undefined | Better HN

0 pointsRealityVoid1mo ago0 comments

You're not going crazy. That is what I see as well. But, I do think there is value in:

- driving the LLM instead of doing it yourself. - sometimes I just can't get the activation energy and the LLM is always ready to go so it gives me a kickstart

- doing things you normally don't know. I learned a lot of command like tools and trucks by seeing what Claude does. Doing short scripts for stuff is super useful. Of course, the catch here is if you don't know stuff you can't drive it very well. So you need to use the things in isolation.

- exploring alternative solutions. Stuff that by definition you don't know. Of course, some will not work, but it widens your horizon

- exploring unfamiliar codebases. It can ingest huge amounts of data so exploration will be faster. (But less comprehensive than if you do it yourself fully)

- maintaining change consistency. This I think it's just better than humans. If you have stuff you need to change at 2 or 3 places, you will probably forget. LLM's are better at keeping consistency at details (but not at big picture stuff, interestingly.)

0 comments

TheAceOfHearts1mo ago

For me the biggest benefit from using LLMs is that I feel way more motivated to try new tools because I don't have to worry about the initial setup.

I'd previously encountered tools that seemed interesting, but as soon as I tried getting it to run I found myself going down an infinite debugging hole. With an LLM I can usually explain my system's constraints and the best models will give me a working setup from which I can begin iterating. The funny part is that most of these tools are usually AI related in some way, but getting a functional environment often felt impossible unless you had really modern hardware.

christophilus1mo ago

Same. This weekend, I built a Flutter app and a Wails app just to compare the two. Would have never done either on my own due to the up front boilerplate— and not knowing (nor really wishing to know) Dart.

chasd001mo ago

I did the same thing but with react and supabase. I wouldn’t have done this on my own because of the react drudgery.

1 more reply

unixhero1mo ago

Cool! With openclaw or with Claude?

1 more reply

zorgz1mo ago

great point. llm breaks that initial fatigue where to start if you go outside of your comfort zone tech stack

kace911mo ago

>driving the LLM instead of doing it yourself. - sometimes I just can't get the activation energy and the LLM is always ready to go so it gives me a kickstart

There is a counter issue though, realizing mid session that the model won’t be able to deliver that last 10%, and now you have to either grok a dump of half finished code or start from scratch.

viking1231mo ago

My problem is that once I have coded a lot with the LLM, and I come across some problem that I just cannot solve with it like a synchronization issue in my game, then I have to go down to the weeds and the effort feels so gargantuan because I have mostly relied on the LLM.

worik1mo ago

That is the point. Do not lean too heavily on an LLM for code generation for that very reason.

They are still very useful, locally.

zephen1mo ago

I wonder about this.

If (and it's a big if) the LLM gives you something that kinda, sorta, works, it may be an easier task to keep that working, and make it work better, while you refactor it, than it would have been to write it from scratch.

That is going to depend a lot on the skillset and motivation of the programmer, as well as the quality of the initial code dump, but...

There's a lot to be said for working code. After all, how many prototypes get shipped?

Fogest1mo ago

> - maintaining change consistency. This I think it's just better than humans. If you have stuff you need to change at 2 or 3 places, you will probably forget. LLM's are better at keeping consistency at details (but not at big picture stuff, interestingly.)

I use Claude Code a decent amount, and I actually find that sometimes this can be the opposite for me. Sometimes it is actually missing other areas that the change will impact and causing things to break. Sometimes when I go to test it I need to correct it and point out it missed something or I notice when in the planning phase that it is missing something.

However I do find if you use a more powerful opus model when planning, it does consider things fully a lot better than it used to. This is actually one area I have been seeing some very good improvements as the models and tooling improves.

In fact, I actually hope that these AI tools keep getting better at the point you mention, as humans also have a "context limit". There are only so many small details I can remember about the codebase so it is good if AI can "remember" or check these things.

I guess a lot of the AI can also depend on your codebase itself, how you prompt it, and what kind of agents file you have. If you have a robust set of tests for your application you can very easily have AI tools check their work to ensure things aren't being broken and quickly fix it before even completing the task. If you don't have any testing more could be missed. So I guess it's just like a human in some sense. If you have a crappy codebase for the AI to work with, the AI may also sometimes create sloppy work.

throwaway0123_51mo ago

> LLM's are better at keeping consistency at details (but not at big picture stuff, interestingly.)

I think it makes sense? Unlike small details which are certain to be explicitly part of the training data, "big picture stuff" feels like it would mostly be captured only indirectly.

j / k navigate · click thread line to collapse

0 pointsRealityVoid1mo ago0 comments

You're not going crazy. That is what I see as well. But, I do think there is value in:

- driving the LLM instead of doing it yourself. - sometimes I just can't get the activation energy and the LLM is always ready to go so it gives me a kickstart

- exploring alternative solutions. Stuff that by definition you don't know. Of course, some will not work, but it widens your horizon

- exploring unfamiliar codebases. It can ingest huge amounts of data so exploration will be faster. (But less comprehensive than if you do it yourself fully)

0 comments

TheAceOfHearts1mo ago

For me the biggest benefit from using LLMs is that I feel way more motivated to try new tools because I don't have to worry about the initial setup.

christophilus1mo ago

chasd001mo ago

I did the same thing but with react and supabase. I wouldn’t have done this on my own because of the react drudgery.

1 more reply

unixhero1mo ago

Cool! With openclaw or with Claude?

1 more reply

zorgz1mo ago

great point. llm breaks that initial fatigue where to start if you go outside of your comfort zone tech stack

kace911mo ago

>driving the LLM instead of doing it yourself. - sometimes I just can't get the activation energy and the LLM is always ready to go so it gives me a kickstart

There is a counter issue though, realizing mid session that the model won’t be able to deliver that last 10%, and now you have to either grok a dump of half finished code or start from scratch.

viking1231mo ago

worik1mo ago

That is the point. Do not lean too heavily on an LLM for code generation for that very reason.

They are still very useful, locally.

zephen1mo ago

I wonder about this.

That is going to depend a lot on the skillset and motivation of the programmer, as well as the quality of the initial code dump, but...

There's a lot to be said for working code. After all, how many prototypes get shipped?

Fogest1mo ago

throwaway0123_51mo ago

> LLM's are better at keeping consistency at details (but not at big picture stuff, interestingly.)

I think it makes sense? Unlike small details which are certain to be explicitly part of the training data, "big picture stuff" feels like it would mostly be captured only indirectly.

j / k navigate · click thread line to collapse