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

As funny as it may sound, this is the future of AI. For example, with Lovable, you don’t need any programming skills at all — websites are created automatically in just 5–10 minutes. And this is the future that will leave most people without jobs

So, will this future AI learn to remove itself then to get rid of hallucinations, LOL?