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

Ask HN: What hacks/tips do you use to make AI work better for you?

news.ycombinator.com

Post reply on HN
Print view View original

101–108 of 108 posts

Re: Ask HN: What hacks/tips do you use to make AI work better for you?

#101

Post by butlike »

joblemblem wrote: post #11

I’m exhausted by these types of posts. I am a developer with >25 of professional experience. I am unable to get these things to do anything useful. I’ve tried: different models, limiting my scope, breaking it down to small tasks, prompt “engineering”; and am still getting less than useless results. I say less than useless, because I will then additionally waste time debugging or slamming my head against the wall the…

There's an element of "I'm not going to do your homework for you" I find sometimes.

I've also never asked it to spit out more than an HTML boilerplate or two, but it is useful for asking best options when given a choice between two programming patterns.

Re: Ask HN: What hacks/tips do you use to make AI work better for you?

#102

Post by butlike »

mehh wrote: post #96
solidasparagus wrote: post #29

Earlier quoted context omitted.

LLMs have dramatically different results depending on the domain. Getting LLMs to help me learn typescript is a joy, getting them to help me fix distributed consensus problems in my fully bespoke codebase make them look worse than useless. Some people will find them amazing, some will find them a net negative. Although finding truly zero use for them makes it hard for me to believe that this person really tried with…

Very much this, I have > 25 years programming experience, but not with typescript and react, it’s helping me with my current project. I ignore probably 2/3 of its auto suggestions, but increasingly I now highlight some code and ask it to just do x for me, rather having to go google the right function/ css magic

Does that feel as rewarding as doing it yourself?

Re: Ask HN: What hacks/tips do you use to make AI work better for you?

#103

Post by bawis »

edanm wrote: post #59
yen223 wrote: post #2

I like using LLMs for building non-critical tools that make me more productive. Things like shell scripts, Github actions, or one-off tools for visualising some problem space. The kind of thing where code quality doesn't really matter, but which will save you a ton of time in the long run

This is an enormously fruitful part of using LLMs for me too. As a programmer, there's always a million small scripts I can think of to improve my life, but it's often not worth spending time actually building them. But with LLMs, I can now usually build a script, even in a domain I don't know much about, in minutes. I don't think this would work as easily for non-programmers yet, because the scripts still aren't per…

"even in a domain I don't know much about, in minutes."

How is this done exactly ? can you provide an easy example for me (not a programmer but I use python/R from time to time)

Re: Ask HN: What hacks/tips do you use to make AI work better for you?

#104

Post by mehh »

butlike wrote: post #102
mehh wrote: post #96

Earlier quoted context omitted.

Very much this, I have > 25 years programming experience, but not with typescript and react, it’s helping me with my current project. I ignore probably 2/3 of its auto suggestions, but increasingly I now highlight some code and ask it to just do x for me, rather having to go google the right function/ css magic

Does that feel as rewarding as doing it yourself?

I'm fine with it, I've forgotten more frameworks and libs for now dead devices/services/OS etc over the years that it's largely pointless memorising these things, I'm very happy for a machine to help me get to where I want to be, and less time faffing about with google/stackoverflow the better, like I said the failure rate is still fairly high, but still useful enough.

Re: Ask HN: What hacks/tips do you use to make AI work better for you?

#105

Post by kirso »

I have chats labeled as "Life" (coaching), "Health" (fetching some data on diets, exercise), "Tech" (discussing various code blocks".

One very uncomfortable but useful hack is when you feed it context, to ask "what are my blindspots", in fact sometimes I ask it to roast me where it reveals some uncomfortable truths that I am not willing to admit but because it sparks an emotional reaction, it makes me more self-aware.

Re: Ask HN: What hacks/tips do you use to make AI work better for you?

#106

Post by eternityforest »

miningape wrote: post #87
eternityforest wrote: post #36

If AI doesn't understand something I assume it's too clever, even if I do get the AI to figure it out I won't understand it in a month and other devs won't understand it at all unless I somehow convince them to read the code(Like as if that's going to happen!). I think it's definitely improved my own code, because it's like always working with a pair programmer, who represents a very average developer with insane typ…

> unless I somehow convince them to read the code(Like as if that's going to happen!). code is read more often than its written. I spend maybe 60-70% of my time reading code when I'm "writing code". I don't think it will take much convincing if you're working on a project with others.

If you're maintaining a part of the code by yourself, some devs might not want anything to do with it, they won't read it or think about it or even learn to use it if they don't have to.

Especially if they're busy, it's very easy to wind up as the lone maintainer of some fairly isolated part of the system that nobody else touches because you seem to be doing just fine.

Re: Ask HN: What hacks/tips do you use to make AI work better for you?

#107

Post by Breza »

bawis wrote: post #103
edanm wrote: post #59

Earlier quoted context omitted.

This is an enormously fruitful part of using LLMs for me too. As a programmer, there's always a million small scripts I can think of to improve my life, but it's often not worth spending time actually building them. But with LLMs, I can now usually build a script, even in a domain I don't know much about, in minutes. I don't think this would work as easily for non-programmers yet, because the scripts still aren't per…

"even in a domain I don't know much about, in minutes." How is this done exactly ? can you provide an easy example for me (not a programmer but I use python/R from time to time)

Here's an example. I had a ton of XML files in an external drive and I needed to delete all the files that didn't contain a certain phrase. I had Claude write a bash script to move all the non-matching files to a new folder, spot checked a few to confirm that it had worked properly, and deleted them. My bash skills are decent but it still saved me time.

Re: Ask HN: What hacks/tips do you use to make AI work better for you?

#108

Post by Breza »

ilrwbwrkhv wrote: post #6

cursor and all the other ai code editors always write bad enough code that i have stopped using them completely. i like the inline completions that things like supermaven provides or github copilot or even the jetbrains full line completion models. Apart from that, I might use Claude or Chat GPT to talk about an idea, but I don't really use it much. I prefer to use my real life experience and skills. Maybe if you're…

Yeah, I love talking about my ideas with an LLM. They can be good at finding holes in my planned approach to a project. And if the holes aren't relevant, it's usually because I didn't explain myself very well at the outset, which means I need to go back to basics before I talk to a human about the project.
Post reply on HN