Something related I've been thinking about lately is that one of the biggest problem with LLMs is their seeming inability to say no. Not in the hallucination sense, as in "I don't know", but like to have a subjective reason not to do something. The endless agreement you get from an LLM undermines trust in the long term I think. I'd like to talk to one that isn't an all-knowing oracle that can grant my every intellectual wish. (Or maybe what I'm asking for is just... a human, lol).
> inability to say no
One word that few wealthy people ever hear, is “No.” It has a pretty significant effect on their worldview. Even the most reasonable, well-informed, well-intentioned, wealthy folks can have their thinking affected.
When every silly, should-be-smothered-in-the-crib idea gets enthusiastically endorsed by your entourage, it’s easy to lose the ability to self-regulate. I’ve watched it happen, numerous times, as acquaintances and friends have become more successful.
Obsequious LLMs are leveling the field. Less wealthy folks now have the chance to lose their ability to self-regulate, just like rich folks.
What net worth threshold do you consider wealthy?
I don't know. It probably varies. SV wealthy is quite different from Appalachia wealthy. It's that point, where people start worshipping your money. Some wealthy folks also make a point of showing off their wealth, so it starts earlier, for them.
Also power. You see the same thing happen with managers that dismiss criticism, and have the power to make it stick.
[delayed]
Feels exactly the way my 2 year old behaves.
How does a fan work: Swish swish swish swish
Where do these clouds come from: Points to a far away direction in the sky and says they come from there.
Who does all these roads, trees and environment belong to? It all belongs to me. Obviously.
They have an answer ready for every question you throw at them and they will answer it with absolute certainty. I will have to wait and see at what age does the concept of "I don't know" develop.
The difference between your two year old is that an LLM gives useful information.
Yesterday I decarboxylated some weed buds in preparation of making a cannabis tincture using the QWET method. Curious how Claude would respond, I asked how to do it.
It walked me through the process and gave accurate, nuanced answers.
Let me know what your 2 year old thinks I should do.
Gemini estimated that male cannabis plant leaves I decarboxylated will have negligible thc content and give me mild relaxation at best, the real effect was it was the highest I've ever been.
That is in the training data. Confidently and correctly answering in-distribution questions (possiibly with a tool call) is expected by now.
Aren't you missing OP's point entirely? Which is: If the LLM didn't have useful information it would still give you an answer... Helpful or not.
Not really, since any LLM will answer all those questions competently. It's a known fact that LLMs sometimes are wrong and hallucinates an answer, but this is exceedingly rare. Having access to a decent LLM is like having an expert with me. Are they always right? No, but the analogy with a two year old simply doesn't hold up.
> Since any LLM will answer all those questions competently
That's false. The LLM will only answer competently if it was trained on that data; and if it has enough data to make the correct connections between your question and the "correct" answer.
In the case of this article they're specifically saying the LLM has limited training.
There is the art of saying no: https://dl.acm.org/doi/10.5555/3737916.3739489
It is possible to create (subjective) reasoning traces like https://huggingface.co/datasets/Bachstelze/ethical_coconot_6...
And train or adapt a model to it: https://huggingface.co/Bachstelze/olmo-7b-ethical-reasoning-...
This is just a little proof of concept, though it is maybe the direction you are looking for?!
It's interesting because i'm kicking the tires on the top tier stuff for a month (because it's expensive as fuck but I need to know where the ceiling is).
I have actually gotten "hey i don't think this is a good idea, here's why" as feedback from at least Opus. It WILL still do it if I just demand stupidity (and hell i've been right, which is another topic entirely) but it has given me more confidence this can be a useful tool in the right spots.
That said I probably don't need the top tiers (metrics at least confirm that) and I'm guessing that's specifically because I was working in coding. Most were worded in a "is this a good idea" framing which probably helped, but at least once I said 'lets use this library/method" and it gave a decent argument on why that was basically redundant without prompting.
I still struggle to see the price point panning out.
Two angles for thought. 1) If an LLM says, "I don't know" its underlying data said it as well. 2) Many system prompts use something along the lines of, "you are a helpful assistant" which may be counter to stating something like, "I don't know."/has a low likelihood of appearing after the system prompt.
Regardless the frontier model considered, we're certainly in a "know-it-all" era.
Maybe the sort of introspective prompt-response is difficult to implement when it could limit/contaminate future improvement. I speculate it's easier to correct a "confidently incorrect" model than a "I don't know" model. A confidently incorrect model response >=0% correct over a 0% correct (I don't know).
Maybe "I don't know" is a model cognito hazard of sorts when many queries can lead back to the response. Maybe future Turing tests will use this sort of introspective evaluation. Who knows? I don't :)
> 1) If an LLM says, "I don't know" its underlying data said it as well.
