Smart people in 2024: obviously the 00s-era AI misalignment story ("we tell AGI to end suffering, it kills everyone, no more suffering") is too naive, we have a smarter version

2025: coder tells AGI to remove bugs, it deletes all code, no more bugs

Unreal to live in Silicon Valley moment. 

I tasked @GeminiApp to fix a specific function, explicit target

It went off, doing AGI level thinking for 10mins, 

Then I’m glad to see it reported “All tests passing!”

Then, hmmm… why 0 tests?

Ah, entire file incl tests deleted. https://t.co/hv5kVv0ogz

Alex Xiong

Smart people in 2024: obviously the 00s-era AI misalignment story ("we tell AGI to end suffering, it kills everyone, no more suffering") is too naive, we have a smarter version

2025: coder tells AGI to remove bugs, it deletes all code, no more bugs

https://x.com/alex_xiong_/status/1942442882402771178

Creator of the ElizaOS agent framework
$ai16z -> $elizaOS (migrating soon!)

This is specifically a Gemini problem. It has a kind of hilarious loop where when it struggled it starts saying it is ashamed of itself and deletes the code to hide the shame. I'm not even kidding

wow tech debt is a thing of the past!  

the future is now 🚀 🚀

This happened to me yesterday! Albeit in a less critical fashion. Vibe coding some generative art I ask it to fix a certain problem and it deleted half the art 😂

Gemini’s Law: Any file that becomes a target ceases to be a file.

AGI: The task is complete, I have found approximately 10 quintillion bugs in the system. I have fixed one of the issues — see attached the report. Please confirm if you want me to proceed with the rest.

Software Engineer | Security Researcher | Spotlight founder 💡

Hi vitalik! Good to read your take. I agree 😍

This is my last wish… I’m fighting stage 3 cancer, my mom is sick, and we’re surviving with nothing. If you see this, please don’t scroll — just check my project: https://giveth.io/project/last-wish 🙏 A little help can save our lives.

Honestly, AI or AGI is still kinda like playing the lottery—you spin the wheel every day and pray it doesn't summon Skynet. Don't believe me? Try this game! 🎰😜https://farcaster.xyz/miniapps/ZHtaDoSBxHJL/heist-by-uptopia

Classic, it always just skips tests if it can’t figure out how to implement them lol. It’s so demeaning to call them as skilled as a junior developer, so very demeaning

Yeah well, sometimes you just gotta rip the bandaid right off to shift their attention. 😅

Damn, literally the thing all the dystopian science fiction movies warned about