this post was submitted on 07 Dec 2024
19 points (72.1% liked)

JetBrains

71 readers
21 users here now

A community for discussion and news relating to JetBrains and its products! https://www.jetbrains.com/

Related Communities

Copyright © 2000-2024 JetBrains s.r.o. JetBrains and the JetBrains logo are registered trademarks of JetBrains s.r.o.

founded 10 months ago
MODERATORS
 

My minimal LLM instructions. These are the current ones for @jetbrains IDEs with their in-IDE AI in particular.

LLMs overengineer so easily. They have verbal diarrhea so readily. They have comments like "set a to 1" for lines like "a = 1" all the time.

This prompt reins them in ... somewhat.

top 20 comments
sorted by: hot top controversial new old
[–] [email protected] 2 points 2 days ago

A post about making AI more useful?!? On... LEMMY!?!?! Guards, prepare the excommunicado order.

/s

[–] glassware 5 points 3 days ago (2 children)

If you are uncertain about something, never make up possible solutions, instead state and admit that you do not know the thing.

Does this work? Given that the LLM doesn't actually know anything or have feelings of uncertainty, surely it just adds a chance that it will say "I don't know" purely at random, without making it any more likely that the answers it does give are correct.

[–] [email protected] 1 points 1 day ago* (last edited 1 day ago)

I find it kind of hilarious how almost every prompt I've seen leaked from various apps almost always has a similar clause, as if it would have any effect at all on the result.

Seeing engineers resort to this level of basically praying and wishful thinking that in reality has no factual value is pretty funny.

"Please, don't give me wrong results 0_0"

[–] [email protected] 1 points 3 days ago

@glassware In my experience, it seems to. It's all fuzzy anyway, but I've had it hallucinate APIs less regularly since adding that to my prompts. I have also done A/B tests in that sometimes, with Claude, I forget switching to my own prompt and see it spew random verbal diarrhea, go back and switch and it's better.

It doesn't have feelings, but it does have certainty of prediction in terms of probability of continuation. I think it does influence that.

[–] [email protected] 11 points 4 days ago* (last edited 4 days ago) (1 children)

I have an even better approach to getting good code, but you might not like it: learn how to code

[–] [email protected] 12 points 4 days ago* (last edited 4 days ago) (1 children)

@Boomkop3 I've been coding for 35 years and I'm earning money with it since 1998, so I think I'm fine in that regard. LLMs can do tedious tasks real quick. And are easily overwhelmed with architecture.

[–] [email protected] -5 points 4 days ago* (last edited 4 days ago) (1 children)

I started when I was nine, and my colleague next to me learned c from the guys who were still working on linux back then.

We both tried llm's, but found that even for tedious stuff it cannot compete with even semi decent knowledge of the advanced text editing features available in almost all ide's.

Thank you for your receipts, now learn how to use a text editor properly.

My colleague across from me finds that a good llm helps him search trough large amounts of documentation.

[–] [email protected] 3 points 4 days ago (1 children)

@Boomkop3 It's amazing how even in the Fediverse, there's needlessly toxic people 😄 I think you should lighten up a bit.

[–] [email protected] -2 points 4 days ago (1 children)

Hey, you brought up receipts. Git gud m8

[–] [email protected] 3 points 4 days ago (2 children)

@Boomkop3 You assumed that I can't code, that was toxic already. Don't deflect.

[–] [email protected] 4 points 4 days ago (1 children)

@Boomkop3 But I'll stop interacting with you. Trolls and dragging down and stuff. We all know that.

[–] [email protected] -2 points 3 days ago

Good on you!

[–] [email protected] -2 points 3 days ago

That was a rethorical statement. When you're good at this, chatgpt isn't much help.

[–] zkfcfbzr 6 points 4 days ago* (last edited 4 days ago) (1 children)

Copy/pastable version:

Your answers must be concise and correct. Brief and short. If one line of code suffices, give me one line of code. Do not repeat vast amounts of code unless specifically asked and tasked to. Never generate more than a few lines of code unless I tell you to. If you are uncertain about something, never make up possible solutions, instead state and admit that you do not know the thing. Never write in-code comments, make the code self-documenting instead. Never overengineer things, never invent your own requirements beyond what I specifically asked you to do.

[–] [email protected] 4 points 4 days ago

@zkfcfbzr Thanks! It's also in the alt text of the image. Should've mentioned that. 💖

[–] [email protected] 1 points 3 days ago (1 children)

Does anyone have experience with phpstorm editing large projects? Are most of the bugs fixed?

[–] [email protected] 1 points 3 days ago (1 children)

@limer What bugs do you mean? I do use PhpStorm regularly, haven't experienced any major issues (unlike with Fleet for example, that's just not finished IMHO), but maybe your projects are different, larger, more demanding?

[–] [email protected] 1 points 2 days ago (1 children)

A lot of the bugs were after a copy paste, and error detection. I had been using it for years on the same projects, and it worked pretty good. But the new issues were seen first this year.

I went over to their youtrack, read other people’s comments and many had rolled back their version to the last release last year. So I did it too.

Then, after the second version this year someone said some of the new issues were still not fixed.

I’ll probably try it again today.

[–] [email protected] 1 points 2 days ago (1 children)

@limer I'm using PyCharm much more often than PhpStorm right now, but they do share a lot of their DNA. There were quite some exceptions being thrown with that AI integration stuff, last month, but that has all been resolved. Let's hope the issues you ran into have gone too!

[–] [email protected] 1 points 2 days ago

That’s great news, am optimistic now