1
Physics, Astronomy & Cosmology / Re: What is the exact cause of the time dilation of the twin?
« on: 29/11/2024 00:26:06 ». Having never used supposed "AI"(no intention of doing so-you can't teach an old dog new tricks!), I am in a weak position to criticise. I have seen some atrocious rubbish in replies to questions posed by others and a high degree of suggestibility. In response to a question that requires a blunt "NO", answers will often digress into unsubstantiated speculation with the seeming aim of perpetuating the discourse rather than delivering a straightforward answer.This is very perceptive. Yes, the answers always seem agreeable, and if you protest a correct answer by asserting your own sufficiently plausible rubbish, none of the LLMs seem capable of telling you that it's still rubbish. It might seem a bit skeptical, but it will encourage you to explore your line of thinking rather than point out where it contradicts evidence or contradicts itself.
I didn't want to tell copilot that its answers were rubbish. I had hoped that it would figure it out itself after I pointed out inconsistencies in its replies.
We may not need forum moderators in the future, an LLM can analyse and critque the work produced by the forum users LLM well enough.Moderators are needed to moderate, to recognize and deal with posts not complying with the rules. Being correct is more of a job for site experts, be they moderators or not.
I'm no expert in pretty much any subject, but I know enough to take apart a lot of answers I see from AI.
Quote
(I copied and pasted the reply @Halc obtained from Gemini).....Actually, Hamdani provided replies from both chatGPT and gemini. I just copied his quotes so I could color them
My replies below are replies to chatGPT apparently agreeing with much of what gemini had to say..
Quote
You say that "spacetime is curved due to the acceleration" in an accelerated frame..... It would be better to mention that acceleration causes the perception of curvature, or locally mimics gravitational effects due to the equivalence principle.But that isn't right. There is no curvature locally, so there cannot be any local perception of it. In the non-local case, most of the effects are due to the accelerated frame. it is quite hard to distinguish curved spacetime from flat since all the effects are present in both, but differently.
For instance, I am under proper acceleration of 1g and dangle a clock on a long rope. In both cases the clock on the rope will run objectively slower, so that effect is not due to curved spacetime. But the two cases differ a bit for how much slower since they differ. Nearby, it differs but a little, but for a gravitational field of a small mass, it can differ a lot over not that much distance.
The equivalence principle does not suggest any of this
Quote
In an accelerating reference frame, spacetime itself doesn?t curve in the same way...It doesn't curve at all. Spacetime curvature is objective, not a coordinate effect, and an accelerated frame is just a coordinate choice. I would have immediately grilled gemini on this point, but I have no access to it.
Quote from: Eternal Student
students using LLM to write the essays and someone else using a LLM to mark and grade them.They get what they deserve if they commit the same sins. Education should devolve into GIGO. Nobody should pay for any pseudo-education implemented in this manner.
I talked to my AI about black holes and got Newtonian answers in response. It had no clue.
Thought of another one: Sagnac effect is a favorite empirical disproof of anything Einstein. Let me have a go:
Does light travel west faster than it does east?
Quote
Light travels at a constant speed in a vacuum, ... This speed remains the same regardless of the direction in which the light is traveling, be it west, east, or any other direction.
The notion that light could travel faster in one direction over another doesn't hold up according to our current understanding of physics. The speed of light is influenced by the medium through which it travels (such as air, water, or glass), but not by the direction.
So if I create a vacuum tunnel and some mirrors around the world and shine a pulse in both directions, both pulses will return to the origin spot at the same time?
Quote
Yes, exactly! In your vacuum tunnel setup, if you shine a pulse of light in both the west and east directions simultaneously, both pulses would return to the origin at the same time. The speed of light in a vacuum is constant and does not depend on the direction of travel.
This constancy of the speed of light is a cornerstone of Einstein's theory of relativity and is true regardless of the motion of the source or the observer. It?s one of the fascinating and sometimes counterintuitive aspects of the way our universe works.
So the Sagnac effect disproves relativity then? It predicts that west and east light go different speeds and measurement of this difference is used to detect absolute rotation. Sure, most Sagnac devices have a far smaller circumference than a planet, but the principle is the same
Quote
...The Sagnac effect occurs in rotating reference frames, such as a rotating disk or the surface of a spinning planet like Earth. In these scenarios, if you send two beams of light in opposite directions around a loop, they will take different amounts of time to complete the loop.Not in the context of Sagnac. In the context of what actually happensQuoteSo the two pulses do take different times to come back to the emitter then?Yes, in the context of the Sagnac effect within a rotating reference frame, the two pulses of light would indeed take different amounts of time to return to the emitter.
Quote
Let's break this down in the context of what actually happens with light pulses and rotation.
If you set up a vacuum tunnel with mirrors and shine a pulse of light in both the westward and eastward directions, the two pulses would indeed take different amounts of time to return to the origin if the system is rotating.
So I didn't color anything, but it didn't take much to get it to contradict itself. The LLM did not take into account the rotating frame of reference in the first reply because despite the real-Earth scenario, I didn't word the question in a way that drew attention to the fact that we're working with a rotating frame, despite the fact that west and east are not even defined on a planet that doesn't rotate.
I did word the one query as an attempt to discredit relativity like so much training material attempts to do, and it at least didn't take that bait. I partly wanted to see if I could lead it down a false path if it looked like it was my purpose to do so.
The copilot replies were edited heavily, cutting it down to actual replies, and cutting out all the educational stuff it tried to add on, and of course all the congratulatory stuff at the end about how perceptive my questions are. It tacks that on to ever single reply in some form or other.
The following users thanked this post: paul cotter