Asking ChatGPT to write my security-sensitive code for me

Re:Asking ChatGPT to write my security-sensitive code for me by BazookaMusic on Saturday January 07, 2023 @06:20AM (#34287104)

I had the exact same experience trying to get ChatGPT to tell me if there's a vscode setting for the max length of tooltip text.

It responded that there is and pointed out the max tokenization length setting with an explanation on why to use it and what value to use. The problem is that this setting is absolutely unrelated to the functionality I asked for.

[ Parent | on HN ]

Re:Asking ChatGPT to write my security-sensitive code for me by holoduke on Saturday January 07, 2023 @06:31AM (#34287140)

A bit like common responses on stockoverflow :)

[ Parent | on HN ]

Re:Asking ChatGPT to write my security-sensitive code for me by omnicognate on Saturday January 07, 2023 @07:24AM (#34287423)

No, StackOverflow is quite a reliable source of correct and relevant answers to programming questions, with effective mechanisms for the community to identify and fix wrong or unhelpful answers.

It won't remain that way if those mechanisms are DoSed with a firehose of free plausible garbage. The flippant attitude that what we currently have is no better than that firehose, and the implication that it isn't worth worrying about or attempting to protect, is starting to grate.

[ Parent | on HN ]

Re:Asking ChatGPT to write my security-sensitive code for me by lwhi on Sunday January 08, 2023 @03:16AM (#34297152)

People make mistakes in stack overview. The community identifies an incorrect (or suboptimal) answer as accepted fairly often in my experience.

[ Parent | on HN ]