Ghideon

No, the LLM does not do that. But there might be surrounding software that performs such actions*. The input to the LLM can then be the user prompt + whatever additional information the surrounding application(s) supply. (There's a lot of details and nuances to be added; I'll wait for Prajna to avoid going off topic) *) For instance a chatbot that behind the scenes access a web search or some stored information such as chat history. The user does not necessarily see it as anything separate.

As far as I know an LLM is static; a fixed set of weights and definition (transformer layers, attention heads, activations). Once trained, the LLM’s weights and it's definition do not change at inference time. So when you say "alter" do you refer to fine-tuning, training, destillation or some other means of altering the LLM? Or do you by "LLM" mean the complete system with LLM + one or more surrounding applications may maintain state (conversation history, retrieved documents, random seeds ...) and possibly integrate with other software systems?

Ok, take your time and read through the question, the quotes and the answer. I think it is rather obvious so I leave it as an exercise. I prefer to discuss here on the forum where other members can correct any misunderstandings or mistakes on my part.

Ok. But what you wrote contradicts the quotes I asked about.

What is this weird format? Copy/paste? (looks like markdown, byt why?)

Thanks, but I posted two quotes from your explanations; please explain how they are not contradictory.

Missed that question. I think the issue is quite a bit bigger than finding suitable words. Assuming the goal is to come up with an acceptable model for "pre-geometry" with properties such as: Recovers known physics Mathematically rigorous Avoids metaphysical slippage Then (with my background and current level of knowledge) I would probably need to do at least the following: 1. Study Philosophy Purpose: Understand scientific realism, instrumentalism, model-theoretic realism, ... Why: need conceptual clarity to avoid building metaphysical assumptions into a pre-geometric theory that claims to avoid them. Also need to understand the "big picture" where this kind of science fits into other areas and their solved or unsolved questions. 2. Study Mathematics Purpose: Build mathematical fluency in both quantum and geometric formalisms. Why: Pre-geometric models, as far as I know, often rely on non-standard mathematical structures that I think removes many standard tools. 3. Study Physics; the Established Theories Purpose: Gain full technical command of existing frameworks. Why: understand what needs to emerge from the model 4. Study Pre-Geometry: History, Branches, Key Issues Purpose: Avoid reinvention and engage existing debates. Understand known pitfalls; Recovering Lorentz invariance from discrete models, Matching semiclassical limit to GR, Preserving unitarity and causality 5. Study current Status of the Field, for instance researchers* such as Leonard Susskind Juan Maldacena Carlo Rovelli, Abhay Ashtekar Rafael Sorkin, Fay Dowker Renate Loll, Jan Ambjørn Daniele Oriti Brian Swingle, Mark Van Raamsdonk Programming and Simulation (One of the few areas where I to some degree could rely on existing knowledge) I believe (but I do not know) that numerical models, simulations and tests are needed I estimate this would span several years of full time work. The result is a knowledge level that allows one to choose between competing models and where to try to contribute. Part of it may require re-location and looking for a position at a university or similar institution. As far as I know no generally accepted and tested model exists for "Pre-spacetime" or "pre-geometry" despite all the efforts by researchers so far this phase of the work could be a life-long endeavour. I also do not expect the result to contain any "chortons". Note: this post is not meant to intimidate, it's just an honest attempt at describing the situation. Also, I do not think any current LLM or chatbot could significantly reduce the time and effort required. *) list from a quick googling of the scientific concepts I think is relevant.

and Using seconds (unit s-1) implies time? But before time there was no time (Note: I can live with a few spelling and/or grammar errors; can you post an explanation that is not produced or supported by an "AI ChatBot"?)

Your conclusion seems reasonable.

That may not work so well if it contains text; searching, quoting or highlighting does not work well in the forum.

As I said earlier: look up ontological bootstrapping

You have not provided any coherent model for the emergence of spacetime. Building new speculations (for instance about expansion) on top of that does not work.

Today I learned about the concept ”non-algorithmic” in relation to computability, Turing machines and Gödel. I don’t remember seeing that concept when studying the ”opposite” (algorithms as part of computer science); my focus was more on software engineering. I think this new knowledge will help me navigate when reading AI related material. Especially philosophical and more speculative stuff. (As always thanks @joigus for using words, concepts and examples that trigger searching, reading and learning)

Quick example: the post where the quote above is taken from. (If you understood “ontological bootstrapping problem” you would have spotted it before posting?)

