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

Stop Telling Me to Ask an LLM

blog.yaelwrites.com

Post reply on HN
Print view View original

71–80 of 154 posts

Re: Stop Telling Me to Ask an LLM

#71

Post by jagged-chisel »

BobbyTables2 wrote: post #57
Animats wrote: post #21

Earlier quoted context omitted.

When I post a technical question in Forums, I usually add something like "Tried Copilot, got useless answer ...". The trouble with asking an LLM is that there are a huge number of people (this predates LLMs) who post answers on forums along the lines of "turn it off and turn it on again" LLMs pick that up as the consensus solution.

I actually hate reading posts that go “I can’t understand/fix this problem. Tried LLM…” To me, such screams “I’m too lazy to do anything more than ask a LLM. I’ve tried nothing and I’m all out of ideas” Show me you put a modicum effort and aren’t just looking to be spoon-fed the content from the first Google result that would have been found.

I get exasperated with the inexperience that I have run across for decades. Yes, I frobnicated the frobnitz, I transmogrified the bit twiddler, I wizzled the wobnosticator, (and this decade, I talked the three LLMs), and the problem still exists. What I really need to know is how the transmogrification affects frobnication, but no one has ever touched that configuration.

“Why would you even want to do that?”

I dunno, man, it’s the job I was given. Do you know or not? No. No one does.

I take a week to figure it out, I come back to the forum to post my response, and it’s automatically closed as off-topic.

*sigh*

Re: Stop Telling Me to Ask an LLM

#73

Post by anon7000 »

hoppp wrote: post #15
theorchid wrote: post #5

Earlier quoted context omitted.

— I thought about this and found there are options A, B, and C of doing X, I like A more but C is the fastest; what do you think? — Ask Claude.

Its a way to say I don't care, don't waste my time

Well, it’s fucking annoying. When I’m asking a question and I put time into understanding the context and problem space, and already did some analysis with AI, I’m looking for a human opinion. I want my colleagues who know stuff to use their experience and their brain for a second to help the team.

I don’t need Claude to give a second opinion on something that Claude already ran through. It’s fucking useless and it’s a huge blind spot.

This shit happens when everyone in an organization is expected to use Claude to answer questions and do the initial investigation / analysis. Yeah, I did that. Now let’s get to work as humans and provide our expertise, and not turn it into an AI circle jerk.

Re: Stop Telling Me to Ask an LLM

#74

Post by qarl2 »

While "I'm busy" might be true, "Ask Claude" is more helpful.

Maybe the people in your life are just trying to be helpful instead of effectively saying "Go away."

But hey, sure, it's AI so you should definitely hate on them. FUCK AI!!1!! AMIRIGHT?!?!

Re: Stop Telling Me to Ask an LLM

#75

Post by anon7000 »

amelius wrote: post #69
mcv wrote: post #34

I completely agree. Replying with "ask Claude" feels to me like admitting you've lost control over the subject matter and don't know anything about it or at least don't trust your judgement anymore. It feels like saying you're replaceable by AI. It makes sense to hate and despise that answer. And yet, I'm not 100% sure I've never used it myself. I will have to watch out for that.

> Replying with "ask Claude" feels to me like admitting you've lost control over the subject matter Huh, what if I don't want to spend time answering a low-effort question? I will have a look if the default answers/approaches don't work.

Then don’t answer it? Or just give a seconds worth of context into why you think it’s not important?

Re: Stop Telling Me to Ask an LLM

#76

Post by Barbing »

apical_dendrite wrote: post #27
theorchid wrote: post #12

I once wrote a similar essay on this topic. When I talk to people, they forward my questions to AI and send me the AI’s answer: https://orchidfiles.com/im-tired-of-ai-generated-answers/

This drives me absolutely crazy. My colleagues send me huge PRs to review (say 2000+ lines). I don't just paste comments from the LLM, I ask the LLM to review it, but I also review it myself. I only include ideas from the LLM if I think a) the LLM has gotten the issue right and b) it's worth having the developer take the time to address the issue. I always write the comment myself so I can add relevant context and pu…

How do ya feel about altercations at work? If like most, then hope your colleagues find your post & decide to stop (without realizing you’re their lead!).

Re: Stop Telling Me to Ask an LLM

#78

Post by Barbing »

XorNot wrote: post #19
hoppp wrote: post #15

Earlier quoted context omitted.

Its a way to say I don't care, don't waste my time

Which is funny because a huge number of people post this in responses to online asynchronous messages, on public forums, when they could also do literally anything else - like close the browser tab.

Wellll lots of those people you’re referring to are human, and when have we ever let it be?!

Re: Stop Telling Me to Ask an LLM

#80

Post by SpicyLemonZest »

t-writescode wrote: post #68
apical_dendrite wrote: post #27

Earlier quoted context omitted.

This drives me absolutely crazy. My colleagues send me huge PRs to review (say 2000+ lines). I don't just paste comments from the LLM, I ask the LLM to review it, but I also review it myself. I only include ideas from the LLM if I think a) the LLM has gotten the issue right and b) it's worth having the developer take the time to address the issue. I always write the comment myself so I can add relevant context and pu…

Beyond mirroring the engineering practices that you yourself want to see other people perform, have you found any techniques to get people to … in short, do their job again? Understand context, understand what they did, why they did it, what they’re doing, etc. The +/-2000 line MR was bad when humans wrote it. It’s way worse when the human didn’t even write or read it. And just vomiting automated CodeRabbit talking p…

For me the trick was just leaning all the way into it. I had a residual idea that if someone sends me a 2000 line PR, 10 page design, etc., that this represents some concrete investment of time and effort that deserves my careful consideration. And it just doesn't anymore.

I have one project where there must be hundreds of pages of design proposals I have not read and will never read, because the author really likes having Claude generate complete design proposals based on incomplete understanding. So every week or two he sends me a new one, I spend 30 seconds skimming it, and then I tab back to Slack to ask him to explain.

I don't like working this way, but you know, I don't like doing rollouts either. It's certainly better than being a human rubberstamp.

Post reply on HN