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

LLMs can be exhausting

tomjohnell.com

Post reply on HN
Print view View original

111–120 of 232 posts

Re: LLMs can be exhausting

#111

Post by jmward01 »

I'm not sure a faster loop is helping. It may actually be the problem. I have taken to creating 'collaboration' and 'temp_code' folders that I am spending more and more time in. By the time I am actually ready to touch the real code I have often written and re-written the problem statement/plan and expanded it to several files and some test code. I tell the other devs at my company that I spend 90% of the tokens on understanding and clarifying the problem and let the last 10% generate an answer. If I don't do that then I get prototype code that won't survive a single feature change and likely has intentionally hidden bugs, or 'defensive' code as some like to call them (try, except, ignore is a common claude pattern). My favorite is when claude hits the unit tests and says 'that failure was there before we started so I can ignore it...'. To get it to write actually good code you have to have caged the problem to a space that the LLM can optimize without worry, but to do that you have to still do work to understand how to break the problem into pieces small enough that the right answer is the obvious one. At that point letting it take the syntax is just fine by me.

Maybe the right answer is to sometimes slow down, explore and think a little more instead of just letting it try something until it (eventually, sort of) works.

Re: LLMs can be exhausting

#112

Post by stavros »

jeremyjh wrote: post #80
stavros wrote: post #57

Earlier quoted context omitted.

It depends on how you use them. In my workflow, I work with the LLM to get the desired result, and I'm familiar with the system architecture without writing any of the code. I've written it up here, including the transcript of an actual real session: https://www.stavros.io/posts/how-i-write-software-with-llms/

Thanks for writing this up. I just woke up recently myself and found out these tools were actually becoming really, really good. I use a similar prompt system, but not as much focus on review - I've found the review bots to be really good already but it is more efficient to work locally. One question I have since you mention using lots of different models - is do you ever have to tweak prompts for a specific model, o…

I don't tweak prompts, no. I find that there's not much need to, the models understand my instructions well enough. I think we're way past the prompt engineering days, all models are very good at following instructions nowadays.

Re: LLMs can be exhausting

#114

Post by eucyclos »

galaxyLogic wrote: post #20
hombre_fatal wrote: post #5

Earlier quoted context omitted.

I think the upper limit is your ability to decide what to build among infinite possibilities. How should it work, what should it be like to use it, what makes the most sense, etc. The code part is trivial and a waste of time in some ways compared to time spent making decisions about what to build. And sometimes even a procrastination to avoid thinking about what to build, like how people who polish their game engine…

Right when you're coding with LLM it's not you asking the LLM questions, it's LLM asking you questions, about what to build, how should it work exactly, should it do this or that under what conditions. Because the LLM does the coding, it's you have to do more thinking. :-) And when you make the decisions it is you who is responsible for them. Whereas if you just do the coding the decisions about the code are left lar…

Hehe, speak for yourself- as a 1x coder on a good day, having a nonjudgmental partner who can explain stuff to me is one of the best parts of writing with an llm :)

Re: LLMs can be exhausting

#115

Post by esafak »

akomtu wrote: post #59
cglan wrote: post #3

I find LLMs so much more exhausting than manual coding. It’s interesting. I think you quickly bump into how much a single human can feasibly keep track of pretty fast with modern LLMs. I assume until LLMs are 100% better than humans in all cases, as long as I have to be in the loop there will be a pretty hard upper bound on what I can do and it seems like we’ve roughly hit that limit. Funny enough, I get this feeling…

You used to be a Formula 1 driver. Now you are an instructor for a Formula 1 autopilot. You have to watch it at all times with full attention for it's a fast and reckless driver.

You're being generous to the humans; we're more like Ladas in comparison.

Re: LLMs can be exhausting

#116

Post by mlaretallack »

olejorgenb wrote: post #42

I find working more asynchronous with the agents help. I've disabled the in-your-face agent-is-done/need-input notifications [1]. I work across a few different tasks at my own pace. It works quite well, and when/if I find a rhythm to it, it's absolutely less intense than normal programming. You might think that the "constant" task switching is draining, but I don't switch that frequently. Often I keep the main focus…

Yes, I follow the same sort of pattern, it took a while to convince myself that it was ok to leave the agent waiting, but it helps with the human context switching. I also try to stagger the agests, so one may be planning and designing, while another is coding, that way i can spend more time on the planning and designing ones and leave the coding one to get on with it.

Re: LLMs can be exhausting

#118

Post by bgdkbtv »

I think that if you build a solid foundation of your project and can articulate somewhat well what it is you want it to do, then you can expect a pretty good result. I typically limit my prompt to a specific file, often specify the lines and outline some of the logic and add references to other files where necessary. Then, Claude gets just enough context to to do what I want it to do.

Another trick I learnt is you can ask Claude to ask you comprehensive questions for clarification. Usually, it will then offer you a choice of 3 options per question that it might have and you can steer it towards the right implementation.

Re: LLMs can be exhausting

#119

Post by retsibsi »

razorbeamz wrote: post #32
jatora wrote: post #28

Earlier quoted context omitted.

You need to learn to use the tool better, clearly, if you have such an unhinged take as this.

The only people who use LLMs "as a tool" are those who are incapable of doing it without using it at all.

> The only people who use LLMs "as a tool" are those who are incapable of doing it without using it at all.

Do you mean that? It's clearly false, but I don't want to waste time gathering famous-person counterexamples if you already know it's a huge exaggeration at best.

Re: LLMs can be exhausting

#120

Post by apsurd »

jumploops wrote: post #103

A lot of these resonate with me, particularly the mental fatigue. It feels like normal coding forced me to slow my brain down, whereas now my mind is the limit. For context, I started an experiment to rebuild a previous project entirely with LLMs back in June '25 ("fully vibecoded" - not even reading the source). After iterating and finally settling on a design/plan/debug loop that works relatively well, I'm now expe…

What do you mean doing it the "right way" from the get-go, as then paired with more features, ballooning projects, and never launching?

Is that why it's in quotes because it's the opposite of the right way?

If there's one thing I learned in a decade+ of professional programming, it's that we can't predict the future. That's it, that simple. YANGNI. (also: model the data, but I'm trying to make a point here)

We got into coding because we like to code; we invent reasons and justifications to code more, ship more, all the world's problems can be solved if only developers shipped more code.

Nirvana is reached when they that love and care about the shipping of the code know also that it's not the shipping of the code that matters.

Post reply on HN