Models hallucinate plausible answers to why they did things. It might be true and it might be complete fiction.
Do you know anyone who actually reads and adheres closely to all of the documentation every time it's changed?
But now that I've been working on it a month and there's a lot of documentation, it's pretty clearly ignoring parts of the documentation and parts of the code. It will come up with some ridiculous statement about how something works, and I'll challenge it, and it'll admit I'm right.
It definitely reads more documentation than any programmer I've ever worked with (myself included) but because it doesn't have a memory other than the documentation, it still makes mistakes like that.
I haven't turned on "memory" or tried it with Codex, so I don't know how that'll change soon, though.
# See DOC-ITEM-NAME
DOC-ITEM-NAME.md
When referencing documents, always use the exact syntax See <TAG> - this is enforced by a lint on precommit
Depending on language I've seen this scale past multiple millions of lines of code, as long as you pair it with all of the linting and tooling that you can possibly build.
https://www.patheos.com/blogs/tippling/2013/11/14/post-hoc-r...
Don't remember that part though. It's been a few decades.
the inconsistency of LLMs is by far one of the biggest gripes I have with them. Closely related to their apparently deep desire to avoid following instructions.
I know these are both a byproduct of noise (which is somewhat tunable) and noise is inherent to these systems in a lode bearing way.
I still hate it. it’s holding the technology back. I don’t honestly see how we can safely or even successfully approach the idealized realm of AI without bypassing this problem, which to my understanding, probably means not using language models at all and trying a totally different approach. But I really don’t know much about machine learning, I’m a super novice compared to a lot on this website.
Sort of, actually. I think we humans actually have some intuition that we'd be more effective if our cognition were augmented more directly by machine strengths: the ability to run precise calculations, more memory, ability to look facts in some sort of knowledge graph.
I think we're on the right track, but instead of augmenting humans with machine strengths, we're building intelligence in hardware in a way where it can access that augmentation. Plus, then we can quickly distribute updates, run parallel instances, etc.
If intelligence is compression, and hallucinations are essentially loss, then as the models grow in size performance (at least as far as hallucinations) should reduce. Or we'll get things fast enough that we can afford to stop relying on model weights for memory and check an increasingly larger set of discrete facts as part of reasoning.
Right now, the models are making trade-offs. As compute grows, and inference gets faster, we can make fewer of those trade-offs and start to use the unique strengths of machines to fill the gaps we're seeing, I suspect.
When we do meta thinking about that process after the fact, two things happen. 1, we change our total “thought” by adding that meta thinking to it. And 2: it’s a very lossy process, because we don’t have very good data about what our brain or mind was actually doing during that first think and emotional factors are nearly always at play and even more complex.
Now for the more complex AI, the fragmented process of multiple agents and loops and reruns are pretty similar to that first think we do. At least structurally. But the meta think is where they differ. They have no emotion, but they also have even worse data about its own function. They constantly degenerate so I would argue their “changing the thought by thinking about it” factor is also generally way higher than ours.
Getting better at consistent/reproducible thinking, with many ‘steps’, that leaves good documentation of that thinking behind for future analysis, has to be one of the more important areas for the big flagships going forward. I’m certain that “what is this fucker doing and why” is the biggest pain point for AI researchers. Or the math, it’s usually the math.
But you’re correct in the general structure; they generally do the same post hoc analysis we do, just noticeably worse because of their opaque nature(even to themselves) and general degenerative instability.
Like
my shit dont stink > its not mine
If they've worked some minutes/hours/weeks on something and you ask them why did they do that, they will either answer honestly and truthfully, lie, or say "I missed that/didn't seem important so I just chose something at random".
None of these cases are similar to how AI works.
Sounds like the left hemisphere usually uses something from the right hemisphere to answer those questions and it can't do that if it's been cut off?
We know that our brains are capable of hallucinating due to substances (drugs), being asleep, brain damage (including split brain), hypnosis, etc. Just as RAM damage make your computer do weird shit. That doesn't mean it operates that way normally.
You can't just remove a huge part of a system and then assume that the whole system behaves the same.
If anything, biological comparisons should make us cautious. Consider the vast gulf that still exists between the finest artificial organ/limb versus the OEM parts of natural nanobots.
Yes, but the vast, vast majority of decisions you make either don't take place via an inner monologue, or include details that were not actively/consciously "thought" and reasoned with in your inner monologue.
And yet, when asked why you did something, you're not likely to respond "sorry, that decision was made subconsciously". Instead, you use your inner monologue to try to backfill in a reason why. That reason may be correct, or it may not be. You don't actually know, since you have new data that may be updating your own internal state as you try to rationalize it after the fact.
Perhaps up to 50% of people actually don't have an inner monologue, much like many have aphantasia where they can't actually see anything in their mind either.
It's not clear to me whether you're aware of a rigorous basis for your claim or you're just inferring based on what you think makes sense, but I can't help but wonder if it's the later, in which case regardless of the mechanism, the outcome certainly seems to resemble what happens with LLMs.
1. recall them correctly
2. say they can't recall them
3. recall them incorrectlyWhile it did help the epilepsy, their brain was essentially two brains controlling two halves of the body. With one controlling speech. There were experiments where one eye was shown some instruction text, the corresponding hand performed that instruction, and when asked why they dix that action, the speaking half just made up some plausible, yet completely wrong reason, just like an LLM.
If you build a robot where a pressurized hose leaks causing fluid to destroy part of the circuitry, we don't praise it as progress towards the human ideal of having brain aneurysms. A similar failure-path is not a reliable indicator of a similar success-path.
Isn't it awesome we built machine that does the exact same thing, but even faster and more often? /s
You can extend this further by using an adversarial agent trying to find mistakes in the other instance's logs in a loop where a 3rd neutral agent weighs the claims of the other two. This is also just another step in reducing error, it does not guarantee elimination of such errors. The latter is an impossible guarantee, even for humans.