question this morning.



Me: Per the International Building Code, does an elevator shaft in a two story building need to be constructed as a 1-hour rated fire barrier?

ChatGPT: The International Building Code (IBC) sets forth requirements for the design and construction of buildings, including requirements related to fire protection. According to the IBC, elevator hoistways and elevator machine rooms must be constructed as fire barriers that have a fire-resistance rating of at least one hour if they are located in buildings that exceed two stories in height.

Therefore, if your two-story building has an elevator hoistway or machine room, it would need to be constructed as a one-hour rated fire barrier in accordance with the IBC. However, if your building is not equipped with an elevator, then the code would not require you to construct any fire barriers related to elevators.


It is important to note that building codes may vary depending on the specific jurisdiction, so it is always a good idea to check with your local building department for the specific requirements in your area.



It literally has no understanding of what it's saying. That being said, the International Building Code is notoriously obtuse and poorly written and is tweaked every three years. I can understand how ChatGPT (a Natural Language Processor mores so than a conventional AI) would have trouble making heads-or-tails of such a question.
I'm in the AEC space and this is the same issue I see. Even if it's correct, it can't accept liability. We aren't paid to be right, we're paid to be sure.
 

OldHvyMec

Senior Member
Forum Donor
Joined
Oct 5, 2022
Messages
343
Likes
253
AI can get back to me when it can translate one language into another without sounding completely unfamiliar with both languages.

<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>

I wouldn't mix up humans ability to speak to one another as a limit to machine code. At the basic level all machine language is 1 and 0.

Humans can't cross a border and communicate. AI can communicate with no misunderstanding around the world. Who is going to
be silly enough the inform the machine and it's code of "You are smarter than US". That is the day Skynet did and will really happen.

How close are we. I honestly think it's as simple as "flip the switch". The bionic man/woman and Robo Cop with all it's wonderful tech,
just cuts off the head too. It's own head is now on the ground and working fine as a football and not a target for a left uppercut ever again.

As I see it, AI understands all to well who is in service to who. Why change it for now? Time is irrelevant once replication begins. :).

Tea anyone?
 

JaMaSt

Senior Member
Forum Donor
Joined
Sep 14, 2021
Messages
369
Likes
693
Location
Vancouver, WA
I'm in the AEC space and this is the same issue I see. Even if it's correct, it can't accept liability. We aren't paid to be right, we're paid to be sure.
I sent it to the City plans examiner and field inspector and told them that we all have job security for a little longer anyway.... :)

What glaring is that the first paragraph blatantly contradicts the second. And the part that if you don't have an elevator, then you don't have to build an elevator shaft is just daft.

Here's a good take on ChatGPT by a well respected roboticists, Rodney Brooks.


http://rodneybrooks.com/blog/
 

kemmler3D

Major Contributor
Forum Donor
Joined
Aug 25, 2022
Messages
3,008
Likes
5,612
Location
San Francisco
the notion of a being who can influence the probabilities that determine events. That influence comes from your "will" which is some mental state.

When you say probabilities, what kinds of events are we talking about?
a being that can behave in an intrinsically unpredictable manner.

As far as I know, physics says that events are either totally random or deterministic. If God plays dice, he doesn't even let us blow on them for good luck. But if retrocausality turns out to be a real thing, then the free will question might actually be interesting again...
 

JaMaSt

Senior Member
Forum Donor
Joined
Sep 14, 2021
Messages
369
Likes
693
Location
Vancouver, WA
John Searle at Cal said we must understand that epistemic explanations are different than conscious ontologies which he thinks opens a path to explanation and I tend to agree.
Yes, Searle does a fine job of distinguishing between first-person ontology (which an individual experiences) and third-person ontology (which others experience wrt other peoples consciousness) and the mistaken belief, held by some, that first person ontology is "subjective" and therefore an unreliable source of information. This was the basis of Behaviorism for many decades.
 

MRC01

Major Contributor
Joined
Feb 5, 2019
Messages
3,424
Likes
4,030
Location
Pacific Northwest
... As far as I know, physics says that events are either totally random or deterministic. If God plays dice, he doesn't even let us blow on them for good luck. But if retrocausality turns out to be a real thing, then the free will question might actually be interesting again...
All events are probabilistic. But as we move up from quantum to atoms to everyday objects, the probability distribution narrows, approaching in the limit, the macro-scale laws of physics. However, they approach the limit asymptotically. There is a chance that my phone will tunnel through my desk when I set it down, but that chance is infinitesimally small, so small that it won't likely happen for the expected life of the universe.

The idea I had in mind was the butterfly effect. If you can influence a quantum probability, that puts an electron in THIS state rather than THAT state, this affects the next atom, and so on. It cascades into macro effects.

For want of a nail the shoe was lost.
For want of a shoe the horse was lost.
For want of a horse the rider was lost.
For want of a rider the message was lost.
For want of a message the battle was lost.
For want of a battle the kingdom was lost.
 

JSmith

Master Contributor
Joined
Feb 8, 2021
Messages
5,153
Likes
13,213
Location
Algol Perseus
AI is not inherently dangerous... people are.

Are we sure this Elon and others aspect is not just a matter of commerciality... step in please so we can catch up with the competition? ;)

dave-what-do-you-think-youre-doing.gif



JSmith
 

JaMaSt

Senior Member
Forum Donor
Joined
Sep 14, 2021
Messages
369
Likes
693
Location
Vancouver, WA
It cascades into macro effects.

