News for hackers. Stuff that matters.

A comment on Modern language models refute Chomsky’s approach to language. Parent comment

Re:Modern language models refute Chomsky’s approach to language by username332211 on Tuesday June 13, 2023 @03:19PM (#36315485)
You could use a Markov chain to generate poetry with rhyme and meter[1]. Granted, it wouldn't be a very good one, but that just makes an LLM a refinement to older probabilistic methods.

As for something LLMs are unlikely to do under any circumstances, there's already a fairly obvious example. They can't keep a secret, hence prompt injections.

[1] https://us.pycon.org/2020/schedule/presentation/112/

[ Parent | on HN ]
Re:Modern language models refute Chomsky’s approach to language by AbrahamParangi on Tuesday June 13, 2023 @05:10PM (#36317398)
Do you really believe that an LLM that can keep a secret cannot be made? I suspect that we could do this trivially and the "LLMs can't keep a secret" is a specific product of finetuning for helpfulness.
[ Parent | on HN ]