Unfortunately this happens to everybody after a certain point. The current AI chat model is outdated and has very few context tokens, meaning that it can not handle a long session of back and forth writing/creating. It will recycle sentences, forget important details, and generally devolve into a maniac if used long enough. This is why the developer is intent on upgrading the text model. We're all hoping that he upgrades to Llama 3.3 which has an exponentially higher context window which will make this issue irrelevant. But we'll just have to wait and see.
Sniebl
joined 4 months ago
Amazing! Thanks for the link.
You should read this: https://perchance.org/perchance-faq
You'll get a feel for the kind of person the developer is. Unfortunately what it boils down to is that you're too emotionally invested in the website for your own good. They'd probably prefer hordes of people to stop coming to the website and then continue as usual regardless at their own pace rather than change their habits and schedule to accomodate any need for communication or updates. Heck, they even mention not paying attention to the site for months at a time.
It's harsh, and I'm not thrilled by it either, but it is what it is, and I've settled for spending my time on other projects/hobbies until a clear upgrade has been implemented. We have no right to complain (with the exception of venting towards each other) since we're literally all freeloading off of dev's time and investment.
That being said, I think there's also a certain kind of charm to just being surprised out of the blue with an unexpected update. It kind of amplifies the reward when it's done in a beneficial way. Some people really enjoyed the image gen upgrade, others had a meltdown, but eventually got the hang of prompting differently. It's all part of the unique, anti-capitalistic/corporate experience that is Perchance. Let's not get ahead of ourselves, and maybe....just maybe...the update will come sooner than expected.