What can LLMs never do?

from Strange Loop Canon [alt+shift+b] in AI

On goal drift and lower reliability. Or, why can't LLMs play Conway's Game Of Life?

10 months ago

Remove from reading list Add to reading list [alt+a] Read now [→]

Improve your reading experience

Logged in users get linked directly to articles resulting in a better reading experience. Please login for free, it takes less than 1 minute.

More from Strange Loop Canon

In defense of Gemini

a kvetch

14 hours ago • 2 votes

How would you interview an AI, to give it a job?

from puzzles to poker

a week ago • 8 votes

What would a world with AGI look like?

a month ago • 42 votes

No, LLMs are not "scheming"

2 months ago • 50 votes

Is AI hitting a wall?

2 months ago • 74 votes

More in AI

See Me at SXSW Next Week!

Talking AI in Austin on March 8th and 9th

11 hours ago • 2 votes

On OpenAI's Safety and Alignment Philosophy

OpenAI’s recent transparency on safety and alignment strategies has been extremely helpful and refreshing.

14 hours ago • 2 votes

In defense of Gemini

a kvetch

14 hours ago • 2 votes

Ezra Klein’s new take on AGI – and why I think it’s probably wrong

In a new episode of his podcast with Ben Buchanan former special adviser for artificial intelligence under Biden, entitled, The Government knows A.G.I.

10 hours ago • 1 votes

Why You Should Never Let AI Debug for You

And 3 ways you should be using AI to code

6 hours ago • 1 votes

New here?