In my tests no, that's still not possible with the model unfortunately, but it feels like you have way more control with prompting over any previous model (stable diffusion/midjourney).
It makes me a bit worried to read this thread, I would've thought its pretty common knowledge why CSV is horrible and widely agreed upon. I also have hard time taking anybody seriously who uses "specification" and "CSV" in the same sentence unironically.
I suspect its 1) people who worked with legacy systems AND LIKED IT, or 2) people who never worked with legacy systems before and need to rediscover painful old lessons for themselves.
It feels like trying to convince someone, why its a bad idea to store the year as a CHAR(2) in 1999, unsuccessfully.
The thread makes me worried for a different reason, especially how many avoid reading the RFC and even saying that the RFC doesn't matter, that there's no standard for csv. maybe there should be an extension for rfc-csv.
Would be interested to know as well. As far as I know there is no public information about how this works exactly. This is all I could find:
> The system uses an autoregressive approach — generating images sequentially from left to right and top to bottom, similar to how text is written — rather than the diffusion model technique used by most image generators (like DALL-E) that create the entire image at once. Goh speculates that this technical difference could be what gives Images in ChatGPT better text rendering and binding capabilities.
I wonder how it'd work if the layers were more physical based. In other words something like rough 3d shape -> details -> color -> perspective -> lighting.
Also wonder if you'd get better results in generating something like blender files and using its engine to render the result.
I’m using 4o and it gets time wrong a decent chunk but doesn’t get anything else in the prompt incorrect. I asked for the clock to be 4:30 but got 10:10. OpenAI pro account.
Why does it sound like this isn't reasoning on images directly but rather just dall e as some other comment said , I will type the name of the person here (coder543)
I got the sense that Lina Kahn was a thorn to Harris as well, otherwise she would've committed to Kahn's FTC instead of leaving it ambiguous and not campaigning on her successes.
Khan made a lot of good regulatory changes, and some good litigation (like RealPage), but a lot of the litigation was frankly counterproductive and/or badly handled.
Splitting Chrome off of Google and making it so that Firefox can't get search engine royalty payments is not going to lead to societally useful outcomes. And voters don't give a shit about it either. The FTC could have had much more impact if they were focused on, say, healthcare, health insurance, preventing private equity from owning (and closing) so many hospitals and chains and nursing homes, etc. They did some of that but it was very clear that big tech was the focus.
And I'm not against taking on big tech even a little bit, but you kind of have to have a plan for the desired outcomes, and it doesn't feel like there was much of one.
> two broad categories: AI sloppish brain rot and more refined products that are hand made
If we graph it: Sloppishness is the Y axis and if we then put progres-in-AI on the X axis, the two lines will eventually touch each other. With some segment¹ of the population not being able to tell the difference sooner than others, slowly reducing available budget of handmade media, increasing it's slop over time. Therefore progress in AI will reduce the quality of even handmade media.
This is of course nonsense, but interestingly enough also a FAQ entry of Sheepit:
> Who owns the copyright of the images generated?
> SheepIt Render Farm does not lay any claim to generated images, it only acts as a tool to provide compute power to owners of the project. The owner of the project will have all rights reserved to them; As long as the claimant is the true rights holder of all assets used, and complies with governed free use laws, as well as potential rights holder permissions.
Otherwise I guess GitHub owns the copyright on all software artifacts build on their CI systems. Obviously not how copyright works, like at all.
"GitHub owns the copyright on all software artifacts build on their CI systems"
Good question, someone should get the IP lawyers to go over the EULA of both git and the login email identity service providers. However, I would assume for most FOSS licensed projects it is likely a moot argument. Microsoft probably wouldn't do anything evil...
Hard to say for sure... One would assume github implicitly agrees to the FOSS project license by hosting the source, and thus is still in compliance when compiling the binary in the CI pipeline.
