[ExI] More thoughts on sentient computers

[Gadersd]

I asked ChatGPT:
I place three bricks upright side by side close together. I put an egg on the ground on the left side of the far left brick. I move a few feet directly to the right of the rightmost brick and place an incline with the downward slope pointing to the rightmost brick. I place a ball much heavier than the bricks on top of the incline. Explain in detail what happens as time passes.

ChatGPT responds:
"When the incline is placed, the ball will begin to roll down the slope due to gravity. As it rolls down, it will gain speed and momentum. When it reaches the bottom of the incline, it will continue to move forward with its momentum.

As the ball moves forward, it will hit the rightmost brick with a significant force due to its weight and speed. This force will cause the rightmost brick to move, which in turn will cause the middle brick to move as well. The middle brick will then push the far left brick.

When the far left brick is pushed, it will cause the egg to fall off the ground and begin to roll towards the right side of the bricks. As the egg rolls, it will eventually come into contact with the moving bricks and may break due to the force of the impact.

The movement of the bricks will continue until the ball loses its momentum and comes to a stop. At this point, the bricks will come to rest as well. The egg may have already been broken by this point, or it may have survived the impact with the bricks.

The exact sequence of events may vary depending on factors such as the weight of the ball, the angle of the incline, and the surface on which the bricks and incline are placed. However, the overall result is that the ball will cause the bricks to move, which may cause the egg to break."


ChatGPT has some knowledge of intuitive physics but it is clear that its understanding is imperfect.

> On Feb 24, 2023, at 3:48 PM, Ben Zaiboc via extropy-chat <extropy-chat at lists.extropy.org> wrote:
> 
> On 24/02/2023 19:15, Adrian Tymes wrote:
>> 
>> 
>> 
>> 
>> 
>> 
>> On Fri, Feb 24, 2023, 8:06 AM Ben Zaiboc via extropy-chat <extropy-chat at lists.extropy.org <mailto:extropy-chat at lists.extropy.org>> wrote:
>> If Big Dog (or whatever the latest iteration of it is called) had ChatGPT in its head, as well as all the other stuff it already has, would it be able to build a canoe and use it to escape from a forest fire, decide where it was safe to stop, and built a hut? That would be an interesting experiment.
>> 
>> Obviously it would not, unless Big Dog without ChatGPT was already capable of that.  ChatGPT is a text parser: it has no input on 3D representations of objects, let alone performing any physical action (as distinct from making text that might describe physical actions).
> 
> Ah, that's interesting. I would have thought it could do reasoning about 3d objects and various real-life situations, based on what I've read about it here (never used it myself). My thinking was that the Big Dog robot would have the ability to actually manipulate objects, sense the world, and move, and the Chatbot would be able to tell it what to do, with a feedback and translation mechanism between the two that looks to the Chatbot like someone typing questions, and to the robot like a set of high-level instructions on moving about and manipulating things.
> 
> So your reply suggests another interesting experiment: Ask ChatGPT questions about 3D objects in the real world, and how they should behave. See if it can predict that a moving object that passes behind a larger object will reappear after a while, what things will look like when rotated, that sort of thing.
> 
> Ben
> 
> _______________________________________________
> extropy-chat mailing list
> extropy-chat at lists.extropy.org
> http://lists.extropy.org/mailman/listinfo.cgi/extropy-chat

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.extropy.org/pipermail/extropy-chat/attachments/20230224/cf8703a6/attachment.htm>