Live data from Hacker News

I'd rather read the prompt

claytonwramsey.com

751–760 of 880 posts

Re: I'd rather read the prompt

#751

Earlier quoted context omitted.

"Let's identify specific, clear areas for improvement, and if they are not able to improve, let's fire them": it's as simple as that. Teaching a human with motivation, potential and desire to learn is both easier , and more rewarding (for most humans), than attempting to teach LLM to write good code every time — humans tend to value their personal experiences more, whereas LLM relies more on the training corpus. So w…

None of this responds to what I just wrote. Can you engage with the question I asked directly? Thanks!

You asked:

  > As a team lead, what would you think of a team member who consistently generated "crap" pull requests?
This is directly answered with my first paragraph: that's exactly what I would think of them, and how I would act on it.

Your first question was:

  > How is that better?
In the second paragraph, I explained why it's better to do a code review for a crappy pull request that's human-produced vs LLM-generated: it is easier, faster, and more psychologically rewarding.

If you are talking about a case where an inexperienced human uses LLM to start off with a crappy code change, but then adapts the output during the review process, and potentially learns through it (though research confirms people learn better when they produce mistakes themselves) — they still won't be able to use LLM to produce comparable code the next time, so they'll have to do the review and improve it by hand before putting it up for review by somebody else, thus negating any productivity gain (which was the original premise), and likely reducing the learning potential.

If there was a question I misinterpreted, please enlighten me. Thanks! :)

Re: I'd rather read the prompt

#752
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.

That's a good one.

One analogy I use a lot: if I have a professor sitting next to me, what is the best way to learn a topic?

Struggle through it on my own and I won't be leveraging the professors knowledge.

Ask the professor to do everything for me and I won't be learning anything at all.

Now if the professor is an AI, the same trade-offs hold.

For example, I will back and forth conversations with AI to explain subjects to me. I ask questions, push back, ask for examples, and so on.

If I do ask the AI to answer something for me, I then ask it to break down the answer for me so I can make sure I understand it deeply.

And of course, none of this matters if I don't want to learn something :)

Re: I'd rather read the prompt

#753
post #436

Earlier quoted context omitted.

In a medieval guild, to be admitted as a master, an apprentice had to create a chef d'oevre, or masterpiece, so called for this reason. In the computer engineering industry, you increasingly have to demonstrate the same: either as a part of your prior work for hire, or a side project, or a contribution to something open-source. A diploma is still a useful signal, but not sufficient, except maybe for very junior posit…

I think software developers might be somewhat of an outlier. Industry wants good programmers but universities teach computer science which really should be called "computation science". Much of what we learn in university will hardly ever be used while many practical skills are at best learned as a side effect. Dijkstra favorite said that computer science is as much about computers as astronomy is about telescopes. S…

> while many practical skills are at best learned as a side effect.

I strongly disagree, that’s the intent not a side effect.

It’s IMO a common misconception that early algorithm classes are just designed around learning algorithms. Instead basic algorithms are the simplest thing to turn abstract requirements into complex code. The overwhelming majority of what students learn are the actual tools of programming, debugging, etc while using the training wheels of a problem already broken up into bite sized steps.

Ramping up the complexity is then more about learning tradeoffs and refining those skills than writing an ever more efficient sorting algorithm or whatnot.

Re: I'd rather read the prompt

#754

I think the answer to the professor's dismay is quite simple. Many people are in university to survive a brutal social darwinist economic system, not to learn and cultivate their minds. Only a very small handful of them were ever there to study Euler angles earnestly. The rest view it as a hoop they have to jump through to hopefully get a job that might as well be automated away by AI anyway. Also viewed from a condi…

Whose system though?

I agree, it's weird for parents to say, "Jump through these hoops, and for every dollar you earn grinding sesame for some company, we'll give you an additional two."

Working and educating yourself is decent and dignified, no? Is this a bad deal?

Re: I'd rather read the prompt

#755

I blogged about this just yesterday. The problem of disguised authorship ruins your reputation as a thinker, worker, and writer. https://www.satisfice.com/blog/archives/487881

This is a good post.

