Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

"Don't You Just Upload It to ChatGPT?"

correresmidestino.com

Post reply on HN
Print view View original

281–290 of 408 posts

Re: "Don't You Just Upload It to ChatGPT?"

#281

Post by not_a_bot_4sho »

toddmorey wrote: post #135
Aurornis wrote: post #118

Earlier quoted context omitted.

> This is why I use AI for all my medical questions and doctors use AI to write software, and we both smirk at the quality the other person is getting from it. There is an interesting third group emerging: People who acknowledge the quality problem, but think they can deal with it by applying more AI to the output. This takes the form of people who spin up a lot of "agents" and give them personalities like security d…

I always imagine the model rolling its silicon eyes when it’s assigned a personality (“you are an expert growth hacker”) at the start of the prompt. Was that ever actually shown to be effective? Is it still?

Back with some papers. (Apologies in advance; I typically don't edit/format comments much here, please bear with me.)

Notable papers describing performance improvements with prescribed roles and personas:

- ExpertPrompting: Instructing Large Language Models to be Distinguished Experts (2023) https://arxiv.org/abs/2305.14688 (if you're going to only read one paper here, maybe read this one but know there has been a lot of follow up with more modern models.)

- Expert Personas Improve LLM Alignment but Damage Accuracy (2026) https://arxiv.org/abs/2603.18507

- When Does Persona Prompting Actually Help? (2026) https://arxiv.org/abs/2605.29420

- Unveiling Power on Combining Prompt Engineering Techniques: An Experimental Evaluation on Code Generation (2025) https://doi.org/10.5753/sbbd.2025.247251

- A Pattern Language for Persona-based Interactions with LLMs (2025) https://www.dre.vanderbilt.edu/~schmidt/PDF/Persona-Pattern-...

A TLDR of my *admittedly heavily biased* mental model (so take it with a grain of salt): personas do improve task alignment and precision to measurable effect but with observed negative impact to accuracy and knowledge grounding. Overall, this makes it quite suitable and preferred for code generation scenarios. (Don't over-index on 'accuracy' here as meaning "bad code", it's more about verbosity/jargon reducing clarity of higher order goals like business objectives and system architecture.)

Outside of code generation, personas have the interesting effect of increasing implicit biases and stereotypes. It's not hard to imagine something like "you are a left|right wing politician ..." or "you are a senior-citizen|teenager ..." influencing token space construction considerably.

Re: "Don't You Just Upload It to ChatGPT?"

#282

Post by Xeoncross »

xp84 wrote: post #45

The ending is a really powerful point. Most people apparently agree on two things: 1. AI is a great boon for all tasks and specialties we don’t have the skills to do ourselves. Understandable, since (A) we’re ill equipped to see the flaws in its output because it isn’t our area of expertise, and (B) it often can unlock great gains because if we trust it, we then don’t have to pay and wait for humans to do that thing.…

Honestly, we're at a point where AI can write better software than some devs and answer medical questions with more knowledge than some doctors.

Likewise, AI is oblivious to it's own mistakes, much like said professionals can be at times.

Not that AI is actually thinking, but rather the collective corpus of text yields greater insights (knowledge of the crowd, not wisdom of the crowd) than a lower-average person in that same industry.

Re: "Don't You Just Upload It to ChatGPT?"

#283

Post by Phaedruss »

Xeoncross wrote: post #282
xp84 wrote: post #45

The ending is a really powerful point. Most people apparently agree on two things: 1. AI is a great boon for all tasks and specialties we don’t have the skills to do ourselves. Understandable, since (A) we’re ill equipped to see the flaws in its output because it isn’t our area of expertise, and (B) it often can unlock great gains because if we trust it, we then don’t have to pay and wait for humans to do that thing.…

Honestly, we're at a point where AI can write better software than some devs and answer medical questions with more knowledge than some doctors. Likewise, AI is oblivious to it's own mistakes, much like said professionals can be at times. Not that AI is actually thinking, but rather the collective corpus of text yields greater insights (knowledge of the crowd, not wisdom of the crowd) than a lower-average person in t…

[dead]

Re: "Don't You Just Upload It to ChatGPT?"

#284

Post by zymhan »

atleastoptimal wrote: post #154

You'd be laughed at if you said that ChatGPT could help you with graduate level mathematics in 2024, but this year, AI models on simple prompts are solving previously unsolved Erdos problems. It seems silly to imagine that there is some fundamental barrier between human intelligence and AI, and that AI could never do many of the things that humans can do. Inferring intent, gauging sentiments, factoring in cultural va…

> You'd be laughed at if you said that ChatGPT could help you with graduate level mathematics in 2024, but this year, AI models on simple prompts are solving previously unsolved Erdos problems.

I'm curious, do you have a graduate degree in mathematics?

Re: "Don't You Just Upload It to ChatGPT?"

