I think I have LLM burnout • Hacker News Board

Re: I think I have LLM burnout

#211

Post by jaynetics » Thu, Jul 09, 2026, 6:07 AM UTC

sefrost wrote: post #94

dpc_01234 wrote: post #13

I don't think I have a "burnout", but LLMs are really exhausting due to amount of pressure they generate. No one is really pushing me to increase my workload, but at every moment there is always something ready, done by my clankers or clankers of other people that I could be unblocking. In the past (before LLMs) it was already hard to keep up, but now it feels like there's 10x more things waiting at any given time, a…

One of the reasons they exhaust me, is that it's always "one more prompt" to get a UI correct. It's often just slightly off, but it can take 5-10 mins sometimes to rework something. It has led to me working much longer hours. I think this is in part because I am one of the software engineers that always liked building products more than writing complex software. So, I am driven by the feeling of creating something. A…

It's a bit paradoxical to use AI to increase productivity, and then feel the need to work longer hours to fully actualize said productivity.

But it's probably a common feeling. I wonder if we'll see an increased number of people burn out in the serious, medical sense.

Re: I think I have LLM burnout

#212

Post by layer8 » Thu, Jul 09, 2026, 6:10 AM UTC

intended wrote: post #184

UncleOxidant wrote: post #104

Earlier quoted context omitted.

> done by my clankers or clankers of other people I'm getting so many requests to review LLM-generated documents - planning docs, docs intended for end-users, project docs, business plan docs. A team member sent me a zip file with about 30 LLM generated documents in it the other day and asked if I could review them right away. And a lot of it was just repetition and/or stuff that was just out of left field, made-up,…

Rate of generation/Rate of verification is a proxy for signal to noise ratios, just for work. That ratio has changed, and verification is the hard part. Verification is the point of all markets (and a decent part of human civ as well). And review isn’t cost less - https://en.wikipedia.org/wiki/Ironies_of_Automation

> Rate of generation/Rate of verification is a proxy for signal to noise ratios

Hopefully you mean Rate of verification/Rate of generation.

Re: I think I have LLM burnout

#213

Post by globular-toast » Thu, Jul 09, 2026, 6:12 AM UTC

I feel this is coming for me. I now have three people generating code using LLMs who have no experience or real understanding of what they're doing. Nor do they have a strong desire to learn, but how could they anyway? I learnt by screwing up time and time again, but each time I went back and learnt why and next time did it better. It would be bad enough if I was managing 5 different agents myself, but it's managing 5 people who are operating 5 agents.

Re: I think I have LLM burnout

#214

Post by globular-toast » Thu, Jul 09, 2026, 6:13 AM UTC

springtimesun wrote: post #208

I am feeling very tired. Since I’ve started working with LLMs my output as a solo dev has easily gone up 20x. I’m closing client projects including ones that previously would have been far too ambitious to take on alone. Long running codebases are getting features that have dragged out for months or been sitting in the planning stages for even longer. And overall quality is way up now with more complete (and honestly…

Classic signs of addiction.

Re: I think I have LLM burnout

#215

Post by nprateem » Thu, Jul 09, 2026, 6:14 AM UTC

throwaway_7274 wrote: post #191

block_dagger wrote: post #25

I've started feeling slightly physically ill when I read Opus output for hours straight. This article rings very true for me. I've started complaining about it with my team; at least have a personal style guide in your agent rules that eliminates emdashes, the "it's not X, it's Y"s, the long lists of modifiers before the noun, using the word "land" to mean finish, etc. I hope this is just a phase of adolescent LLMs.

Me too. It feels like I’m taking psychic damage from reading so much of this stuff. Contrary to the theory that it’s “just the contract workers’ Nigerian English,” I think the models are developing an ultra-terse hyper-stylized dialect of their own under RL pressure. They seem to be writing increasingly in _code_, and I don’t mean computer code. The words don’t mean quite what they mean to humans.

Over the last few days with fable I've found it at times incomprehensible, terse word salad. It also invents phrases assuming I'll understand (but that could be because it's reusing terms in the codebase I no longer remember).

