Wow you really weren't kidding. Fully automated AI slop tentacles for everyone! https://pastes.io/uenL6X9K It also seems to have an obsession with this celebrity, based on how many times ctrl-f for "stefani" turns up a result. https://en.wikipedia.org/wiki/Gwen_Stefani
Wow, it displays Korean properly without breaking.
But there are still a lot of typos. Haha, it's good that Korean displays properly, but there are a lot of incorrect sentences
The meta keywords in the HTML is very interesting. 100+ references to NSFW topics such as hentai, nudes, etc.
Wow you really weren't kidding. Fully automated AI slop tentacles for everyone! https://pastes.io/uenL6X9K It also seems to have an obsession with this celebrity, based on how many times ctrl-f for "stefani" turns up a result. https://en.wikipedia.org/wiki/Gwen_Stefani
They must have trained on GPT Image 1 outputs. The yellow tint is unmistakable. https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen-Image/i... https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen-Image/i... https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen-Image/i... https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen-Image/i...
GPT Image 1 ended up with a yellow tint without training on another image-generation model's output. It's just that humans like pictures with a soft sunset glow, and this is a very easy global signal for a preference model to pick up on, and for a image-generation model to imitate. So optimizing for aesthetic appeal makes everything slightly tinted by default, unless you make sure to countersteer.
They must have trained on GPT Image 1 outputs. The yellow tint is unmistakable. https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen-Image/i... https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen-Image/i... https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen-Image/i... https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen-Image/i...
GPT Image 1 ended up with a yellow tint without training on another image-generation model's output. It's just that humans like pictures with a soft sunset glow, and this is a very easy global signal for a preference model to pick up on, and for a image-generation model to imitate. So optimizing for aesthetic appeal makes everything slightly tinted by default, unless you make sure to countersteer.
Wow you really weren't kidding. Fully automated AI slop tentacles for everyone! https://pastes.io/uenL6X9K It also seems to have an obsession with this celebrity, based on how many times ctrl-f for "stefani" turns up a result. https://en.wikipedia.org/wiki/Gwen_Stefani
> ben 10 hentai game where qwen gets drunk erm... what?
> qwen ten hentai, qwen ten xxx, qwen tennason footjob, qwen tennison hentai, qwen tennyson, qwen tennyson ass expansion, qwen tennyson giantess pussy, qwen tennyson hentai, qwen tennyson porn, qwen tft, qwen the milk maid, qwen the milkmaid, qwen the parts over, qwen the wolf witcher, qwen tire, qwen tneyson porn, qwen to go feelies youtube, qwen tokenizer java,
Wow you really weren't kidding. Fully automated AI slop tentacles for everyone! https://pastes.io/uenL6X9K It also seems to have an obsession with this celebrity, based on how many times ctrl-f for "stefani" turns up a result. https://en.wikipedia.org/wiki/Gwen_Stefani
> ben 10 hentai game where qwen gets drunk erm... what?
Whelp today’s a unique day on hacker news, wow! Didn’t expect to read that at my desk lol
Wow, it displays Korean properly without breaking. But there are still a lot of typos. Haha, it's good that Korean displays properly, but there are a lot of incorrect sentences
I find it mildly interesting how your comment repeats itself but with different phrasing