News for hackers. Stuff that matters.

A comment on Large Language Models' Emergent Abilities Are a Mirage. Parent comment

Re:Large Language Models' Emergent Abilities Are a Mirage by HarHarVeryFunny on Monday March 25, 2024 @09:30AM (#39816045)
Apparently Claude-3 Opus can do reversal tasks pretty well, even without a code interpreter (or does it use one internally?).

https://twitter.com/AlexTamkin/status/1767248600919355670

[ Parent | on HN ]
Re:Large Language Models' Emergent Abilities Are a Mirage by chmod775 on Monday March 25, 2024 @12:02PM (#39817993)
Pretty much all of them will able to fake it on short sentences. All break down eventually (and soon).

Also that's not a reversal task because there was no input. It was free to make up anything that fits.

[ Parent | on HN ]