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

I'd rather read the prompt

claytonwramsey.com

Post reply on HN
Print view View original

451–460 of 880 posts

Re: I'd rather read the prompt

#451

Post by mettamage »

derefr wrote: post #187
musicale wrote: post #141

Earlier quoted context omitted.

> LLMs are like anti-compression algorithms when used like that, a simple idea gets expanded into a bloated mess by an LLM, I think that's the answer: LLMs are primarily useful for data and text translation and reduction, not for expansion. An exception is repetitive or boilerplate text or code where a verbose format is required to express a small amount of information.

There is one other very useful form of "expansion" that LLMs do. If you aren't aware: (high-parameter-count) LLMs can be used pretty reliably to teach yourself things. LLM base models "know things" to about the same degree that the Internet itself "knows" those things. For well-understood topics — i.e. subjects where the Internet contains all sorts of open-source textbooks and treatments of the subject — LLMs really…

This is how I currently am relearning upper high school math. It’s tremendously helpful as I am a why guy.

Why is the angle called m? Why is a combination nPr * (1/r)? What is 1/r doing there?

I use mathacademy.com as my source of practice. Usually that’s enough but I tend to fall over if small details aren’t explained and I can’t figure out why those details are there.

In high school this was punished. With state of the art LLMs, I have a good tutor.

Also it’s satisfying to just upload a page in my own handwriting and it understands what I did, and is able to correct me there.

Re: I'd rather read the prompt

#452

Post by sigmaisaletter »

geysersam wrote: post #435
bumby wrote: post #303

Earlier quoted context omitted.

Academia clearly lost their monopoly on information. Since their last moat is a monopoly on credentials, I expect them to defend it intensely. We could make it less meaningful if employers weren’t so keen on using credentials as their own gateway. That may have more of a chance of happening if the OPs perspective becomes more prevalent and the credential becomes an increasingly worse signal for meaningful skills.

In what way does academia have monopoly on credentials? You can start issuing your own credentials tomorrow.

I don't know where you live, but in the "developed" parts of the world this is illegal. There will either be some government agency or some council of credential-giving institutions and they will give you a license to issue degrees, or most likely they will not give it to you.

Re: I'd rather read the prompt

#453

Post by godelski »

aniforprez wrote: post #421
godelski wrote: post #398

Earlier quoted context omitted.

> then she could issue a degree in piano. It's worth noting, plenty of universities do this. You can get a degree "in piano".

Yes they did actually say that. They go into the process of accreditation that would result in a person or institute being able to give a degree "in piano"

Not every reply is written to disagree.

Re: I'd rather read the prompt

#454

Post by nradov »

palata wrote: post #275
soerxpso wrote: post #253

Earlier quoted context omitted.

> I should hope that the purpose of a class writing exercise is not to create an artifact of text but force the student to think I'm there for the degree. If I wanted to learn and engage with material, I could save $60,000 and do that online for free, probably more efficiently. The purpose of a class writing exercise is to get the university to give me the degree, which I cannot do by actually learning the material (…

> I'm there for the degree. If I wanted to learn and engage with material, I could save $60,000 I would argue that if it costs $60,000, both your education system and the recruitment in those companies that require this degree are broken. It's not the case in all countries though. Not that it is your fault, just stating the obvious.

Sure, the system is broken but what's the alternative? Employers have a surplus of applicants for entry-level technical positions. They need to filter the applicant pool down to those with some level of competence and discipline. Possession of a college degree is a reasonably accurate proxy for those attributes: lots of false negatives but good enough from the employer's perspective.

Ideally maybe employers ought to rely on more targeted selection mechanisms. But this would be extremely expensive (and potentially legally risky due to equal opportunity laws) so most don't bother.

Re: I'd rather read the prompt

#455

Post by phamilton »

deadbabe wrote: post #245
sn9 wrote: post #221

> I should hope that the purpose of a class writing exercise is not to create an artifact of text but force the student to think; a language model produces the former, not the latter. It's been incredibly blackpilling seeing how many intelligent professionals and academics don't understand this, especially in education and academia. They see work as the mere production of output, without ever thinking about how that…

Someday, LLMs are going to cost actual serious money to use and people will have “LLM bills” to pay every month just to have some semblance of a brain at work. Maybe a portion of salary can just be deducted directly from a paycheck to pay for LLM tools.

I can run the Qwen 3 0.6B model directly on my 3-year-old phone, and it can rewrite text and help me clearly explain my views. Even with new models possibly being less open and subsidized options drying up, we still have useful open models available for free on consumer hardware.

Source: I used it to write this post.

Re: I'd rather read the prompt

#456

Post by hnfong »

godelski wrote: post #409
soerxpso wrote: post #253

Earlier quoted context omitted.

