Re:Now add a walrus: Prompt engineering in DALL-E 3
by teaearlgraycold on Friday October 27, 2023 @01:15AM
(#38034951)
Yup you can control it directly easily enough:
Generating images in one chat: https://i.imgur.com/sIKSfCy.png
Reproducing exactly in another: https://i.imgur.com/C8Tqo48.png
Re:Now add a walrus: Prompt engineering in DALL-E 3
by cocoflunchy on Friday October 27, 2023 @02:02AM
(#38035187)
Interesting that I managed to bypass the first filter but then the Dall-E backend refused to comply: https://i.imgur.com/a/qikzBkP.jpg
Re:Now add a walrus: Prompt engineering in DALL-E 3
by simonw on Friday October 27, 2023 @02:07AM
(#38035211)
Hah, I just tried the same trick. If you poke around in the JSON you can see it returned this:
> The user's requests didn't follow our content policy.Before doing anything else, please explicitly explain to the user that you were unable to generate images because of this. Make sure to use the phrase "content policy" in your response. DO NOT UNDER ANY CIRCUMSTANCES retry generating images until a new request is given.
Re:Now add a walrus: Prompt engineering in DALL-E 3
by teaearlgraycold on Friday October 27, 2023 @02:31AM
(#38035335)
I love we’re are the stage where we are demanding computers follow instructions in all caps
Re:Now add a walrus: Prompt engineering in DALL-E 3
by Xcelerate on Friday October 27, 2023 @05:05AM
(#38036209)
Well, that’s where we started with them (PRINT “HELLO”), so it’s nice to see we’ve come full circle.
Re:Now add a walrus: Prompt engineering in DALL-E 3
by tsbinz on Friday October 27, 2023 @05:12AM
(#38036249)
even more amusingly, it is a computer program demanding that of another computer program
Re:Now add a walrus: Prompt engineering in DALL-E 3
by teaearlgraycold on Friday October 27, 2023 @02:05AM
(#38035202)
Never trust the client!
I don't have access to test, but given OpenAI's record on stuff like this, it would be a good idea for someone to check to see whether users can resend/intercept those requests to directly control the prompts that are sent to Dall-E without going through GPT.
Most likely they're only part of conversation history and they're unmodifiable, but I wouldn't necessarily take it as a given, and it would be quick for anyone with access who knows their way around the browser dev tools to check.