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

521–530 of 1001 posts

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

#521

Post by blablabla123 »

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…

So I'm scrolling through this Ask HN and this is now the 3rd similar problem. Would you mind adding more details as well as the patch? Perhaps as a gist if it's unfinished?

I mean just googled https://www.google.com/search?q=kodi+crash+chromecast+4k I'm getting really a lot of issues such as https://forum.kodi.tv/showthread.php?tid=381239

It seems to be a quite common problem. Are you sure it was the rube goldberg fix and not a more mundane solution? Such as pulling in someone's fork from GitHub or just clearing the cache on a loop?

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

#522

Post by ben_w »

userbinator wrote: post #462
jodacola wrote: post #225

Earlier quoted context omitted.

Very similar thing this week, and an interesting story to go along with it! I called my normal HVAC company for my rental home because the tenant reported the AC wasn't cooling the house. When I called, I got one of the latest AI voice assistants to help me, and it was an awful experience and I ended up not hearing back after the assistant told me the office would call me back. So, I went over to the house and used C…

Even before AI, YouTube was full of videos on these topics.

When I was a kid, if I didn't know how to spell a word and asked the teacher, a common answer was to tell me to look it up in the dictionary.

As words in a dictionary are sorted alphabetically rather than phonetically, this is unhelpful.

YouTube videos have the same kind of problem, in that you can only easily find the video explaining which dielectric unions suit your problem when already know what those are (to use an example that I had to ask ChatGPT for because I have no plumbing experience even if I did know about galvanic corrosion and therefore immediately understood why they're important once I saw the name).

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

#523

Post by dash2 »

I asked it to prove the theoretical result in a (published, prize-winning - though not really for the theory) academic paper of mine. The proofs hadn’t been that hard objectively, but they’d taken at least a week. I fed it the model. It got the correct basic results in about 5 minutes.

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

#524

Post by amstan »

dash2 wrote: post #523

I asked it to prove the theoretical result in a (published, prize-winning - though not really for the theory) academic paper of mine. The proofs hadn’t been that hard objectively, but they’d taken at least a week. I fed it the model. It got the correct basic results in about 5 minutes.

Are you sure the models did not have your exact solved proof already in their dataset?

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

#525

Post by fsniper »

The are lots of small "oh shit" moments for me. First interaction with an llm was already magical.

"This shit can emulate understand language, find a solution, answer it into words" .

Then came realisations it's not limited to single human languages, you can ask in one language and it could answer in another. It's also capable of understanding and generating code. Not only that, it's better than most humans for that. It can hear, it can see, it can paint, it can do music, it can sing.. It can combine, give a picture, ask for a music from that picture. Give a video, get software. It can mix and match.

After that came improvements, - no The revolutions - It started as a 4 year old with encyclopedic knowledge. It knew but could not convey, could not make sense sometimes. Was incorrect most of the time. Blubber. In a few years it matured to impeccable levels. It now can relate information with a lot of clarity, and it's less and less wrong. Nearly no hallucinations. It can do maths! Correct maths! Maths that I could not even my life depends on it. It's getting to a stage that it can proof where humans failed.

I am getting "oh shit moments" day by day.

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

#526

Post by nkoren »

userbinator wrote: post #462
jodacola wrote: post #225

Earlier quoted context omitted.

Very similar thing this week, and an interesting story to go along with it! I called my normal HVAC company for my rental home because the tenant reported the AC wasn't cooling the house. When I called, I got one of the latest AI voice assistants to help me, and it was an awful experience and I ended up not hearing back after the assistant told me the office would call me back. So, I went over to the house and used C…

Even before AI, YouTube was full of videos on these topics.

Yeah, and with 95% of those videos, there'll be something they gloss over which I don't understand; or I'll have a concern which they don't address; or, conversely, they'll assume that their target audience was born in the 15th century, and spend 20 minutes building up the context, when what I really needed was about 12 seconds.

With an AI, I can say "I don't understand that part, can you explain more?" Or "what about this concern I just thought of", or "I already know almost enough about this, I just need this one gap filled in." It's an objectively better experience.

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

#527

Post by sajithdilshan »

comment0r wrote: post #509
sajithdilshan wrote: post #192

For me it was last February or so when I started using Opus. But today I watched a video from Andrej Karpathy on YouTube on how LLMs works and my illusions got completely shattered. Turns out they are a glorified autocomplete. All the engineering happens actually on the harness

Which video, please?

It’s this one https://youtu.be/7xTGNNLPyMI?is=yld6dPGAJ1HvjDsw

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

#528

Post by mft_ »

darksim905 wrote: post #434
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…

I know this isn't apples to apples, but given that I can't get Copilot or other tools to view a simple profile page on LinkedIn makes me curious/skeptical how this would work in this depth. I'm sure it's possible but I'm curious what the skills and toolchains involved were for you to get all that to work.

To expand on another answer, it’s all about the harness. Different harnesses (Claude Code or Cowork, Hermes, OpenCode, Pi, etc.) offer different default tools, system prompts, and ultimately approaches. (IME the corporate CoPilot app is terrible - basically a chat interface.)

I’m currently using Hermes for local LLMs - seems pretty good so far.

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

#529

Post by fsniper »

philovivero wrote: post #221
jachee wrote: post #173

I haven’t had that yet. I tried again this week, and CoPilot Plan Mode read the same 5-line markdown file 18 times over the course of 5 minutes of churning on a simple request, then provided zero value over what I posed in the request itself, and hallucinated things about my terraform repo that were just flat-out wrong. As an Infrastructure/Cloud engineer, I’m far from worried about AI coming for my job.

Weird. I had LLM (Claude) work with OTF to generate an entire infrastructure HCL (from existing). It built a very nice project that seemed idiomatic from my experience. Then used it over the course of several hours to refactor it to take variables/inputs for everything, then over a few days got it to a state where it would create entire new environments "equivalent" to the original environment. Days because you know.…

I am with you on this. I am a good, and experienced infra engineer. And I feel like - no know that - llm can probably replace me if a good operator handles that.
Post reply on HN