zlacker

[return to "LLMs cannot find reasoning errors, but can correct them"]
1. eschat+zw1[view] [source] 2023-11-21 04:16:35
>>koie+(OP)
LLMs can’t find reasoning errors because *LLMs don’t reason*.

It’s incredible how uninformed the average Hackernews is about artificial intelligence. But the average Hackernews never met a hype train they wouldn’t try to jump on.

◧◩
2. dmichu+512[view] [source] 2023-11-21 08:42:24
>>eschat+zw1
> LLMs can’t find reasoning errors because LLMs don’t reason.

I have several experiences where people belittle me when I say the same thing. To the extent I rarely say it anymore. For everybody else AGI is around the corner and it's gonna dominate the world.

> never met a hype train they wouldn’t try to jump on

Crypto-currencies

◧◩◪
3. rsynno+s12[view] [source] 2023-11-21 08:46:06
>>dmichu+512
> Crypto-currencies

HN _eventually_ largely gave up on these, but it was basically a True Believer space from 2011 to the early days of NFTs; it was more credulous than just about any other community which had known about cryptocurrencies since the early days.

[go to top]