Nope. Emergent behavior exists and at this point dominates LLM behavior. Most of the stuff LLMs say they never learned (they are, always, imitating many different sources at the same time)
... which imho is exactly what humans do.
I think that is an issue. Also, the ability to quickly build any idea might not be such a great thing. Not only do we probably all prefer things of quality that were made with care but some ideas also just shouldn't be built.
Over the last 3 years I've seen projects where I thought, pretty obviously that's a bad idea. But, because LLMs don't say no and can just be pushed to build it anyway, the people building them might never learn that or learn why.
It's nice to be able to have a quick prototype or mvp. But if we never hit friction or something not working out, we never learn or have to come up with a creative solution.
Now, the LLM might seem incredibly intelligent (relatively speaking) and also creative but let's not forget that all is based on its training data. I simply don't believe it can ever be omniscient or that the companies training it are careful enough when doing so.
There’s still friction, it simply moved to another stage, and as such, people will need new learning and feedback mechanisms to understand what did/didn’t work.
I’m using ChatGPT and started to notice that lately it answers my prompts starting with „Yes” even if my question was open. As if the first token gets injected and the LLM is left to finish the response in a sensible way, often ending up with some form of „Yes, but not really”.
You should not need it to say no.
You can get just as good information by asking its thoughts for and against some issue.
That doesn't force it to stop being sycophantic; in fact it actually exploits sycophancy to give you what you want.
My experience with opus/fable is somewhat different - they CAN reject something, but it has to be phrased very deliberately.
It's a bit annoying honestly. I'm always very careful to be incredibly neutral on the direction of a request, and I'd say 10% are knocked back on on valid grounds, which is great.
On occasion I accidentally say "let's do this" and it blindly goes and does it - I spent 2 days undoing something I built that was just a truly awful idea, because I accidentally phrased it lightly as a request, not a discussion!
I have a similar experience with GPT 5.6 sol.
Nowadays I often prompt like "I heard there is also this different direction, what do you think about that?"
Another thing I do is asking the agent to make a decision matrix for choices. It's useful to discuss, give feedback on, and signals that it's a discussion, not a request for a particular direction.
It's then also easy to say: create a prototype for multiple directions so I can compare the solutions.
That way I choose the problem, I choose the solution, but the agent can help me discover solutions, make tradeoffs visible, and implement solutions.
Agreed, it is abolutely an issue. It is quite difficult to find an optimal solution to some problem when every considered new idea is ”definitely the right shape”.
This is an active area of research to inject humility into llms in order to create some kind of knowledge boundary. You can look this paper from nouswise https://arxiv.org/html/2604.17843v1 and the product build on top it to try the humility.
I've been wondering whether that is a feature of the foundation model or whatever finetuning they do on top. I remember this from the earliest versions of (pre Chat-) GPT I've been using, which would suggest it's a feature of the foundation model. But I don't really understand why. Something that's been trained on StackOverflow and BB forums, among other things, should have seen a ton of examples of answer refusals.
> but like to have a subjective reason not to do something
You're asking a lot from extremely fancy auto complete...
True, but fancy autocomplete keeps exceeding my expectations in what it can do, so why not this one!
The model providers could randomize the system prompt to make it say no 2.36% of the time, automatically tuned up or down depending on user feedback.
Maybe that'd work, but I think it'd come across too mechanical. If it was going to refuse something it'd need to be congruent with its "personality" I think.
They've tried, and then seen the drop it results in on poorly designed benchmarks where confidently bullshitting gets you ahead of the rest, and said no thanks. As long as we compare models in ways that rewards it, nothing will change.
There's also a second aspect to it, just in terms of RLHF mechanisms. If you've ever experimented with VLA models (i.e. vision input + text task = robotic arm motion output), they tend to need all the training examples of the robotic arm being motionless removed entirely, otherwise the model simply learns that staying still is rewarded and proceeds to never do anything at all. You successfully train the laziest bot in the universe. I wouldn't be surprised if something similar happens to LLMs if reinforcement learning is involved in the instruct tuning process. If no is a valid answer, why ever do anything?
Pointing the finger at RLHF is basically right. It removes variance from model outputs compared to base model. That makes each output more predictable and more correct on average, but across trials it repeats the same thing.
It's relevant to AI safety. If you have a diversity of outputs, the AI will agree to hack the bank 0.1% of the time regardless. If you have a uniformity of outputs, in most contexts the AI will hack the bank 0% of the time, but in certain odd contexts, all AIs will work together to hack the bank 100% of the time.
You've hit on an important insight.
After an answer, try asking it why, over and over. It's a machine to give answers, not explanations. A magic 8 ball. https://news.ycombinator.com/item?id=49307396
People smarter than me have a habit of getting me to see things without telling me. They ask the right questions.
LLMs, incidentally, respond in a similar pattern in my experience.
Yep, agree, very succinct way of describing my issue with it.
[dead]
It can, just use Grok.
"no"