| HN Mirror

Y	Hacker News new \| ask \| show \| jobs

4 comments

Maybe so, but please don't post unsubstantive comments to Hacker News.

In what sense?

Really?

You've already seen the fruits of your prompt and how far your "isn't is super obvious I don't need to explain myself" attitude is getting you.

This was performed on animals.

What is a less crazy way to progress? Don't use animals, but humans instead? Only rely on pure theory up to the point of experimenting on humans?

Yes, this is scary.

Why?

Because a LLM architecture seems way too fuzzy and unpredictable for something that should be reproducible.

I thought that was the temperature setting that does that?

Real world isn't "reproducible". If a robot can't handle weird and unexpected failures, it wouldn't survive out there.