Ashley

As discussed with @hahuyhoang411: - Error when thread exceeds the context length - Recommend users to delete message by themselves or create a new thread ## Design: https://www.figma.com/file/ytn1nRZ17FUmJHTlhmZB9f/Jan-App-(version-1)?type=design&node-id=6847-111809&mode=design&t=ErX19MBkMjVhBSjO-4 (This is...

Hi @Gri-ffin thank you so much for bringing this up! Great idea! FYI, I'll change the design a little bit to match Jan's style

@Gri-ffin here's the updated design for this: https://github.com/janhq/jan/issues/1315, thanks @Gri-ffin

Archive the original comment of Alan: ________ ## Problem - Windows users experience 100% CPU usage (#887) - Nitro/Jan needs to support hardware optimizations for different Windows architectures (CPU, GPU)...

Thank you for your suggestion. We are refactoring inference engines right now (including options to disable remote models). Please stay tuned for the change!

Hi there! Can you clarify more on this? > Jan adds features like GPTs

Archive Nicole's original comment: ____ **Problem** Users can't see how long a llm response took in total **Success Criteria** A clear and concise description of what you want to happen....

Let's simplify it: - Remove that message queued - Type 1st message -> send -> model start -> type 2nd message while model is starting -> cant send

HUB REVAMP Figma link: https://www.figma.com/file/ytn1nRZ17FUmJHTlhmZB9f/Jan-App?type=design&node-id=479-21691&mode=design&t=uV0D1oQLPoF6kzy2-4 Changes that address all the feedbacks & comments: - 2 features model to get started - List all models with sticky navs, and allow users...

Archive Daniel's original comments - @imtuyethan to work on the latest specs: ## Kanban https://github.com/orgs/janhq/projects/5/views/7?filterQuery=milestone%3A%22Improved+Hub+Experience+for+Models%22+ **Problem** - Hub is currently a poorly-ordered list of models that user has to go...