catonmat

The "verify their own reality" point resonates. I stumbled on a post recently where someone documented getting an OCR model from 90% to 98% accuracy - turns out most of the gain came from discovering their training labels were 27% wrong, not from model tweaks. The interesting bit was their finding that running AI verification in parallel resulted in 2% correction rate, but sequential processing caught 65%. That kind of hard-won, numbers-backed insight is what makes technical blogs worth reading vs the flood of tutorial content.

  https://devguide.dev/blog/teaching-ai-to-distrust-itself

> However, there are some questions left unanswered.

> Why did I need to do the absolute most to reach this point?

> Why couldn’t I just leave Loom and say “I don’t know what I want to do next”?

> Why do I feel the need to only be on a journey if it’s grand?

> What is wrong with being insignificant?

> Why is letting people down so hard?

For these questions, I would suggest, you please read blogposts on https://os.me

Om Swami is an entrepreneur extraordinaire and has discovered his own truth. I am sure you will find it helpful.

Spoiler: He was(is?) also ultra rich and has figured out this stuff.

We wrote https://trackcourier.io frontend in Go. Its been really stable so far and is ridiculously fast.