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

181–190 of 391 posts

Re: I think I have LLM burnout

#181

Post by chrisandchris »

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!

> side-projects

Just be careful about any legal implication of doing side-projects during work with work-resources.

Re: I think I have LLM burnout

#183

Post by teaearlgraycold »

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.

"just here for the paycheck" vs. "here for the paycheck but also genuinely enjoy parts of the job" are miles apart.

Re: I think I have LLM burnout

#184

Post by intended »

UncleOxidant wrote: post #104
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…

> 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

Re: I think I have LLM burnout

#185

Post by digitaltinfoil »

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.

I had to tell it never to say "hand-wavey" ever again to me. But I agree, I hate the way LLMs phrase sentences.

Re: I think I have LLM burnout

#186

Post by intended »

nacozarina wrote: post #76
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…

LLMs drive the unit cost of cognition to zero. Therefore, you will exhaust yourself near-instantly trying to drive differentiated value out of cognitive work. Non-arbitrable labor is one safe haven: bending steel, drilling wells, running cables, flying drones, etc. Physical agency gets you a premium the clankers can’t (yet?) trespass upon. That’s why guys building data centers are making bank & job-hopping while the…

I’d scope it down further than cognition.

Cost of generation has been reduced, and is highly subsidized currently.

Cost of verification has effectively not changed. I’d say as a rule of thumb: verification is the tough part.

Our brains don’t fare well under constant review pressure. https://en.wikipedia.org/wiki/Ironies_of_Automation

Re: I think I have LLM burnout

#187

Post by soonnow »

woutr_be wrote: post #106

I’m currently doing a project with someone who only uses LLMs, and it’s exhausting and mentally draining. Whenever I give feedback on something, the answer is just “let me tell Claude”. The person has no understanding of how everything works, and most of the code reflects that. The other day he hardcoded in a demo mode, simply because he didn’t even know how to set up a local environment and set environment variables…

I'm the same as you. Very specific tasks. Just now I spent two hours in a conversation with claude code to change 5 lines of code that change a significant semantic.

On the other hand my buddy is spending $10k in tokens a day on agents to build something. He's a very smart guy, former developer so it's not just AI psychosis talking.

Still trying to figure it out. Not that I have $10k to spend.

Re: I think I have LLM burnout

#188

Post by 7xmohamed »

I saw myself throughout this blog post. It's a bit difficult to come to terms with because I chose this field because I genuinely enjoy coding and building things.

Even projects that used to be challenging enough to impress people with your skills can now be built in 10 minutes with AI just by describing what you want. It's an incredible shift, but it also changes how I think about the craft and what it means to be a good engineer.

Re: I think I have LLM burnout

#189

Post by helloplanets »

dpkirchner wrote: post #134
helloplanets wrote: post #77

Earlier quoted context omitted.

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).

I just did this on one .claude directory and >20% of the answers there included some variation of "real", "actual", "exact", "honest", "genuine", "valid", "true". ~15% in that directory contain some variation of "real", "genuine" or "honest". This is excluding thinking tokens, sub-agent output, etc.

Re: I think I have LLM burnout

#190

Post by bratbag »

jampa wrote: post #118
canada_dry wrote: post #68

The reason I'm getting LLM burnout is from dealing with the obvious neutering and opaque downgrading of all the top models. Prior to the last 12mos AI companies were hell bent on squeezing out the best results from mediocre models. But... now that the top models have progressed, those same AI companies have switched their efforts into reducing the computation (cost of a producing a result) as much as possible without…

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?

Post reply on HN