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

631–640 of 1001 posts

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

#631

Post by mistersquid »

Zopieux wrote: post #583
jackdoe wrote: post #560

I have had many, but the last one was quite funny: It fixed my printer after dist-upgrade and separate chrome upgrade, the printer worked everywhere but not in chrome. After 30 years of using linux I didn't even want to know what is wrong, is it colord again? dbus + cups issue? I completely accepted that I wont be able to print from chrome for a couple of months until next update. I just ran it in dangerously-skip-pe…

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

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

A: Linux

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

#632

Post by mft_ »

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…

Would you either share the code, or describe the approach? I’ve asked LLMs how to do something similar a few times recently, and received several different potential approaches. I’m still no clearer which route to take!

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

#633

Post by jFriedensreich »

I had a pretty involved cross module state bug with complex dependencies and also reactivity issues interleaved. I tried fixing it multiple times manually with 4h time box as well as claude models up to opus 4.6 high and codex 5.3 all which failed. When the GPT-Pro model came out i heard it was not supposed to be an everyday coding model but tried anyways as it looked impressive. It took a single 8h run burning 200$ with doing nothing but occasionally waiting for test runs or me writing “continue”. After 8 hours, and fearing i wasted the money, the bug was consistently fixed, not just one edge case that triggered the behavior.

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

#634

Post by jFriedensreich »

jFriedensreich wrote: post #633

I had a pretty involved cross module state bug with complex dependencies and also reactivity issues interleaved. I tried fixing it multiple times manually with 4h time box as well as claude models up to opus 4.6 high and codex 5.3 all which failed. When the GPT-Pro model came out i heard it was not supposed to be an everyday coding model but tried anyways as it looked impressive. It took a single 8h run burning 200$…

ps the refactoring it did as part of the solution was a bit verbose and had a few abstractions i knew would not be needed and asked it to remove but were solid otherwise.

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

#635

Post by justinmarsan »

Being self taught, there are lots of things I never formally learned, rules I know from the rule of thumb, and not the deeper knowledge... So I set out to learn the root of what can be used to measure good robust code... Spent an hour asking lots of questions, learning about LCOM, Halfstead, why circular dependencies are bad, and so on...

The next morning I figured the same LLM could compute that on my code, so I asked it to make an agent to do so, and report issues to me...

And then I ran that agent with next to no changes on a feature that had grew organisally over the last months, that I knew was messy and sometimes difficult to work on, despite being unable to precisely say why... And it did tell me exactly why, and proposed changes to improve stuff, and then implemented them...

Up until that point, I'd felt like the LLMs always produced bad code, that worked for a specific feature but often broke stuff or evolve poorly over time. Then I realized if you had the LLM do code improvements, it could do that fairly well too...

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

#636

Post by magpi3 »

p0w3n3d wrote: post #626
awbvious wrote: post #592

Not sure, but I can tell you what my "oh s** astroturfing is so bad, it's even in Hacker News" moment. And if I learned GenAI was used to make some of the astroturf, that's more an "ah s* “ than an "oh s* “ thing. I mean, the prominence, ubiquity, and breathlessness. One out of three, sure. Two out of three, maybe. And some corpo shilling definitely happens here. But this is like, well, covering an entire area with a…

TIL what astroturfing is. Moreover I now understand that it is almost impossible to tell the robots from the people in the internet

I've thought this for a while: a day will come when the anonymous internet becomes a thing of the past. It really feels like we are already there but not everyone realizes it yet. What's the point of conversing with someone on the internet (like right now) if you can't tell the difference between a bot and a real person? And it will only get worse.

But what does an anon-free internet even look like? Is it even possible? Or will all online content eventually be considered untrustable and worthless? You can see a world where newspapers (online or otherwise) make a comeback simply because of the need for a trusted gatekeeper (which is what I imagine made them valuable in the first place). It's wild to think about.

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

#637

Post by xyzal »

awbvious wrote: post #592

Not sure, but I can tell you what my "oh s** astroturfing is so bad, it's even in Hacker News" moment. And if I learned GenAI was used to make some of the astroturf, that's more an "ah s* “ than an "oh s* “ thing. I mean, the prominence, ubiquity, and breathlessness. One out of three, sure. Two out of three, maybe. And some corpo shilling definitely happens here. But this is like, well, covering an entire area with a…

YC indisputably has a financial incentive for AI sentiment to be positive on HN. The structural conflict of interest is worth being aware of.

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

#639

Post by jerieljan »

I remember in the early days when I was just trying out ChatGPT on a phone for the first time (this was around GPT-3.5? GPT-4o?) and snapping a picture of our fridge that's full of magnet souvenirs and asked it to identify all the places we've been in and it gave a nice list of what it saw and the places that were featured.

Did it get it fully right? No. But it was one of those "oh wow, you could do that?" moments for me. There's obviously a lot more "oh shit" moments as time went on, but it was a neat little moment.

Post reply on HN