Re:Show HN: Promptr, let GPT operate on your codebase and ot...
by oslac on Tuesday April 04, 2023 @09:29AM
(#35439252)
It sounds like a good idea to send your codebase through a MITM to OpenAI, both of these ideas I mean.
[ Parent
| on HN ]
Re:Show HN: Promptr, let GPT operate on your codebase and ot...
by deathmonger5000 on Tuesday April 04, 2023 @09:36AM
(#35439355)
The files you pass to promptr are indeed sent to OpenAI. There’s no man in the middle. Privacy is important, and I’m glad you care.
The relevant code is here https://github.com/ferrislucas/promptr/blob/3ae09d1cffbb6b93...
And here: https://github.com/ferrislucas/promptr/blob/3ae09d1cffbb6b93...
Re:Show HN: Promptr, let GPT operate on your codebase and ot...
by debarshri on Tuesday April 04, 2023 @11:23AM
(#35441151)
I think, if I am not wrong, commentator is saying that you are the man in the middle.
Re:Show HN: Promptr, let GPT operate on your codebase and ot...
by tough on Thursday April 06, 2023 @07:33PM
(#35475989)
Is it really a MITM if the codebase is open source and you trust him to deploy that code
Re:Show HN: Promptr, let GPT operate on your codebase and ot...
by debarshri on Saturday April 08, 2023 @02:16AM
(#35490984)
Default trust is problem. How can you establish if this person is a good faith actor?
Re:Show HN: Promptr, let GPT operate on your codebase and ot...
by WrtCdEvrydy on Tuesday April 04, 2023 @09:37AM
(#35439374)
This is good for security overall... think about it, if we sent all of our stuff to the NSA, they would find security bugs and fix them for us.
Re:Show HN: Promptr, let GPT operate on your codebase and ot...
by iamerroragent on Tuesday April 04, 2023 @09:52AM
(#35439616)
NSA be like:
"Romani ite domum"
After catching you writing:
"Romanes eunt domus"
Re:Show HN: Promptr, let GPT operate on your codebase and ot...
by MuffinFlavored on Tuesday April 04, 2023 @11:46AM
(#35441507)
Is the size/file limit with OpenAI API different than what you can send via ChatGPT in the browser?
How much are you going to pay for example to send a 1kb, 2kb, 4kb, 8kb, 16kb source file for analysis? If you are paying per "token", a 3kb file I have with like 70 lines of code might have 2-3 tokens per line if I understand what a token is, 210 tokens? Each token costs...
Ok, not as bad as I thought.