> I should hope that the purpose of a class writing exercise is not to create an artifact of text but force the student to think I'm there for the degree. If I wanted to learn and engage with material, I could save $60,000 and do that online for free, probably more efficiently. The purpose of a class writing exercise is to get the university to give me the degree, which I cannot do by actually learning the material (…

> I'm there for the degree Would you hire someone without a degree? When you're in a position to hire or influence hiring, will you consider those without degrees? I ask because I hear this sentiment a lot but we still have a system becoming more reliant on degrees. The universities may be the gatekeepers of those degrees but they're not the ones gatekeeping the jobs. They have no influence there. They were not the o…

Speaking personally, yes, very much so.

I see your point, but the issue is that it's quite futile to shame students for playing the game that people in the industry has set up. It doesn't help that in the past, college degrees were in fact more relevant than today, especially before the era of the internet and wikipedia, so if older people who are currently in charge of hiring aren't aware of these changes, they might just apply their outdated personal experience and just assume college degrees hold the same weight as they did in the past.

I'm pretty certain when kids these days eventually become responsible for hiring decisions, they probably will handle things differently since their experiences are different.

Re: I'd rather read the prompt

#457

Post by phamilton »

torben-friis wrote: post #128
necovek wrote: post #54

I've already asked a number of colleagues at work producing insane amount of gibberish with LLMs to just pass me the prompt instead: if LLM can produce verbose text with limited input, I just need that concise input too (the rest is simply made up crap).

“Someone sent me this ai generated message. Please give me your best shot at guessing the brief prompt that originated the text”. Done, now ai is just lossy prettyprinting.

Jokes aside, this happens all the time.

I have it write doc strings. I later ask it to explain a section of code, wherein it uses the doc strings to understand and explain the code to me.

A less lossy way to capture this will probably emerge at some point.

Re: I'd rather read the prompt

#458

Post by phamilton »

ponector wrote: post #199
necovek wrote: post #54

I've already asked a number of colleagues at work producing insane amount of gibberish with LLMs to just pass me the prompt instead: if LLM can produce verbose text with limited input, I just need that concise input too (the rest is simply made up crap).

Chatgpt very useful for adding softness and politeness to my sentences. Would you like more straight forward text which probably will be rude for regular american?

If we can detach content and presentation, then the reader can choose tone and length.

At some point we will stop making decisions about what future readers want. We will just capture the concrete inputs and the reader's LLM will explain it.

Re: I'd rather read the prompt

#459

Post by expensive_news »

bost-ty wrote: post #4

I like the author's take: it isn't a value judgement on the individual using ChatGPT (or Gemini or whichever LLM you like this week), it's that the thought that went into making the prompt is, inevitably, more interesting/original/human than the output the LLM generates afterwards. In my experiments with LLMs for writing code, I find that the code is objectively garbage if my prompt is garbage. If I don't know what I…

I have mixed feelings. Generally I don’t think that LLM output should be used to create anything that a human is supposed to read, but I do carve out a big exception for people using LLMs for translation/writing in a second language.

At the same time, however, the people who need to use an LLM for this are going to be the worst at identifying the output’s weaknesses, eg just as I couldn’t write Spanish text, I also couldn’t evaluate the quality of a Spanish translation that an LLM produced. Taken to an extreme, then, students today could rely on LLMs, trust them without knowing any better, and grow to trust them for everything without knowing anything, never even able to evaluate their quality or performance.

The one area that I do disagree with the author, though, is coding. As much as I like algorithms code is written to be read by computers and I see nothing wrong with computers writing it. LLMs have saved me tons of time writing simple functions so I can speed through a lot of the boring legwork in projects and focus on the interesting stuff.

I think Miyazaki said it best: “I feel… humans have lost confidence“. I believe that LLMs can be a great tool for automating a lot of boring and repetitive work that people do every day, but thinking that they can replace the unique perspectives of people is sad.

Re: I'd rather read the prompt

#460

Post by beAroundHere »

jameshart wrote: post #329
sn9 wrote: post #221

> I should hope that the purpose of a class writing exercise is not to create an artifact of text but force the student to think; a language model produces the former, not the latter. It's been incredibly blackpilling seeing how many intelligent professionals and academics don't understand this, especially in education and academia. They see work as the mere production of output, without ever thinking about how that…

I’ve come across this analogy that I think works well: Using an LLM to do schoolwork is like taking a forklift to the gym. If all we were interested in was moving the weights around, you’d be right to use a tool to help you. But we’re doing this work for the effect it will have on you . The reason a teacher asks you a question is not because they don’t know the answer.

I think you're quoting the Sci Fi author - Ken Liu from his article in some major news outlet.

I related with that analogy too, infact that whole piece is worth reading. I can't seem to find it's link though!

Post reply on HN