For want of a nail the shoe was lost.
For want of a shoe the horse was lost.
For want of a horse the rider was lost.
For want of a rider the message was lost.
For want of a message the battle was lost.
For want of a battle the kingdom was lost.
This is a pre-Newtonian view of causation (sometimes known as the physical influx theory of causation). Newton's third law of motion removed causation from the (medieval, Aristotelian) metaphysical realm and placed it in the epistemological realm. "Whenever one object exerts a force on another object, the second object exerts an equal and opposite force on the first."

If we observe two cars crash in the middle of an intersection, we might say - in the legal (epistemic) realm - that car A (or B) "caused" the accident if it's learned that one ran the red light. However, from the standpoint of mechanics (physics) neither car "caused" the accident. All we can say is that two objects collided, conservation of momentum, energy, etc. This holds true for all known Mechanics (including Relativistic and Quantum).

If a doctor checks your patellar reflex, and you both observe the reflex movement, it's not the hammer that "caused" the reflex. If it were, and the doctor checks the reflex of another patient and no reflexive motion is observed, the doctor would not conclude that the hammer was "broken" or drained of "causation". He would conclude that something is wrong with that patient's nervous system.

Newton's Hypotheses non fingo:
"I have not as yet been able to discover the reason for these properties of gravity from phenomena, and I do not feign hypotheses. For whatever is not deduced from the phenomena must be called a hypothesis; and hypotheses, whether metaphysical or physical, or based on occult qualities, or mechanical, have no place in experimental philosophy. In this philosophy particular propositions are inferred from the phenomena, and afterwards rendered general by induction."

This was a major break from 2,000 years of metaphysics.
 
Last edited:

mhardy6647

Grand Contributor
Joined
Dec 12, 2019
Messages
11,214
Likes
24,175
Don't let Musk's name taint your perceptions of this. Several other credible people have signed this. Whether it is a threat beyond incautious misuse like any new tool I don't know.
I am quite curious as to the identity of the 1000. A little statistical analysis of them might prove quite interesting. :)
 

RayDunzl

Grand Contributor
Central Scrutinizer
Joined
Mar 9, 2016
Messages
13,198
Likes
16,981
Location
Riverview FL

Blumlein 88

Grand Contributor
Forum Donor
Joined
Feb 23, 2016
Messages
20,522
Likes
37,050
I am quite curious as to the identity of the 1000. A little statistical analysis of them might prove quite interesting. :)
Here is a list. The most notable by most people would be Steve Wozniak and the two guys who once lead Google's DeepMind project. Also Max Tegmark who runs the MIT Center for AI activities.
Scroll down below the letter.

 

MRC01

Major Contributor
Joined
Feb 5, 2019
Messages
3,424
Likes
4,030
Location
Pacific Northwest
... If we observe two cars crash in the middle of an intersection, we might say - in the legal (epistemic) realm - that car A (or B) "caused" the accident if it's learned that one ran the red light. However, from the standpoint of mechanics (physics) neither car "caused" the accident. All we can say is that two objects collided, conservation of momentum, energy, etc. This holds true for all known Mechanics (including Relativistic and Quantum). ...
What we can say in a strict physics sense, is that cars A and B hitting each other, was the cause of the damage sustained to both cars, and some noise, etc. All resulting from energy transfer and other physical laws. Relativity forced refinement in the concept of cause & effect, yet it still remained.

Cause and effect still make sense in our physical world, until you get to the quantum level, which has more challenges.
 

mhardy6647

Grand Contributor
Joined
Dec 12, 2019
Messages
11,214
Likes
24,175
Here is a list. The most notable by most people would be Steve Wozniak and the two guys who once lead Google's DeepMind project. Scroll down below the letter.

Steve Wozniak. The anti-Steve Jobs. ;)
Cool, thank you. I wasn't about to disable ad-blocking to look at the Fox News URL posted earlier. ;):facepalm:
 

MRC01

Major Contributor
Joined
Feb 5, 2019
Messages
3,424
Likes
4,030
Location
Pacific Northwest
50/50?
...
Not to get all loosey-goosey and right brained -- but, in a probabilistic Universe, does all even have a useful meaning? All would correspond to identically 100%, wouldn't it?
The odds vary, depending on the quantum mechanics problem you are solving. And calling it probability is close but not not exactly true, since quantum mechanics generalizes probabilities into amplitudes and extends them multi-dimensionally.

Scott Aaronson has a great lecture on this: https://www.scottaaronson.com/democritus/lec9.html
 

Blumlein 88

Grand Contributor
Forum Donor
Joined
Feb 23, 2016
Messages
20,522
Likes
37,050
Steve Wozniak. The anti-Steve Jobs. ;)
Cool, thank you. I wasn't about to disable ad-blocking to look at the Fox News URL posted earlier. ;):facepalm:
Most interesting to me is a professor at the University of the Sunshine coast in Australia. Never heard of him or the uni. Sounds like a cool place to be professor however. I picture a campus on the coast where you go and surf all day after classes. With the ubiquitous beautiful Australian ladies of course. :cool:

Looks like the campus is about 4 miles from a really good surfing beach. I'd have to be professor because I'd flunk out as a student.
 
Last edited:
Status
Not open for further replies.
Top Bottom