#285

Post by Folcon »

tombert wrote: post #9

I have no doubt that the writer is better at translating than AI, but I have to say that AI translation has gotten so good that I'm not sure how much longer translation work will be there, or rather it might end up being more about auditing. For example, I just read the Lawrence Ellsworth translation of The Three Musketeers, which I very thoroughly enjoyed. I don't speak or read French, but from my understanding Ells…

> but I have to say that AI translation has gotten so good that I'm not sure how much longer translation work will be there, or rather it might end up being more about auditing

It's functional? I wouldn't say it's poetic, I wouldn't want any AI translator translating art, like say a book or poem, I'd be so uncertain that it would correctly bridge the concepts

A good translator can make stylistic choices that elevate the work and make it fit in their language

(Having read lots of well translated manga and anime, also from what I understand there's a few books I've been told by my bilingual friend's are just chef's kiss quality translations)

Considering translating meaningful art is of some value, on that score I don't think we're there yet

Re: "Don't You Just Upload It to ChatGPT?"

#286

Post by bandrami »

greazy wrote: post #266
Aurornis wrote: post #118

Earlier quoted context omitted.

> This is why I use AI for all my medical questions and doctors use AI to write software, and we both smirk at the quality the other person is getting from it. There is an interesting third group emerging: People who acknowledge the quality problem, but think they can deal with it by applying more AI to the output. This takes the form of people who spin up a lot of "agents" and give them personalities like security d…

> There is an interesting third group emerging: People who acknowledge the quality problem, but think they can deal with it by applying more AI to the output. Ah yes, the known unknowns. The discussion reminds me of a talk Zizek gave in which he discusses the speech Rumsfeld gave regarding the evidence Iraq supplying weapons to terrorist[0]. Zezik argues the unknown knowns are far more interesting (and the reason why…

As an aside, the mass mockery in response to Rumsfeld's statement always bothered me because it's the single most intelligent statement he ever made about the Iraq war, and if he had started out with that mindset things probably would not have gone nearly as pear-shaped as they did.

Re: "Don't You Just Upload It to ChatGPT?"

#287

Post by 4k0hz »

atleastoptimal wrote: post #154

You'd be laughed at if you said that ChatGPT could help you with graduate level mathematics in 2024, but this year, AI models on simple prompts are solving previously unsolved Erdos problems. It seems silly to imagine that there is some fundamental barrier between human intelligence and AI, and that AI could never do many of the things that humans can do. Inferring intent, gauging sentiments, factoring in cultural va…

> all those things aren't magical tasks that can only occur inside a human skull, they are a product of information processing

I agree but it's useful to remember that 1. brains and especially the human brain are enormous and 2. individual tokens carry significantly more meaning than individual tiny muscle twitches so even extremely primitive "cognition" can look like it's doing more work than it actually is.

Re: "Don't You Just Upload It to ChatGPT?"

#288

Post by bandrami »

FeteCommuniste wrote: post #180
bryanrasmussen wrote: post #169

Earlier quoted context omitted.

I remember there were some studies that this kind of thing was effective a year or so ago, so essentially a lifetime in Model years. However to me it seems completely reasonable that it would work, because my understanding of what happens is the model interprets what you said as: Look for a group of people who are considered to be expert growth hackers by the world at large and answer my questions as though they were…

I imagined it as kind of a shorthand for "you should be spending my tokens on looking for / addressing issues like X, Y, and Z," where X, Y, and Z are the sorts of things that an expert in [insert domain here] would be likely to care most about.

At some point we have to just admit we're mass cargo-culting here and that these secret invocations people swear by have the same epistemic value as medieval superstitions.

Re: "Don't You Just Upload It to ChatGPT?"

#289

Post by tetromino_ »

greazy wrote: post #266
Aurornis wrote: post #118

Earlier quoted context omitted.

> This is why I use AI for all my medical questions and doctors use AI to write software, and we both smirk at the quality the other person is getting from it. There is an interesting third group emerging: People who acknowledge the quality problem, but think they can deal with it by applying more AI to the output. This takes the form of people who spin up a lot of "agents" and give them personalities like security d…

> There is an interesting third group emerging: People who acknowledge the quality problem, but think they can deal with it by applying more AI to the output. Ah yes, the known unknowns. The discussion reminds me of a talk Zizek gave in which he discusses the speech Rumsfeld gave regarding the evidence Iraq supplying weapons to terrorist[0]. Zezik argues the unknown knowns are far more interesting (and the reason why…

Link for the curious: https://www.lacan.com/zizekrumsfeld.htm

Re: "Don't You Just Upload It to ChatGPT?"

#290

Post by not_a_bot_4sho »

shnock wrote: post #277
not_a_bot_4sho wrote: post #196

Earlier quoted context omitted.

> Was that ever actually shown to be effective? Is it still? Yes! Personas demonstrated measurable improvement in a few different ways, with caveats of course. The common intuition is that personas influence token space in beneficial ways. I'll come back here later on desktop and link a few (still) relevant papers on this topic.

Please do, thank you! I have been similarly skeptical as your comment's parent

I added some brief commentary here: https://news.ycombinator.com/item?id=48507278#48511524 (or just refresh parent comment replies to see it)

It scratches the surface really but hopefully provides a helpful starting point.

Post reply on HN