stuff20230314
Re:The Stupidity of AI
on Thursday March 16, 2023 @07:32PM (#35190474)
As a liberal-left lifestyle tabloid, they had to bash something out on this hot topic.
Re:Women Are 41% More Likely to Experience Toxic Workplace Culture Tha...
on Thursday March 16, 2023 @07:29PM (#35190443)
It doesn't matter, just like gender ratios within imprisonment, homelessness, suicide rates and child custody outcomes.
Re:Bandcamp Unionizes
on Thursday March 16, 2023 @07:10PM (#35190243)
Epic owns ArtStation too.
Re:Introducing react.dev
on Thursday March 16, 2023 @05:43PM (#35189140)
Decoupling your personal future from Silicon Valley devs' pursuit of promotions is always a great idea.
Re:GPT-4 is phenomenal at Code
on Tuesday March 14, 2023 @08:13PM (#35161667)
Yeah, I am sure the FAANG devs are all copy-pasting things into ChatGPT or requesting Copilot. Sure.
Re:GPT-4 is phenomenal at Code
on Tuesday March 14, 2023 @08:09PM (#35161617)
...it does really well... As in "ready to commit" or leaving the hard part (review of correctness) to developer?
Re:GPT-4 is phenomenal at Code
on Tuesday March 14, 2023 @08:07PM (#35161583)
1. So, current and immediate future limits prevent this beyond relatively small projects?
2. But like, you still have to write tests though? If I need to think and check what the generated tests are doing, I'd rather write them myself to be honest. I want the time-consuming parts automated, not typing code. Maybe I am in minority. Surely generating 99% complete unit tests should be some sweet-spot for ChatGPT? I would imagine this AI can ignore halting problem, and somehow traverse all possible states anyway?
Re:GPT-4 is phenomenal at Code
on Tuesday March 14, 2023 @08:02PM (#35161510)
Because of some cherry-picked niche samples?
Re:GPT-4 is phenomenal at Code
on Tuesday March 14, 2023 @07:57PM (#35161443)
That's cool and all, but can it do "in this existing code, please amend this feature"? Also useful, "please cover this code with meaningful unit tests"?