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

191–200 of 408 posts

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

#191

Post by code_biologist »

bryanrasmussen wrote: post #169
toddmorey wrote: post #135

Earlier quoted context omitted.

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?

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…

It's been interesting to see how aggressively some reasoning models like to "reason" by analogy. They love to say things like "it's like a CPU" or "it's like a highway", and then they start to make logical leaps based off that rather than just using it for user explanation. Gemini 2.5 and 3.1 Pro have been particularly bad for this type of behavior. Telling models to "speak as though you are a physiologist considering the case with an expert colleague" gets them to "reason" using a more correct linguistic substrate.

The Opus models over the last year doesn't seem as vulnerable to this type of behavior and I've noticed the "identify as expert" prompt tricks aren't as meaningful there.

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

#192

Post by ozgung »

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.…

I feel like I am the only one thinking AI is actually much better than me in the things I'm supposed to do well. I feel like that for years now, so it's not about the latest generation of models. I can't imagine a single thing I can really compete with an AI at this stage. I am not sure if I am under-skilled or others are overconfident. Maybe people who feel like me don't say this out laud.

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

#193

Post by dools »

kingkongjaffa wrote: post #160
whazor wrote: post #148

Earlier quoted context omitted.

But using AI itself is a job too. It takes effort to correctly prompt, to steer it, to verify it, and to improve the harness.

show me a prompt that is meaningfully expertly crafted beyond just providing Do's, Do not's, task context, and a goal. > Correctly prompt, to steer it, to verify it, and to improve the harness. I doubt this a lot. The average AI user is running claude code as the harness, or Codex etc. prompting has no secret incantations, and steer and verify is just knowing what the answer should roughly look like, which is a domai…

> show me a prompt that is meaningfully expertly crafted beyond just providing Do's, Do not's, task context, and a goal.

The way that information is organised and formatted matters for compliance. It’s pretty similar to writing good procedural documentation for humans.

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

#194

Post by kube-system »

arjie wrote: post #122
layer8 wrote: post #84

Earlier quoted context omitted.

It’s unfortunate because we are seeing more poor translations in all domains, and users suffer from it. It’s part of a general enshittification of things. There are few contexts where low-quality translations don’t constitute a degradation of user experience. Just one amusing example I saw recently: On the Amazon website, a submit button labeled “Go” in English was translated to something which when translated back w…

On the other hand, a bridge sign that says "No entry for heavy vehicles" is unlikely to now read "I am out of office for the next 2 weeks" in Welsh: https://www.theguardian.com/theguardian/2008/nov/01/5

Now instead it will say, in Welsh

    "Switched to Opus 4.8 - Fable has safety measures that flag messages on most cybersecurity or biology topics. They may flag safe, normal content as well. These measures let us bring you Mythos-level capability in other areas sooner, and we're working to refine them."

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

#195

Post by layer8 »

Legend2440 wrote: post #107
layer8 wrote: post #84

Earlier quoted context omitted.

It’s unfortunate because we are seeing more poor translations in all domains, and users suffer from it. It’s part of a general enshittification of things. There are few contexts where low-quality translations don’t constitute a degradation of user experience. Just one amusing example I saw recently: On the Amazon website, a submit button labeled “Go” in English was translated to something which when translated back w…

I think you overestimate human translators. There is a lot of very poor quality human-translated text out there. English translated from Chinese is famous for this. There will never be enough expert-level human translators, and they tend to be very expensive. Machine translation has raised the floor.

I don’t agree that machine translation has raised the floor, because even LLM-based translation can get pretty bad when it isn’t provided with the necessary context. And the average quality level I’m encountering has dropped since machine translation became mainstream. Poor translations have become the norm, which wasn’t the case 20 years ago, despite the occasional “all your base are belong to us”.

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

#196

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?

> 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.

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

#197

Post by black3r »

s_tec wrote: post #91
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.…

It seems to be a general principle: If AI is better than you at something, you use it. If AI is worse than you, you don't. Each time the frontier models get better, I see another wave of AI doubters suddenly become believers. People say things like, "AI couldn't code last year, but now I use it for everything!" Interesting. Now we know how that the person who said this has the coding skills of a Claude Opus 4.5 or wh…

the sentiment "AI couldn't code last year, but now I use it for everything!" rings true for me... but I didn't flip cause AI is now better than me... I flipped cause now I am faster with AI than without it...

A year ago the AI output was so bad that getting it up to my standards took more than writing it myself from scratch. And nowadays it is faster for me to start with AI output and iterate from there to reach quality submission.

The ninety-ninety[0] rule was a thing talked about 40 years ago, long before anyone thought of AI coding. AI can nowadays make the first 90% of the task very fast and good enough. The last 10% is still the hardest part of coding by far.

[0]: https://en.wikipedia.org/wiki/Ninety%E2%80%93ninety_rule

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

#198

Post by Blackthorn »

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?

At least in the beginning of spicy autocomplete, this sort of role-play did work pretty dramatically at aligning a conversation to a task, though I don't think anyone ever tested it versus somewhat less cringe priming.

After that, cargo cults do what they do best.

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

#199

Post by throw-the-towel »

Aurornis wrote: post #118
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.…

> 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…

> People who acknowledge the quality problem, but think they can deal with it by applying more AI to the output.

Brute Force: if it doesn't work, you're just not using enough.

What if they're right though?

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

#200

Post by hyperpape »

Drupon wrote: post #14

An honest to god article full of em dashes that's not because it was AI but because it was a human using them as a crutch to get around crafting sentences that flow naturally. Almost brings a tear to my eye.

First sentence:

> In my Ottawa life, every Tuesday evening, I take two gym classes back to back—boxing and the pompously named “body sculpt,” which makes me discover muscles I didn’t know I had.

The em-dash matches how you'd speak out loud.

You'd say "I take two classes every Tuesday back to back, boxing and 'body sculpt'. Weird name." (Parts of that sentence did flow oddly, but not because of the em-dash).

Grammarians say you can't make those separate sentences without adding some extra words, and because of blah-de-blah-blah-blah, someone might say you can't join them with a comma. So we have an em-dash.

Rewriting the sentence would make it flow less naturally, not more.

Post reply on HN