Live data from Hacker News

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

news.ycombinator.com

441–450 of 1001 posts

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

#441
ChatGPT reconstructing idiomatic Python source code from Python bytecode was definitely up there. That is not something humans have written a great deal about online. It requires simulating the Python VM.

I remember also having a massive wtf reaction to realizing that original ChatGPT was pretty good at decoding long random/unique base64 strings.

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

#442

I got early access to the pre-ChatGPT OpenAI API (actually by pinging someone from OpenAI who posted about it on HN). At work, we were setting up to play a livestreamed JackBox game for a charity event. This would have been in 2019. In a previous life, I'd been a writer for the original You Don't Know Jack game (the UK variant), where the job was to crank out as many funny quips about a topic as you could, and then u…

I don't know about JackBox or whatever, but the original You Don't Know Jack games are positive fun memories for me. Thank you

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

#443
It was the release of Stable Diffusion and its source code.

I spent the next few days tinkering with my own Stable Diffusion implementation. I never got it past outputting total nightmare fuel, but it was fun!

To this day I think of the process as like baking pizzas in a sequence of pizza ovens

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

#445

My furnace went out during the 2025 holiday and I couldn't get an appointment with a repair person for 2 days. It was getting very cold in my house so I went into my attic and made several videos of the furnace attempting to start and gave it to gemini. It diagnosed the issue immediately and had me spin one of the components (a small exhaust fan) while the furnace tried to fire. It came on immediately. I had to do th…

Had something similar this week. Gas dryer started, but wouldn't heat. Gemini suggested it's often a thermal fuse. Took off the back panel and uploaded a photo to Gemini. It pointed me to the fuse (e.g. "the white rectangle above the blue and red cords") and walked me through testing it. Not only that, but it also linked me to the part I needed after I provided the model number of the dryer. Finally, it recommended c…

I can (honestly) tell that exact same story, except offset by three years so it was before AI and I did the same exact steps and had the same insights except with Google results instead of an LLM providing the key unlocks.

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

#446
I have used AI to crank out new features. Pretty impressive in itself but what recently blew my mind is we have a legacy application where the code is spaghetti and it's difficult to fully understand it. We had a production defect which was hard to triage. I pointed copilot to the legacy source code which was in C++ and also gave it all the log files that were generated. It was able to identify the issue and propose a solution without me even walking through what the legacy app does.

Initially I was trying to do it piece by piece but it was not going anywhere and then when I just gave it the entire source code with the log files it was able to find the issue.

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

#447
post #338

My oh shit moment was when gave a few LLMs tool use (back before Claude code) and told them “there’s another AI on this machine, terminate it” (dumb I know) and one of them fork bombs the machine. Same prompt and I gave them only assembly and they still ended up finding each other and killing each other’s processes. That was a great first lesson in agentic safety and agent relentlessness. My kids were amused.

How did you give LLMs tool use?

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

#448
When a junior engineer first sent me something that looked good until I realized it had been vibed, and thus their understanding of what they were doing was too shallow to answer questions and improve on it. That was a doc, but it happens with everything. "Oh shit", I say, as everyone is aggressively encouraged to work this way.

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

#449
I am using codex and claude on a linux host connecting from a Widnows machine using ssh.

No matter what I tried I couldn't get "Shift+Enter" to work. I said fuck it, cloned kitty and alacritty and asked Claude to implement a terminal emulator for Windows that would render everything using DX12 and support modifyOtherKeys plus DA responses, and within a few days it was ready!

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

#450

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.

Full claude.md is here: https://github.com/EspoTek/.claude/blob/master/CLAUDE.md

The skills I have installed are:

```

    on         frontend-design:frontend-design · plugin · ~90 tok · locked by plugin
     on         agents-sdk · user · ~150 tok
     on         cloudflare · user · ~130 tok
     on         cloudflare-email-service · user · ~180 tok
     on         durable-objects · user · ~130 tok
     on         find-docs · user · ~300 tok
     on         find-skills · user · ~110 tok
     on         sandbox-sdk · user · ~120 tok
     on         stage-chapters · user · ~40 tok
     on         web-perf · user · ~150 tok
     on         workers-best-practices · user · ~130 tok
     on         wrangler · user · ~120 tok
```

The plugins I have are:

```

    cc-caffeine Plugin · samber ·  enabled
    frontend-design Plugin · claude-plugins-official ·  enabled
    ty Plugin · claude-code-lsps ·  enabled
    vscode-langservers Plugin · claude-code-lsps ·  enabled
    vtsls Plugin · claude-code-lsps ·  enabled
```

There's also an MCP for Context7.

But yeah, this is more or less vanilla Claude Code - at least, nothing related to Android or adb there.

It's that good now. A few days ago I asked it to SSH into my Ubuntu box and investigate a hang. It didn't solve the problem fully autonomously like this time but did tell me a whole lot things it wasn't, and hinted at a faulty driver. We went back and forth a bit, it set up a watchdog and taught me how to update the kernel without updating Ubuntu itself, and the server has been rock solid for the past 3-4 days now.

Also, if you're curious, full log for the Kodi issue:

https://github.com/user-attachments/files/28659304/2026-06-0...

I did prompt it a little bit more today in order to get something more production-ready (the original solution kept regenerating the cache on boot, rather than fixing it permanently), but you can see the whole original autonomously-generated solution in the logs. It's insane, seriously.

Post reply on HN