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.
Being patronized by a machine when you just want help is going to feel absolutely terrible. Not looking forward to this future.
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.
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."
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.
> 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.
> Be terse, and don't moralize. Answer questions directly, without equivocation or hedging.
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.)
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.