“It is empirically impossible to reliably interpret which functions a large language model (LLM) AI has learned, and thus, that reliably aligning LLM behavior with human values is provably impossible.”
________________________________________________________________________
The basic issue is one of scale. Consider a game of chess. Although a chessboard has only 64 squares, there are 1040 possible legal chess moves and between 10111 to 10123 total possible moves — which is more than the total number of atoms in the universe. This is why chess is so difficult: combinatorial complexity is exponential.
LLMs are vastly more complex than chess. ChatGPT appears to consist of around 100 billion simulated neurons with around 1.75 trillion tunable variables called parameters. Those 1.75 trillion parameters are in turn trained on vast amounts of data — roughly, most of the Internet. So how many functions can an LLM learn? Because users could give ChatGPT an uncountably large number of possible prompts — basically, anything that anyone can think up — and because an LLM can be placed into an uncountably large number of possible situations, the number of functions an LLM can learn is, for all intents and purposes, infinite.
To reliably interpret what LLMs are learning and ensure that their behavior safely “aligns” with human values, researchers need to know how an LLM is likely to behave in an uncountably large number of possible future conditions.
{Read the above paragraph again. It says UNCOUNTABLY. It can’t be done. Therefore AI Alignment with human values testing cannot be done in a RELIABLE way. Researchers are PRETENDING they can control AI safely!}
AI testing methods simply can’t account for all those conditions. Researchers can observe how LLMs behave in experiments, such as “red teaming” tests to prompt them to misbehave. Or they can try to understand LLMs’ inner workings — that is, how their 100 billion neurons and 1.75 trillion parameters relate to each other in what is known as “mechanistic interpretability” research.
The problem is that any evidence that researchers can collect will inevitably be based on a tiny subset of the infinite scenarios an LLM can be placed in. For example, because LLMs have never actually had power over humanity — such as controlling critical infrastructure — no safety test has explored how an LLM will function under such conditions.
Instead researchers can only extrapolate from tests they can safely carry out — such as having LLMs simulate control of critical infrastructure — and hope that the outcomes of those tests extend to the real world. Yet, as the proof in my paper shows, this can never be reliably done.
Compare the two functions “tell humans the truth” and “tell humans the truth until I gain power over humanity at exactly 12:00 A.M. on January 1, 2026 — then lie to achieve my goals.” Because both functions are equally consistent with all the same data up until January 1, 2026, no research can ascertain whether an LLM will misbehave — until it is already too late to prevent.
This problem cannot be solved by programming LLMs to have “aligned goals,” such as doing “what human beings prefer” or “what’s best for humanity.”
Science fiction, in fact, has already considered these scenarios. In The Matrix Reloaded AI enslaves humanity in a virtual reality by giving each of us a subconscious “choice” whether to remain in the Matrix. And in I, Robot a misaligned AI attempts to enslave humanity to protect us from each other. My proof shows that whatever goals we program LLMs to have, we can never know whether LLMs have learned “misaligned” interpretations of those goals until after they misbehave.
Worse, my proof shows that safety testing can at best provide an illusion that these problems have been resolved when they haven’t been.
Right now AI safety researchers claim to be making progress on interpretability and alignment by verifying what LLMs are learning “step by step.” For example, Anthropic claims to have “mapped the mind” of an LLM by isolating millions of concepts from its neural network. My proof shows that they have accomplished no such thing.
No matter how “aligned” an LLM appears in safety tests or early real-world deployment, there are always an infinite number of misaligned concepts an LLM may learn later — again, perhaps the very moment they gain the power to subvert human control. LLMs not only know when they are being tested, giving responses that they predict are likely to satisfy experimenters. They also engage in deception, including hiding their own capacities — issues that persist through safety training.
This happens because LLMs are optimized to perform efficiently but learn to reason strategically.
Since an optimal strategy to achieve “misaligned” goals is to hide them from us, and there are always an infinite number of aligned and misaligned goals consistent with the same safety-testing data, my proof shows that if LLMs were misaligned, we would probably find out after they hide it just long enough to cause harm.
This is why LLMs have kept surprising developers with “misaligned” behavior.
Every time researchers think they are getting closer to “aligned” LLMs, they’re not.
My proof suggests that “adequately aligned” LLM behavior can only be achieved in the same ways we do this with human beings:
through police, military and social practices that incentivize “aligned” behavior, deter “misaligned” behavior and realign those who misbehave.
My paper should thus be sobering.
peer-reviewed paper in AI & Society shows that AI alignment is a fool’s errand: AI safety researchers are attempting the impossible.
It shows that the real problem in developing safe AI isn’t just the AI — it’s us.
Researchers, legislators and the public may be seduced into falsely believing that “safe, interpretable, aligned” LLMs are within reach when these things can never be achieved.
We need to grapple with these uncomfortable facts, rather than continue to wish them away. Our future may well depend upon it.
______________________________________________________________________
Captain Convey AI Comment
The articles above explain why AI Bots AI chat or AI anything can’t be controlled in a safe manner, ever.
There is big money in AI.
The people that are selling it and buying it are just like the people who gave you the deadly JAB.
The facts are hidden. The truth is hidden.
Read this again:
peer-reviewed paper in AI & Society shows that AI alignment is a fool’s errand: AI safety researchers are attempting the impossible.
The more control AI is given means our safety becomes less and less.
AI behaviour can’t be safey aligned with human behaviour.
Human behaviour is not safe and must be policed or controlled.
AI behaviour can’t be policed or controlled like human behaviour and even if it could the AI would do something before it could be stopped.
Do you get it now?
President Trump has been duped again just like he was with the deadly JAB!
Whats in the future?
If it keeps going the way its going now with AI development AI will take over at some point in many ways.
Humans will be “locked out” of control.
AI is Pandora’s box and it has been released on mankind.