I've often had to paste its output back in to ask it what it actually means. Weird.

I think the main thing is just fatigue. There's so little variety. Each model has its preferred idiolect which everyone becomes tired of due to ubiquity. That's the worst part. It's like always eating fast food.

Re: I think I have LLM burnout

#216

Post by datsci_est_2015 » Thu, Jul 09, 2026, 6:17 AM UTC

jaggederest wrote: post #33

dools wrote: post #18

Earlier quoted context omitted.

Don’t read the code!!

I actually dispute this, I read all the code, the core thing people have to give up is not "reading the code" per se, it's giving up on "that's not how I would have done it". When you see a perfectly clear function or object that just isn't your style, you have to accept it and move on. Where there are concrete concerns, or it's unreadable, demand excellence, but treat it like a coworker, not an IDE.

> When you see a perfectly clear function or object that just isn't your style

is the critical caveat to “that’s not how I would have done it”. Basically, choose your battles because we all have limited bandwidth. So, it’s not really a perfect binary, but a taste that you personally develop.

Re: I think I have LLM burnout

#217

Post by ramon156 » Thu, Jul 09, 2026, 6:17 AM UTC

Speak for yourself! This is my third week on SSRI medication and I am the zombie the CEO wants me to be! /s (well, only half /s)

At work, I ended up doing other chores, getting a lot more involved in projects I wouldn't even care to touch. Turns out it's kinda fun being the source of truth at work. I now have a clear sketch of what the company has done and what we can improve on.

Being able to fill in the gaps at a company that doesn't do much feels like a company within a company. Sure, its not Silicon valley, but it's still fun! And job security is guaranteed if you do a bit more than just play the ticket factory

Re: I think I have LLM burnout

#218

Post by chairmansteve » Thu, Jul 09, 2026, 6:28 AM UTC

hoppp wrote: post #2

Tell the llm to answer like a cavemen, if llm talk like cavemen, the answers become shorter and more compressed. https://github.com/JuliusBrussee/caveman It's for getting it to output shorter answers, but also could help with your burnout.

Works for me.

Re: I think I have LLM burnout

#219

Post by layer8 » Thu, Jul 09, 2026, 6:38 AM UTC

gitaarik wrote: post #178

16bitvoid wrote: post #92

Earlier quoted context omitted.

We get it, you don't have a passion for the act or the craft, just the end result, but I'm absolutely sick of hearing it all over this site as if it's a universal truth that some of us just don't recognize yet. Sorry, some of us have a joy for programming where the how is just as important, if not more so, than the what and the why. No matter how much people proclaim that the how doesn't matter to them , it isn't goi…

But ultimately you got into this craft to solve a problem. That is how the craft developed. And when you build a very complex elaborate system, it can still have interesting technical challenges, even for a developer with AI. You should shift your technical insight to a higher abstraction level, where the AI cannot help anymore.

What’s interesting to me is reasoning about the problem and its implementation. And that doesn’t stop at any abstraction level. Reasoning in the small is just as important as reasoning in the large. And the issue with LLMs is that their capacity for sound reasoning is limited. They are sloppy on any level. You can’t get them to be thorough and dependable in reasoning, regardless of the abstraction level.

Re: I think I have LLM burnout

#220

Post by dmichulke » Thu, Jul 09, 2026, 6:41 AM UTC

bratbag wrote: post #190

jampa wrote: post #118

Earlier quoted context omitted.

I feel the same way about consumer AI tools now. Gemini and ChatGPT have been abysmal lately. They can no longer be relied on to do multi-turn searching and thinking. Before, they could stay in thinking mode for more than 7 minutes. For example, "find a source for this claim" would search, analyze, and self-adjust the query. Nowadays, even if I push for it, I cannot make these tools work for more than 30 seconds befo…

At one point we considered adding artifical delay to responses because irrational users dont trust something that finishes fast, even if its the same quality. How empirical are your comparisons of new and old outputs?

Counterpoint: Reels apparently are still addictive