Apparently, stealing other peopleâs work to create product for money is now âfair useâ as according to OpenAI because they are âinnovatingâ (stealing). Yeah. Move fast and break things, huh?
âBecause copyright today covers virtually every sort of human expressionâincluding blogposts, photographs, forum posts, scraps of software code, and government documentsâit would be impossible to train todayâs leading AI models without using copyrighted materials,â wrote OpenAI in the House of Lords submission.
OpenAI claimed that the authors in that lawsuit âmisconceive[d] the scope of copyright, failing to take into account the limitations and exceptions (including fair use) that properly leave room for innovations like the large language models now at the forefront of artificial intelligence.â
Iâm unconvinced that the fact theyâre getting better at following instructions, like putting objects where the prompter specifies, or changing the colour, or putting the right number of them, etc means the model actually understands what the objects mean beyond their appearance. It doesnât understand the cultural meanings attached to each object, and thus is unable to truly make a decision about why it should place an apple rather than an orange, or how the message within the picture changes when itâs a red sports car rather than a beige people-carrier.
how the message within the picture changes when itâs a red sports car rather than a beige people-carrier.
Well, thatâs part of the LLM step, so letâs put it to the test:
Image prompt:
Create an ad for a car. The target audience are young adults, with high income, and thrill seeking. Come up with a brand name fitting such a car, and include it in the image. For the car, come up with a shape, and color, best fitting of the target audience. Come up with an image layout, art style, and camera angle, best fitting of the target audience. Include between zero and two additional items that will make the overall picture more attractive to the target audience.
ChatGPT:
[(âan advertisement for a carâ, [45, 58, 422, 396]), (âa high-performance carâ, [123, 193, 266, 128]), (âan edgy and dynamic brand name logoâ, [188, 10, 136, 30]), (âa sleek, red sports carâ, [168, 254, 176, 102])] Background prompt: An adrenaline-pumping car advertisement targeting young adults with high income and a thrill-seeking spirit. The layout includes a bold brand name logo, a sleek red sports car, and a dynamic composition to captivate the audience. Negative prompt: additional items
How did it know to pick a âsleek red sports carâ? Or the rest of the elements.
Because some of its training data included some of the many, many websites out there that describe marketing techniques. However, your example has actually proved my point - the red sports car is a car for insecure middle-aged men needing a mid-life crisis penis extension. The LLM has entirely missed that cultural association, and has basically suggested a red sports car for a young audience, when an alternate colour would actually be more appropriate - because it doesnât actually understand what a red sports car means.
It also hasnât actually picked any distinctive elements that couldnât be found on a website offering generic marketing advice. âA dynamic compositionâ is obvious, but it hasnât specified any details about what the composition should look like. It hasnât detailed any of the surrounding scenery. It says you should include a brand name logo, which was obvious because you prompted it to come up with a brand name, but itâs failed to detail what those should actually look like. The entirety of the elements itâs created here is âsleek red sports carâ, which has a cultural connotation inappropriate to the target audience, and the rest you could literally get from any search for âhow do I create an advert for a car?â
