News for hackers. Stuff that matters.

A comment on Large language models reduce public knowledge sharing on online Q&A platforms. Parent comment

Re:Large language models reduce public knowledge sharing on ... by simonw on Sunday October 13, 2024 @10:18AM (#41828240)
Both the "count the Rs in strawberry" and the "multiply two large numbers" things have been solved for over a year now by the tool usage pattern: give an LLM the ability to delegate to a code execution environment for things it's inherently bad at and train it how to identify when to use that option.
[ Parent | on HN ]
Re:Large language models reduce public knowledge sharing on ... by vlovich123 on Sunday October 13, 2024 @10:26AM (#41828303)
I think the point is that playing whack a mole is an effective practical strategy to shore up individual weaknesses (or even classes of weaknesses) but that doesn’t get you to general reasoning unless you think that intelligence evolved this way. Given the adaptability of intelligence across the animal kingdom to novel environments never seen before, I don’t think that can be anything other than a short term strategy for AGI.
[ Parent | on HN ]
Re:Large language models reduce public knowledge sharing on ... by simonw on Sunday October 13, 2024 @12:04PM (#41829123)
Sure, LLMs won't ever get to general reasoning (for pick your definition of "reasoning") unassisted.

I think that adding different forms of assistance remains the most interesting pattern right now.

[ Parent | on HN ]
Re:Large language models reduce public knowledge sharing on ... by shagie on Sunday October 13, 2024 @01:08PM (#41829640)
(I did an earlier attempt at this with a "ok, longer conversation" ... and then did a "well, what if I just asked it directly?")

https://chatgpt.com/share/670bfdbd-8624-8011-bc31-2ba66eab3e...

I didn't realize that it had come that far with the delegating of those problems to the code writing and executing part of itself.

[ Parent | on HN ]