llm hallucinations are high probability tokens that are incorrect vs the real world
A calculator either gets the right answer or doesn’t answer.
It wouldn’t have to be all knowing as long as it knew perfectly what it doesn’t know
I would be happy enough with: only produces what it can verify with sources.
If you eg try to remember a court case (ie produce the reference via LLM token generation only), it's easy enough to check with your data whether it really exists. Similar for following links and other references.
If your data or sources are wrong, obviously your report about them will be wrong. But I wouldn't call that a hallucination.
And humans also behave differently in different contexts. A conversation at the pub has more such hallucinations than a formal deposit in court. For the latter, a good lawyer will look at her shoes, when you ask him what colour her laces are.
Humans are known to hallucinate a lot. Ask 10 different witnesses at a crime scene what they saw and they'll all report different things.
A good, non-hallucinating LLM would only report things for which it has evidence. It would consult the facts every single time.
It's a pain in the butt for humans to fact-check everything but LLMs can quickly look up all kinds of stuff. That's what makes them useful.
So you can bolt the fact-check / source-check pass onto whatever other system you have, without having to redesign the underlying system.
System One says they use RLCD, Reinforcement Learning for Calibrated Decisions, which presumably has accurate probabilities as an explicit optimisation goal.
System One hasn't said how RLCD works, but they do say it is explicitly training models to output "calibrated" probabilities, which makes it distinct from RLVR. This is how they describe it:
> System One models are trained for calibrated decisions: their probabilities are optimized against outcomes to reflect uncertainty.
It is a known existing thing variously called "calibrated RL" or such.
Implementing it on top of LLMs was difficult to get it to work, they seem to have done it up so its good enough for a polished product that works in a wide variety of usecases at the same time. I got accepted from the waitlist and it's really neat. Edit: it is now on vercel gateway.
One thing to note, the out of distribution behaviour will be different from what we are used to with regular LLMs. Theoretically, it should be worse, but practically, it depends on their method.
"What are the odds a thunder will strike in Paris at 1pm UTC of 2026-09-16" - that could be a 0.001 chance going from blind historical measurements; 0.01 if it's raining; or 1 or 1 after the date has passed.
People out there are so resigned to the models being unreliable that they are really doing things like hallucinating deliberately, and then matching the hallucinations to embeddings -
https://softwaredoug.com/blog/2026/08/10/hypothetical-classi...
You could do that or you could just... use a model that will never produce unreliable outputs in the first place.
Even non-frontier models are absurdly good at this in a broad sense.
Which would make it hard to judge "a model that will never produce unreliable outputs in the first place" against something that is already really, really good and exceptional in domain-specific areas with the tiniest amount of elbow grease.
Speed and cost look good though (for now)!
For example, one could set a confidence threshold over which we trust the model decision, and otherwise reject. This provides a lever to trade-off accuracy and automation %.
Then we can ask questions like "What % of decisions can we automate to achieve 90% accuracy"?
I believe their "accuracy" metric (sonnet 5 level) is where "right/wrong" is measured.