Re:Ask HN: What is your comfort level with code generated by...
by shekkizh on Wednesday October 16, 2024 @09:47AM
(#41858999)
Agreed. What would make you less skeptical? We typically do not look into the code within the software that we install in our systems today - so there is some level of trust already.
[ Parent
| on HN ]
Re:Ask HN: What is your comfort level with code generated by...
by voidUpdate on Wednesday October 16, 2024 @10:37AM
(#41859545)
If LLMs didn't hallucinate as much I'd maybe trust their output more. But they have a tendency to do unpredictable things, which isn't really what you want in a production environment. I keep seeing stories of what AI assistants have done incorrectly, which makes me hesitant to pipe their output into a codebase, unmodified
Re:Ask HN: What is your comfort level with code generated by...
by JTyQZSnP3cQGa8B on Wednesday October 16, 2024 @10:52PM
(#41866007)
> We typically do not look into the code
I actually do it, and when I don’t there is a chain of responsibility to handle that. LLMs write random code that haven’t been approved, agents would make that worse by actually running it.
Most AI fans want us to run commands like “cat /etc/random | sh” and that’s why software engineering is not real engineering.
Re:Ask HN: What is your comfort level with code generated by...
by shekkizh on Thursday October 17, 2024 @01:55AM
(#41866803)
haha. I get that there are no rigorous standards in software engineering, but this has not stopped us from using software.
I wonder if implementing a "chain of responsibility" -- kinda falls into my third scenario -- will improve trust levels for code generated by LLM.