Re:Prompt Engineering vs. Blind Prompting
by 8organicbits on Saturday April 22, 2023 @02:21PM
(#35669475)
Are you not fact checking chatgpt? I've seen wrong info, especially subtle things. It seemed reckless to use as-is.
[ Parent
| on HN ]
Re:Prompt Engineering vs. Blind Prompting
by etimberg on Saturday April 22, 2023 @02:39PM
(#35669636)
For fun I tried asking chatgpt to create a simple using an opensource project I maintain. The generated answer was sort of correct but not correct enough to copy and paste. It missed including a plugin, used a version of the project that doesn't exist yet, and generated data that wasn't valid datetimes.
Re:Prompt Engineering vs. Blind Prompting
by blowski on Saturday April 22, 2023 @02:31PM
(#35669560)
Both ChatGPT and StackOverflow suffer from content becoming outdated. So some highly-upvoted answer on StackOverflow has been out of date since 2011, and now ChatGPT is trained on it.
I see the future as writing test cases (perhaps also with ChatGPT), and separately using ChatGPT to write the implementation. Perhaps we will just give it a bunch of test cases and it will return code (or submit a PR) that passes those tests.