Each profile would have its a limited amount of slots for files that models can retrieve on-demand. For example, I have a profile for job search and often have to upload my CV into every thread when I wanna have an LLM write me cover letters. Would be nicer if the LLMs could simply retrieve my CV from a stash of files that I give it access to.
It would be wonderful if the moment I enter burst overage, I could customize it so that it would automatically (or ask to swap) to a model of my choosing.
A simple button to automatically have the current model write a handoff of the chat, create a new thread and send the handoff in that chat. Helpful when a thread is getting long but your problem hasn’t been solved.
TL;DR Optimizing Model capabilites is sluggish. Add a “Create Model Preset” Option to model selection. Allow to save “model + reasoning + number of searches“ as a named preset. Problem Trying to optimize for Token efficiency, it is sluggish to adjust Model capabilities based on my upcoming Prompt. I find myself configuring reasoning and search all the time. I also find myself often times checking those settings when switching to another model before I write my prompt. This adds friction. Goal I would like to have the ability to configure Model presets. e.g. a research preset, that would possibly be something cheap/cheaper with maximum searches enabled. e.g. “deepseek v4 flash, low reasoning, 5 searches“. Other presets could be simply high reasoning and include something like “kimi k3, high reasoning, no searches“ or any in-between. Maybe “creative support & planning“, which could be “kimi k3, low reasoning, 2 searches“. These are presets, that I can just think of right now. What I find sluggish is, that when I made a research request with a cheap model, it has the full search capabilites. Maybe I now want a more intelligent model, but don’t strip search completely from it, if it decides, that it has to look up information. Switching back and forth requires a lot of clicking in the ui. It is cumbersome when I want the same model, but with different estimated token cost, generally adjusted for the task. What would I use it for Planning Trips or researching would allow me to quickly select my preconfigured favorite models for the Task at hand. I could quickly prompt a detailed search based on some criteria, e.g. looking for interesting spots on the road when I plan a roadtrip from point A to point B. Right afterwards use the same model to rank or filter those models based on feedback and possibly reason over a clever schedule. Maybe still allowing for some search to lookup current conditions, timed events, known road blocks etc. Or simply ditch the research and try to develop a detailed goals & wishes, dos & don’ts list. Same pattern can be applied to learning new skills, researching new topics etc.
The contrast between selected and not selected of the model selector filter buttons is too low, making it harder to determine if a filter was selected or not
If a current chat goes off topic or the user moves to a different topic, the title of that chat stays the same with whatever the user first sent in that chat. I want an auto-updating chat title that updates every X amount of messages (either that can be configured by the devs or by the users) so we know the chat title isn’t outdated. [and yes i know there is a regenerate chat title option, but i want it to be auto]
Whenever switching profiles on mobile, you currently have to go to the sidebar, click your profile and then switch the profile. Since there is no way to set another default profile or remember the last used profile, I reckon it would be a good addition to add it somewhere in the header. Maybe next to the chat/canvas switcher or within the chat settings ui.
It would be great to add support for GPT‑5.6 Luna xhigh or max reasoning levels in T3 Chat. OpenAI recently changed the pricing for its Luna and Terra models, making GPT‑5.6 Luna xhigh and max reasoning levels considerably cheaper than many other available options. Adding these models could reduce costs while maintaining a high level of intelligence.
Can we get a toggle in the settings to permanently hide the long thread popup and the triangle at the bottom when you close the message?
The banner has done its job to warn me that content blockers can cause problems, I acknowledge it and decided I don’t care. (My blocker even says “0 trackers, ads and more blocked” so its not even that anything is actually being blocked) Let me disable the damn banner instead of showing it every single time I open a new tab.
https://github.com/JuliusBrussee/caveman#before--after
Currently exported chats do not contain search data and Search Grounding Details. The links and information in there is a useful snapshot.
Please and I mean please allow this to be turned off because I have been trying to create app store screenshots for my iPhone app. The aspect ratios that you have are not in proportion with what they want and whenever I try to manually say, "Hey, use this aspect ratio," it does not.
You have the information for some of the models for Intelligence, Coding, and Math. It would be good to sort/filter by these performance metrics so that users can know which models are better at each without having to go into each model individually or look it up.
Can you please add the date the chat was created next to the chat so that we can more easily filter through chats? Thanks
It would be really useful to have a way to archive profiles and then restore them later if needed. I am a student and use a profile for each class I am taking (so I have quite a few) and don’t want to delete them completely when I’m done with the class but also don’t want them on the sidebar and in the various menus. Yes, you could delete the profile and move the threads to another profile, but this isn’t really a solution as you are still losing the grouping information (I might want to look back at all the chats for an old class). My current workaround is to just download all of my account’s thread content from settings and use a script to extract specific profiles from that. Another minimal solution would be to make it easy to select all threads from a profile in the settings menu to make local archival of a profile a lot easier.
Users with long chat histories struggle to track down older conversations and have requested ways to search or filter by date. While adding timestamps to every chat title would clutter the clean UI, requiring users to type complex search commands (like date:2023) is too advanced and hidden for the average user. The Proposed Solution: Add a small "Filter" icon (like a funnel) directly next to or inside the "Search your threads..." bar. Clicking this icon would open a small, simple dropdown menu allowing users to visually select a timeframe. This dropdown could include quick options like "This Month", "Last 3 Months", or a simple calendar/date-range selector. Once selected, the sidebar only displays chats active during that period. The Benefit: This provides an incredibly intuitive, point-and-click way for average users to filter their chat history. It completely solves their frustration of losing older chats, makes the feature highly visible, and perfectly preserves the minimalist design of the chat list itself.
Users can sometimes lose track of their chats. While the sidebar logically groups chats by recent activity (e.g., "Last 7 Days", "Last 30 Days", "Older"), it doesn't give the precise date. Adding visible dates to the sidebar list would ruin the clean, minimalist design of the interface, but users still need context for when they last worked on a thread. Proposed Solution: Update the existing hover tooltip on sidebar chat titles (which currently just repeats the title). When a user hovers over a chat, it should display the specific date the user last interacted with it. Example Tooltip text: "History Lessons... (Last Active: May 12, 2026)" This keeps the UI clean while giving users exact clarity.
On PC, I’m used to doing Enter for send, and Shift+Enter for new line. On my tablet, however, the touch keyboard won’t allow me to send Shift+Enter, so I enabled the “Invert Send/New Line Behavior” setting and it solved my issue! However, this setting appears to sync between clients, leading to accidental sends after switching between clients. Bounding this setting to the client instead of syncing it would fix this issue, and should be pretty easy to implement. A middle ground could be a synced default and a local, persistent override. Ideally, we would only have to configure this behavior once per device and not have to keep mental track of which client we used last or go to the settings to change each time we open the website.