To better understand the clear critiques other members have posted you may want to look up and read about “ontological bootstrapping problem” (using tools that can’t logically exist at the model’s starting point). That may give you valuable insight about the overall problems with the explanations you post. Also, there is a risk that AI usage reinforces this. The LLM does not contain any non-spacetime model about ”chortons” and will likely fall back on spacetime terms, even if they logically does not apply.

Layman question: Without units in mathematics, how do you distinguish between radians and degrees in geometry?

Testing an editor \[ \frac{\pi}{4} = \sum_{k=0}^{\infty} \frac{(-1)^k}{2k+1} = 1 - \frac{1}{3} + \frac{1}{5} - \frac{1}{7} + \cdots \] \[ 4* \sum_{k=0}^{\infty} \frac{(-1)^k}{2k+1} \]

I use the sandbox section in this forum to test mathematical formulas and latex.

That is absolutely a possibility! @swansont commented on that and a similar scenario in a recent thread https://scienceforums.net/topic/136269-flood-of-spam-12th-july-2025-why-would-someone-do-that/#findComment-1293102

I do not think that, sorry if you got that impression from my post. If you share what you have got so far I may comment on AI aspects of the progress.

I agree! The comment triggered my curiosity (even if not directly related): Can moderators see if forum software blocked any spam associated with the same burst of activity? I'm wondering if the reason for the spam is to stress the forum software, for instance Reverse engineer thresholds: tweak link count, pictures vs text to see what just slips through. Leverage shared platforms: a bypass on one forum could works unchanged on others. ML probing: make tiny edits to find variants that evade the same spam filter model.

It seems there may be a misunderstanding about how generative AI works? It does not infer; it predicts tokens based on statistical correlation, not on causal understanding. Adding a phrase like “be brutally honest” may change the tone of the response but it doesn’t make the output more scientifically valid or rigorous. An analogy may help to illustrate: Imagine someone is unaware of the laws of thermodynamics and they interact with ChatGPT to develop equations for usage in physics. The resulting equations may be mathematically correct but when applied to physics the equations could describe perpetual-motion machine ("over-unity" device). Since the user has not studied thermodynamics they can neither include relevant constraints in their prompts nor identify issues in the output. ChatGPT, in turn, is not guaranteed to flag such issues even if it has seen training material stating that perpetual motion is impossible. Prompting it to be “brutally honest” won’t fix this. Now, scale up: "quantum gravity" or "Photon Collapse as the Origin of Gravitons" is orders of magnitude harder. Neither you nor ChatGPT have any real understanding of what a valid graviton theory would look like. ChatGPT may produce superficially plausible equations but you can't tell if they're meaningful or nonsense. (That said, using generative AI in combination with other metods and sources can probably be helpful when studying, but locating scientific papers and discussing such aspects of AI usage is probably better in a separate thread)

Regarding AI* in context of your idea What "AI" did you use? What method do you apply to distinguish nonsense from useful scientific progress? If you use generative AI maybe you could share your prompting strategies for feedback. Since you seem to develop a novel idea, how does the model get trained on these new, and to the model, unknown concepts? Note that a "correct" output from an established language model, if it was trained on established physics, would be scepticism. Depending on the prompts the model could, similar to the experts here, question the basis of the idea. But it could also generate nonsense physics that statistically matches your input and possibly guide you in the wrong direction. If the model is a state of the art mathematics capable model it is quite possible to get mathematically sensible output that makes no sense in physics. My point: Using "AI" nowadays is easy. Correctly applying AI in the context you have described is hard; you would need to study both physics and AI. *) which is closer to my area of knowledge than particle physics

Just a quick note from someone who's been around a while: I tend to approach comments like that a bit differently: with curiosity. When someone knowledgeable, like @joigus, casually sets something aside within their area of expertise, and I can’t immediately follow why, I take it as a sign that they’re drawing on insights or theories I might not yet be familiar with. That usually prompts me to ask: What am I missing since this seems straightforward to them? How could I go about understanding that better given that I already have a basic grasp of the topic? And from there: Am I curious enough about this particular subject to explore it further?

Hello! I am unable to follow your logic. Please explain what happens if someone creates a paradox by time travel from some other identical universe and arrives in this universe where we have this conversation. They prevent you from posting the opening post above*. What will happen in this universe according to your idea? Your idea seems to say the future is “predetermined” but also says your arrival instantly changes that future. Those two statements cannot both be true as far as I can tell. *) for instance by creating the grand father paradox in this universe