Re:Home-Cooked Software and Barefoot Developers
by TeMPOraL on Wednesday June 12, 2024 @03:23AM
(#40655487)
LLMs literally read all that commentary in training, so they're taking it into account, not regurgitating the top-voted answer from SO. They're arguably better at this than junior devs.
[ Parent
| on HN ]
Re:Home-Cooked Software and Barefoot Developers
by ben_w on Wednesday June 12, 2024 @07:35AM
(#40656880)
While LLMs are better at reading the surrounding context, I am not convinced they are particularly good at taking it on board (compared to an adult human, obviously fantastic compared to any previous NLP).
Biggest failure mode I experience with LLMs is a very human-like pattern, what looks like corresponding with an interlocutor who absolutely does not understand a core point you raised 5 messages earlier and have re-emphasised on each incorrect response:
--
>>> x
>> y
> not y, x
oh, right, I see… y
--
etc.