Re:ChatGPT powered GitHub code review app
by educaysean on Tuesday March 07, 2023 @04:12PM
(#35061311)
Agreed. I was expecting the AI to uncover and offer more nuanced suggestions. The examples on the site were highly local issues, with most of them being one-liners our linters are already catching. I was excited to see what the AI can do when it has the context of the entire repo, but I was not wowed.
[ Parent
| on HN ]
Re:ChatGPT powered GitHub code review app
by marceloabsousa on Tuesday March 07, 2023 @05:58PM
(#35062540)
I wouldn't discard the capabilities of the LLM. I've been using it to do relational reasoning of Java comparators and it is surprisingly accurate. https://twitter.com/marceloabsousa/status/163289383288582963...