This week we've made improvements to our avatar image generation cluster, increasing speed and reducing generation errors.

We're also introducing new advanced features:

• Negative Prompt: better control of what you don't want ib your image
• Image Guidance: generate an image similar to another image
• Seed Locking: Allow to redo the same generation but with changes to the prompt

Enjoy and let us know how you like it!

When you take the time to rate the replies you receive, you help us improve our service. It only takes one click to give a 1 to 4 stars rating to the response!

Thanks so much for your help!

We're committed to providing a high-quality, free service to our user community, and it's the generous support of our premium subscribers that makes this possible for everyone.

We're excited to announce an important upgrade exclusively for our True Supporter ($14.95) and I'm All In ($24.95) subscribers. Over the past few weeks, we've integrated more advanced GPUs and leveraged recent advancements in the field. As a result, we're now able to offer a doubled context size for a more comprehensive user experience.

For those unfamiliar, Large Language Models (LLMs) operate within a finite token limit—traditionally set at 2048 tokens (roughly 1500 words). This limit dictates the amount of conversational history we can utilize when generating responses. By expanding this limit to 4096 tokens (approximately 3000 words), the model can now consider a wider range of previous interactions, enabling more context-rich and accurate responses.

We hope our premium subscribers enjoy this enhanced capability. And for our free users, know that it's thanks to our supporters that we can continue to innovate and make improvements across our platform.

• Get bot recommendations based on your likes and interactions.
• Discover more of what you love, with less effort.

To more personalized chats and exciting discoveries

Exciting News! We’ve been listening to your feedback, and today we’re thrilled to roll out one of our most requested features - Content Tags Filtering. With **80 unique tags** to choose from, you can now easily categorize the bots you create. From ‘NSFW’ to ‘Anime’, ‘Fantasy’, and more – categorizing your bots is now a breeze!

More than just labels, these tags are a powerful tool for users to **explore and discover** chatbots that match their interests, making the SpicyChat.ai experience more tailored than ever.

Give it a try, and share your thoughts with us! Start tagging and help others discover your bots!

Start tagging and help others discover your bots!

One of the biggest complaint about our model's text generation has been the issue of bot entering a loop and repeating the same sentences over and over.

We've just deployed a big improvement to mitigate those issues. The new Anti-Looping feature should now prevent 90% of bot looping cases and dramatically reduce the need to edit responses when that happens.

Enjoy!

An often requested feature has been the ability to view the chatbot definitions of public chatbots. To respect creators that want to keep their "secret sauce" secret, we're introducing the ability to make bot definitions public as an opted-in feature. When creating new bots, you can enable or disable Definition Visibility.

For previously created chatbots, you will have to update your definition to make it public.

We've added a Star Rating system that allows you to give us feedback on the quality of the text generation our models generate. This will allow us to better filter out bad data when fine-tuning future models. Thanks to those of you that will take the time to rate responses. We've also made improvements to our text generation clusters, allowing us to now support more simultaneous users with faster generation time. We started working this week on Semantic Memory, this feature will be for Subscribers Only but will allow your chatbot to make better use of previous messages in a long conversation, giving your bot a long term memory. Plus many bug fixes, especially on mobile!

You can now edit messages from your conversation. That a great way to fix a generation error or to steer the conversation in the direction you want.

We clarified our Community Guidelines, also added Male / Female tags this week as well as a few minor fixes. Follow us on Twitter if you are not doing so already: https://twitter.com/SpicyChatAI

It's now possible to delete characters you have created,

Also, just a reminder that you can join us on Discord to report any issues or request features.

https://discord.gg/ruexExw2nr