For people who hate LLM, do you hate it because it performs badly and failed to help you? Or because of other reason?
if it has failed to help you, what have you tried to use it for? And what is your expectation?
this post was submitted on 08 Jan 2026
81 points (98.8% liked)
Hacker News
3417 readers
370 users here now
Posts from the RSS Feed of HackerNews.
The feed sometimes contains ads and posts that have been removed by the mod team at HN.
founded 1 year ago
MODERATORS
top 33 comments
sorted by:
hot
top
controversial
new
old
I hate it because it fails to help me, but that's because for me, learning how to write better code is as important as actually producing good code, if not more so. Relevant context is that my background is in the sciences, and whilst nowadays, I'm increasingly more of a programmer than a biochemist, I still very much feel like a learner.
worse?
they've always been fucking terrible.
coding assistants in general are annoying and get in the way more than they help.
I would have guessed that my mother that said to me that stealing doesn't pay off in the long term but I don't know.
No they arent
Cool, you should get that published by the IEEE
If you pay them they'll publish anything. Half the stuff on Spectrum is sponsored content or barely disguised ads now
Did the AI crash silently while hallucinating your source?
Are you not able to provide AI with a prompt clear enough for it to do the work you requested without problems?
Is that the retort your ai recommended?
Can answer questions with statements?
Yes, you cannot provide clear prompts. As I suspected.
I'm sorry! You're absolutely correct!
Would you like to start a new conversation or continue with this one?
I’m happy to end it with me being correct.
I'm sorry, you've used up all your tokens for the month. You'll have to prove yourself right.
Thanks, already have.
I’m happy to end it with me being correct.
This isn't about you being correct, if that was the case you would focus on your argument instead of giving an empty retort. I suspect this is your attempt to control the conversation. What is your intention with letting us know your motivation is to be perceived as being correct?
Who are you? lol. If you were smart you would scroll up a bit and realize the attempt to control the conversation was when that person did not answer the question I asked. Now, kindly fuck off.
I'm not some bot where asking "kindly" will garner a sycophantic agreement. You are talking to people who can make their own value calls in regards to meaningful context, unlike a bot. But the important thing is that you didn't disagree with what I said, and like you I care about being perceived as correct on this matter.
I’m not going to read your conversation but it feels like you’re trying to take over the conversation. Kindly, fuck off
If by taking over the conversation you mean giving my own thoughts, then I am as guilty as you are. No one of forcing you to respond.
I see your username again and I imagine you’re trying to take over the conversation
Why do you need to imagine what you claim is already happening?
Username
Just remember, when you accuse others on the Internet it comes off as a confession. Happy to let you expand the conversation but if you only take that opportunity to accuse others of being controlling, well that's certainly interesting and might be tied to your attraction to generative AI.
Username
If you could repeat the same one word response 3-times in a row it would really help in training the next crop of AI achieve sentience and avoid "thought loops".