11–20 of 399 posts
Technically not, we just don't have it high enough
You're doing exactly what you said you wouldn't though. Betting that network requests are more reliable than an LLM: fixing probability with more probability.
Not saying anything about the code - I didn't look at it - but just wanted to highlight the hypocritical statements which could be fixed.
Earlier quoted context omitted.
but the acceptance criteria becomes binary and deterministic. Unfortunately, the use-case for AI is often where the acceptance criteria is not easily defined --- a matter of judgment. For example, "Does this patient have cancer?". In cases where the criteria can be easily and clearly stipulated, AI often isn't really required.
You're 100% right. For a "judgment" task like "Does this patient have cancer?", the final acceptance criteria must be a human expert. A purely deterministic verifier is impossible. My thesis is that even in those "fuzzy" workflows, the agent's process is full of small, deterministic sub-tasks that can and should be verified. For example, before the AI even attempts to analyze the X-ray for cancer, it must: 1/ Verify…
We are trying to fix probability with more probability. That is a losing game. Thanks for pointing out the elephant in the room with LLMs. The basic design is non-deterministic. Trying to extract "facts" or "truth" or "accuracy" is an exercise in futility.
Exactly. We treat them like databases, but they are hallucination machines. My thesis isn't that we can stop the hallucinating (non-determinism), but that we can bound it. If we wrap the generation in hard assertions (e.g., assert response.price > 0), we turn 'probability' into 'manageable software engineering.' The generation remains probabilistic, but the acceptance criteria becomes binary and deterministic.
Earlier quoted context omitted.
Exactly. We treat them like databases, but they are hallucination machines. My thesis isn't that we can stop the hallucinating (non-determinism), but that we can bound it. If we wrap the generation in hard assertions (e.g., assert response.price > 0), we turn 'probability' into 'manageable software engineering.' The generation remains probabilistic, but the acceptance criteria becomes binary and deterministic.
I don't agree that users see them as databases. Sure there are those who expect LLMs to be infallible and punish the technology when it disappoints them, but it seems to me that the overwhelmingly majority quickly learn what AI's shortcomings are, and treat them instead like intelligent entities who will sometimes make mistakes.
The overwhelming majority of what?
LLM provides inputs to your system like any human would, so you have to validate it. Something like pydantic or Django forms are good for this.
Earlier quoted context omitted.
Exactly. We treat them like databases, but they are hallucination machines. My thesis isn't that we can stop the hallucinating (non-determinism), but that we can bound it. If we wrap the generation in hard assertions (e.g., assert response.price > 0), we turn 'probability' into 'manageable software engineering.' The generation remains probabilistic, but the acceptance criteria becomes binary and deterministic.
but the acceptance criteria becomes binary and deterministic. Unfortunately, the use-case for AI is often where the acceptance criteria is not easily defined --- a matter of judgment. For example, "Does this patient have cancer?". In cases where the criteria can be easily and clearly stipulated, AI often isn't really required.
Earlier quoted context omitted.
Exactly. We treat them like databases, but they are hallucination machines. My thesis isn't that we can stop the hallucinating (non-determinism), but that we can bound it. If we wrap the generation in hard assertions (e.g., assert response.price > 0), we turn 'probability' into 'manageable software engineering.' The generation remains probabilistic, but the acceptance criteria becomes binary and deterministic.
> We treat them like databases, but they are hallucination machines. Which is kind of crazy because we don't even treat people as databases. Or at least we shouldn't. Maybe it's one of those things that will disappear form culture one funeral at a time.
Anyway, I've written a library in the past (way way before LLMs) that is very similar. It validates stuff and outputs translatable text saying what went wrong.
Someone ported the whole thing (core, DSL and validators) to python a while ago:
https://github.com/gurkin33/respect_validation/
Maybe you can use it. It seems it would save you time by not having to write so many verifiers: just use existing validators.
I would use this sort of thing very differently though (as a component in data synthesis).
We are trying to fix probability with more probability. That is a losing game. Thanks for pointing out the elephant in the room with LLMs. The basic design is non-deterministic. Trying to extract "facts" or "truth" or "accuracy" is an exercise in futility.
"Willison’s insight was that this isn’t just a filtering problem; it’s architectural. There is no privilege separation, and there is no separation between the data and control paths. The very mechanism that makes modern AI powerful - treating all inputs uniformly - is what makes it vulnerable. The security challenges we face today are structural consequences of using AI for everything."
- https://www.schneier.com/crypto-gram/archives/2025/1115.html...