Off-topic, but on your parenthetical about SMS "wrong number" texts "(That scam doesn’t even make sense...)", part of why they do it is what's called "warming up" their sending number so that it's seen as legit by carriers and SMS filters. They're also seeing whether you're a real person who responds, in which case they can come back later with a more sophisticated scam (or re-sell you number, which is now more valuable, to another scammer for that purpose).

But you're right that it doesn't make much sense as a text you might receive naturally. Best thing is to not reply so that you're not feeding the beast.

Incidentally, I used ChatGPT to refresh my memory about how this works, and in its initial response it got it backwards, saying that "warming up" is what it does to your number. You can't trust these things one bit! Your post calls it "automated irresponsibility", and I like that.

Re: I'd rather read the prompt

#756
post #645

Earlier quoted context omitted.

Techbically even those hidden phrases arent permitted by law, and you have the right to get those phrases removed/have it be turned into a basic evaluation (just from when to when + what job) The employers that do use those hidden phrases just hope they arent challenged/the employee doesnt notice. Thats also why most evaluations are entirely written in the superlative.

Unfortunely they are common enough to keep lawyers and book publishing businesses going with dictionaries "evaluation => real meaning", exactly for that little help to go though it and validate its correctness. Many employeers profit from foreigners that aren't well versed in these nuances, and have to be educated this is a thing. An example for others not used to German work market, https://www.karriereakademie.de/a…

There's software for that even. The input is a ranking of the employee on a bunch axis (1-5 or something) and it spits out the appropriate text. Does the reverse too.

Re: I'd rather read the prompt

#757
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.

It's an e-bike for the mind!

Re: I'd rather read the prompt

#758
post #489

Earlier quoted context omitted.

We can't fix the problem by making better choices as individuals, and exhorting people to do so saps energy and distracts. The system interprets integrity as damage and routes around it.

This attitude willingly donates what agency you have to the people and things trying to take it from you. Lead by example. Mimicry is real, we all do it whether or not we are aware. Every node in the graph influences others. If you must exhort, it works better if you follow your own advice. Of course, be discerning as you do this, and don't expend your energy or goodwill where it will be wasted. Be like Gandalf. Any…

It's disheartening how many people do not want to hear this. But it's the only way we can get things done. It's the same thing that led to this system we all hate, a race to the bottom. I posted this a week back. I think you'll enjoy the article if you haven't read it yet. Don't give up, you're not alone and I think we're gaining momentum. https://news.ycombinator.com/item?id=43824534

Re: I'd rather read the prompt

#759

Earlier quoted context omitted.

> We can't fix the problem by making better choices as individuals That's wildly inaccurate. Your logic necessitates that "the system" is not composed of individuals. The problem itself was created through individual actions...

The problem of individuals making optimal choices on an individual scale being sub-optimal on a society scale is so widespread we have a specific phrase to describe it: Tragedy of the commons I would love to live in a world where everyone was altruistic and made correct choices for the long term good of society, but I don't. And there are limits to how much I'm willing to act as if I do, when in practice it just mean…

  > The problem of individuals making optimal choices on an individual scale being sub-optimal on a society scale
The problem is people think this is a remotely accurate statement. These things only work if you use very low order approximations. Like being the only person and time not existing. As soon as you build any accuracy your net benefit more aligns with society.

The classic example of this is the marshmallow experiment. It's myopic. We do it all the time but frequency doesn't make an action intelligent https://news.ycombinator.com/item?id=43873275

This isn't a tragedy of the commons issue. There's no finite resource we're all trying to draw upon in this case. The supply is generated by ourselves and it could be infinite if we chose to.

Re: I'd rather read the prompt

#760

Earlier quoted context omitted.

If students went to college only to learn, colleges wouldn't bother giving diplomas. Compare: My piano teacher doesn't give diplomas because none of her students would care, her students actually want to learn. When my piano teacher cancels class, I am disappointed because I wanted to learn. My piano teacher doesn't need to threaten me with bad grades to get me to practice outside of class (analogous to homework), be…

Students want the diploma because it has value. It has value because a student can only get it by learning and problem-solving. If students find a way to get a diploma without doing the work, it will soon be worth less than the paper on which it is printed.

You can also get it by cheating and bribing.
Post reply on HN