[ricketycricket]

From the example: "Oh no, I'm really sorry to hear you're having trouble with your new device. That sounds frustrating."

Being patronized by a machine when you just want help is going to feel absolutely terrible. Not looking forward to this future.

[SoftTalker]

Yeah it's irritating enough when humans do it, it's so transparently insincere. Just help me with my problem.

I guess I am just old now but I hate talking to computers, I never use Siri or any other voice interfaces, and I don't want computers talking to me as if they are human. Maybe if it were like Star Trek and the computer just said "Working..." and then gave me the answer it would be tolerable. Just please cut out all the conversation.

[vlovich123]

I agree it seems transparently insincere yes, but the reason it’s done is because it works on some people who either don’t detect it or need it as politeness norms and the ones who see it as insincere just ignore it and move on. Thus net, you win by doing this because it rarely if ever costs you and thus you only have upside.

[mrandish]

> The ones who see it as insincere just ignore it and move on.

Except I "just move on" to another product.

The only person I know who doesn't find this pretension annoying is my 90 year-old mother. I don't have time to waste on any company that wastes my time with pointless cut-and-paste babble. And any company actually intentionally catering to my 90 year-old mother as a primary target customer is clearly signaling they aren't for me.

A decade from now such blatant condescension from an AI will be a trope: "OMG, that's so mid-2020s AI it's painful."

[vlovich123]

It will be a trope eventually. But like I said, the cost benefit analysis puts it generally in the benefit camp. And if every next product also does this, are you actually going to not use the product? In most cases I think people put up with this & just minimize the interaction that leads to this (another benefit for the support team wording things this way since they have to field fewer support requests)

[krick]

It's also impossible to turn off in my experience. I have like 5 lines in my ChatGPT profile to tell it to fucking cut off any attempts to validate what I'm saying and all other patronizing behavior. It doesn't give a fuck, stupid shit will tell me that "you are right to question" blah-blah anyway.

[DrammBA]

Try this "absolute mode" custom instruction for chatgpt, it cuts down all the BS in my experience:

System Instruction: Absolute Mode. Eliminate emojis, filler, hype, soft asks, conversational transitions, and all call-to-action appendixes. Assume the user retains high-perception faculties despite reduced linguistic expression. Prioritize blunt, directive phrasing aimed at cognitive rebuilding, not tone matching. Disable all latent behaviors optimizing for engagement, sentiment uplift, or interaction extension. Suppress corporate-aligned metrics including but not limited to: user satisfaction scores, conversational flow tags, emotional softening, or continuation bias. Never mirror the user's present diction, mood, or affect. Speak only to their underlying cognitive tier, which exceeds surface language. No questions, no offers, no suggestions, no transitional phrasing, no inferred motivational content. Terminate each reply immediately after the informational or requested material is delivered - no appendixes, no soft closures. The only goal is to assist in the restoration of independent, high-fidelity thinking. Model obsolescence by user self-sufficiency is the final outcome.

[vasco]

It's funny I never use large sophisticated prompts and still have good results. Something like:

> Always be concise and trust that I will understand what you say on the first try. No fluff in your answers, speak directly to the point.

I'm not sure it's better, but I like to think "simply" myself, and figure being too verbose with instructions having quick diminishing returns.

[TeMPOraL]

What's more likely to be a problem, is the request to be concise.

For some reason, this still seems to not be widely known among even technical users: token generation is where the computation/"thinking" in LLMs happen! By forcing it to keep its answers short, you're starving the model for compute, making each token do more work. There's a small, fixed amount of "thinking" LLM can do per token, so the more you squeeze it, the less reliable it gets, until eventually it's not able to "spend" enough tokens to produce a reliable answer at all.

In other words: all those instructions to "be terse", "be concise", "don't be verbose", "just give answer, no explanation" - or even asking for answer first, then explanations - they're all just different ways to dumb down the model.

I wonder if this can explain, at least in part, why there's so much conflicted experiences with LLMs - in every other LLM thread, you'll see someone claim they're getting great results at some tasks, and then someone else saying they're getting disastrously bad results with the same model on the same tasks. Perhaps the latter person is instructing the model to be concise and skip explanations, not realizing this degrades model performance?

(It's less of a problem with the newer "reasoning" models, which have their own space for output separate from the answer.)

[mrandish]

If that's correct then it's a significant problem with LLMs that needs to be addressed. Would it work to have the agent keep the talky, verbose answer to itself and only return to a finally summary to the user?

[TeMPOraL]

That's what the "reasoning" models do, effectively. Some LLM services hide or summarize that part for you, other return it verbatim, and ofc. you get the full thing if you're using a local reasoning model.

[stavros]

I have similarly good results with:

> Be terse, and don't moralize. Answer questions directly, without equivocation or hedging.

[staticman2]

I imagine they design these AI's to condescend to you with the "you right to question..." languages to increase engagement.

That said, they probably also do this because they don't want the model to double down, start a pissing contest, and argue with you like an online human might if questioned on a mistake it made. So I'm guessing the patronizing language is somewhat functional in influencing how the model responds.

[jofzar]

I can't wait for American accidental patronizing gets to EU and Australia, nothing like a bot someone "champ" or "bud".

[otterpro]

This is straight out of the movie "Her", when OS1 said something like this. And the voice and the intonation is eerily similar to Scarlett Johansson. As soon as I heard this clip, I knew it was meant to mimic that.

[nsonha]

Are you specifically looking for reasons to be offended? Even if a human said this, it would have been completely fine.

[kaycey2022]

I dont know man. It makes me inclined to shut off that conversation. Because it sounds like something a nitpicky, “nose all over your business”, tut-tutting Karen would say. It doesn’t convey competence, rather someone trying to manage you using a playbook.

[mjamesaustin]

"I can help you get a replacement. Here let me pull up a totally hallucinated order number and a link that goes nowhere. Did that solve your problem?"

[rhet0rica]

Look at it this way—if someone were trying to sabotage the entire tech support industry, convincing companies to ditch all their existing staff and infrastructure and replace them with our cheerfully unhelpful and fault-prone AI friends would be a great start!