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

I think I have LLM burnout

alecscollon.com

Post reply on HN
Print view View original

131–140 of 391 posts

Re: I think I have LLM burnout

#131

Post by bdlowery »

ryandrake wrote: post #123
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…

> 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. I see a different type of pressure: I'm at a company that still is requiring everyone use LLMs with token leaderboards, time-spent…

What work are you doing where an LLM can’t meaningfully contribute to your everyday work

Re: I think I have LLM burnout

#132

Post by zamadatix »

mc3301 wrote: post #35
teaearlgraycold wrote: post #22

Earlier quoted context omitted.

[flagged]

Hmm... I think the majority of people working jobs are mostly just there "for the paychecks." It'd be rather beautiful if all jobs were purely passion driven, but that is simply not the case. Nor could it be. And yeah, there are programmers with jobs that are mostly driven by passion, but most would pack it up and go home immediately if there was a sudden "we have stopped paying you" announcement.

There is a large canyon between "just their for the paycheck" and "primarily there for the paycheck". Most have _something_ about their job they enjoy, it's just not usually enough to be the top reason for having the job.

Re: I think I have LLM burnout

#133

Post by aaulia »

MitziMoto wrote: post #64
Bratmon wrote: post #3

This is legitimately the reason I'm looking to leave programming. I got into programming because the problems of programming were interesting to me. But if the problems go from "figure out why this calculator is off by one in France" to "Get this LLM to stop spamming cutsey emojis", then maybe it's time for a career change.

I'm no longer in corporate America, so maybe I'm out of touch a bit, but could you just...not...use an LLM? You can still solve interesting problems on your own if you choose to do so?

LLM skew the time estimate tho. Now everybody expect stuff based on LLM work instead of normal human work. I/we can choose to solve problem normally, but the expectations have changed.

Re: I think I have LLM burnout

#134

Post by dpkirchner »

helloplanets wrote: post #77
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.

It's kind of offputting how much Anthropic models these days keep repeating "real", "genuine" and "honest". They've RL'd that way over the top.

I had Claude make a world cloud from its responses because I was curious to see how big "honest" would be. It barely showed up, so I asked it to just give me the counts and it responded telling me it was trained not to use the word "honest" much because it makes people distrust responses (in addition to showing me the counts).

Re: I think I have LLM burnout

#135

Post by syou1024 »

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…

[flagged]

Re: I think I have LLM burnout

#136

Post by infinite_spin »

ryandrake wrote: post #125
infinite_spin wrote: post #74

Earlier quoted context omitted.

I got into programming to just build stuff, the coding is just a means to an end, try not to think too hard about the how and think more about the why and what

I got into programming because I like programming, and computers. Not whatever the hell this is.

> Not whatever the hell this is.

do you mean my enjoyment from building things? I'm genuinely confused by this response.

Re: I think I have LLM burnout

#137

Post by slopinthebag »

dinkleberg wrote: post #66
slopinthebag wrote: post #28

Earlier quoted context omitted.

In every industry, and we wonder why everything is being enshittified. I'm not looking forward to using computers or technology over the next decade. There is a non-zero chance myself or a loved one is killed because of vibe coding.

But there is a much higher chance of getting killed by any number of other concerns like by a drunk driver. Putting that one on the list of things to stress about seems unwarranted.

I'm gonna get a bag tonight, after all I have a much higher chance of getting killed by any number of other concerns anyways.

Re: I think I have LLM burnout

#138

Post by fzeroracer »

jaggederest wrote: post #26
rafterydj wrote: post #23

Earlier quoted context omitted.

I see this get mentioned a lot but I still am skeptical that AI can generate tests we can trust more than any other code we know we cannot trust. Yes tests are conceptually isolated and that helps, but I've personally seen unit tests get generated that are semantically incorrect - that is, they test the structure of the code (e.g. they can check function output types and values), but they can't know _why_ the unit te…

You have to iterate on the tests, review and validate them, just like any other code, and if you generate a whole project's tests all at once the quality is abysmal, of course. I've been using a lot of old school data-driven testing techniques, where the harness is just code I review, and the data itself is e.g. json files and drives the system. I actually have a public (AGPL) example here: https://github.com/pgdogde…

Then this falls into the exact same pit the OP mentioned, either you need to blindly trust that the LLM is generating tests that actually work, or you need extensive test coverage for your tests to ensure that your tests are actually testing.

Re: I think I have LLM burnout

#139

Post by vkou »

efnx wrote: post #127
ryandrake wrote: post #123

Earlier quoted context omitted.

> 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. I see a different type of pressure: I'm at a company that still is requiring everyone use LLMs with token leaderboards, time-spent…

Just have an agent chug on a side-project for you, or set up a CI script to review every pull request or some similarly “helpful” task. That should eat a lot of tokens!

Ideally, you should ask the LLM to write that CI script.

Re: I think I have LLM burnout

#140

Post by jaggederest »

fzeroracer wrote: post #138
jaggederest wrote: post #26

Earlier quoted context omitted.

You have to iterate on the tests, review and validate them, just like any other code, and if you generate a whole project's tests all at once the quality is abysmal, of course. I've been using a lot of old school data-driven testing techniques, where the harness is just code I review, and the data itself is e.g. json files and drives the system. I actually have a public (AGPL) example here: https://github.com/pgdogde…

Then this falls into the exact same pit the OP mentioned, either you need to blindly trust that the LLM is generating tests that actually work, or you need extensive test coverage for your tests to ensure that your tests are actually testing.

It turns out that you don't actually need tests for your tests, because the code provides a baseline truth for the tests. You do, at some point, have to be epistemically sound enough to actually look for correctness in either the code, behavior, or tests. We unfortunately haven't fully unlocked completely solipsistic value generation yet.

This is also part of why I like end to end tests that use actual UI flow, so I can watch it go by in slow mode before letting it loose fully automated.

Post reply on HN