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

Ask HN: What was your "oh shit" moment with GenAI?

news.ycombinator.com

Post reply on HN
Print view View original

841–850 of 1001 posts

Re: Ask HN: What was your "oh shit" moment with GenAI?

#841

Post by stevefan1999 »

vibe coding a C compiler and doing a parser rewrite, all of a sudden it dropped all its code that was refactored to use a token stream, reverted back to using string symbols (that is a huge refactor since it involved parser combinator and turning it from string to logos and eat whitespaces is no easy feat). I almost shitted my pants and tell Opus to stop and fuck off, ask him to recover the code from the context window, but luckily it was git stahed. It scared the shit out of me.

During the process I learned a lot more about giving a chance for LLM to do commit after its work because it will sometimes just give up. Also learned a hard lesson on C preprocessor and why tokenization is necessary.

Re: Ask HN: What was your "oh shit" moment with GenAI?

#842

Post by AussieWog93 »

NamTaf wrote: post #794
AussieWog93 wrote: post #268

Literally just last night I have Claude Code the following prompt, verbatim: "Whenever I launch Kodi on my Chromecast 4k, it crashes. I think this is related to a plugin or skin. It goes away for a bit if I clear cache but will eventually come back. Can you connect to the device via adb (I've run adb connect already), and debug exactly where it's crashing? Once you've done that, propose a solution. If this requires d…

You know, I've had this exact bug for some time on a Fire Stick 4K Max Gen 1 (similarly anaemic). I figured it was storage or RAM pressure causing the problem as I could see both were close to the limit, but didn't realise it was OS swap/cache eviction removing critical files as it only happened to Kodi. I assumed Kodi just didn't really clean up after itself fully and after a bunch of heavy uses some cruft built up,…

I don't really know exactly how many tokens it used, but at no point did Claude Code auto compact. So that would be roughly ~500k output?

Re: Ask HN: What was your "oh shit" moment with GenAI?

#844

Post by dspillett »

jackdoe wrote: post #593
Zopieux wrote: post #583

Earlier quoted context omitted.

Don't leave us hanging, what was the issue?

I will never know.

This is one of the reasons why I'm avoiding it.

I see the people around me care that little, when I see them at all as I'm effectively on remote teams most of the time (and soon to be fully on remote teams almost all of the time if I don't leave) and I don't want to be that nor do I want to be the only one, or one of the few, who gives a crap.

I know that if I continue to avoid it I'll have a fine future in the hospitality industry, with dicking around with tech as at best a hobby, but I'm hating tech work because of the everyone-is-remote business anyway so that is likely be better for my mental health. Better off skint but alive… Good luck to the rest of you.

Re: Ask HN: What was your "oh shit" moment with GenAI?

#845

Post by dubed1505 »

I am starting to play Pokémon Gen 1 on game boy with my kid that just learned to read.

She traded one of his Pokémon for me to train, and my ezflashjr microsdcard corrupted. I was kind of embarrassed so I've plugged it anyway and asked glm5.1 to extract the Pokémon.sav file if it can. It turned for a bit but was able to get it and I was able to create another SD card and give back that Pokémon intact.

Re: Ask HN: What was your "oh shit" moment with GenAI?

#846

Post by evanb »

I'm a professor of physics; my research area is computational quantum field theory. I was beginning a new approach for a certain kind of model. I know the model has not been simulated before (a collaborator has just constructed it for the first time using in-field knowledge developed in the last year).

I've been steadily more impressed, but the real startling moment was earlier this week, I could show that in a particular operation I had a bug (some identity wasn't satisfied) but I couldn't understand why. In one try Claude Code grokked my code, explained the problem to me (there were some dimension-dependent minus signs that needed to be computed), and fixed it.

Re: Ask HN: What was your "oh shit" moment with GenAI?

#847

Post by OpFour »

I started using different LLMs and gguf files locally then graduated to Gemini, then Claude code. I created about 12 different apps and projects, some web based for my catering business, several old games from the early 90's, and a secure communications apps and an app to protect vulnerable people who found themselves in difficult or undesirable situations. This trip has been nothing BUT fun for me! My ADD addled brain loves coming up with random thoughts for apps and fixes for older problems that I simply haven't had to time to learn about and address. I then build them for fun... I LOVE this stuff!!!

Re: Ask HN: What was your "oh shit" moment with GenAI?

#848

Post by naikrovek »

jerryoftheyear wrote: post #399
xtracto wrote: post #389

I probably will be burned for this, but with the help of an LLM I wrote a tiny program that captures video from a browser screen (Xbox live online FPS game), passes the video images through a small trained NN that recognizes people forms and presents the video on another screen. That way I can place a green overlay on enemies and they are easier to see on PVP matches. All that in around 100 lines of code, including t…

I'm curious, what amount of input lag does this introduce?

None.

It introduces output latency, not input latency.

Re: Ask HN: What was your "oh shit" moment with GenAI?

#850

Post by wcchandler »

I’m a working professional but going back to school for my Masters. The amount of students using GenAI for everything is mouth gaping. At first I thought it’d be popular in the work force, partly through forced usage. But students (those just out of undergrad) are eating it up. Hitting their limits. Scheduling their work around it. And turning in the slop straight from the outputs. Nauseatingly, the instructors aren’t discounting their work. Our grades show averages, and it’s obvious those with AI answers are receiving high marks.

Surprisingly, instructors are also leveraging it. For their grading. For their feedback. For their communications. I even got a note that had the heading “here is a ready to post announcement for canvas, written in your voice”

I’m floored. This is the next generation of workers. It reminds me of those who started using Google correctly, back when I was in undergrad, ~20 years ago. AI is here and it will be dominant, no matter how bad it becomes.

Post reply on HN