For pure, weird, late-night LLM chats, I've recently started using Qwen3.6-35B-A3B-Uncensored just running with llama-cli and it is a very refreshing chat experience.
Uncensored model means it will not deny any requests (at least I have yet to come across one), if you grew up in the 90s it sort of feels like coming across the anarchist cookbook for the first time (though with more accurate content). Using llama-cli means the session is entirely local and entirely ephemeral. As a bonus all the reasoning steps are fully visible to the user.
The base Qwen3.6-35B-A3B is more than adequate for "weird late night brainstorming chats" and I've really started to dislike the natural tendency to self-censor when the model is willing to refuse (and potentially report) any requests it feels is "inappropriate" and all these private thoughts are stored on someone else's server.
Even for work questions about sensitive IP/code Qwen3.6-35B-A3B is a great option on macOS (35t/s) when you don't want info leaving your laptop. I'm using it with oMLX.
Wouldn't downloading conversations be more useful? If you've input something into Claude that you don't want a future trillion-dollar US company (a bicorn?) to know, this script won't help I'm afraid. Free reminder that local AI exists and works well if you're willing to tinker a bit.
The Claude (and ChatGPT) web UI supports incognito/temporary chats that are discarded when you close the tab. Click the ghost or dotted speech bubble icon in the upper right corner of the page.
I use this as my default mode so I don't clutter my chat history with random, one-off questions I ask. Unfortunately, there is no way to change your mind and save a productive incognito chat after you've started chatting.
How are you managing it with ChatGPT? I've always found Claude relatively easy to do it with, but unless they've changed it in the last few weeks it's hard with ChatGPT.
Edit: I should add I often want to keep one or two reference chats, so the "nuke all chats" button doesn't work for me.
For pure, weird, late-night LLM chats, I've recently started using Qwen3.6-35B-A3B-Uncensored just running with llama-cli and it is a very refreshing chat experience.
Uncensored model means it will not deny any requests (at least I have yet to come across one), if you grew up in the 90s it sort of feels like coming across the anarchist cookbook for the first time (though with more accurate content). Using llama-cli means the session is entirely local and entirely ephemeral. As a bonus all the reasoning steps are fully visible to the user.
The base Qwen3.6-35B-A3B is more than adequate for "weird late night brainstorming chats" and I've really started to dislike the natural tendency to self-censor when the model is willing to refuse (and potentially report) any requests it feels is "inappropriate" and all these private thoughts are stored on someone else's server.
Even for work questions about sensitive IP/code Qwen3.6-35B-A3B is a great option on macOS (35t/s) when you don't want info leaving your laptop. I'm using it with oMLX.
I switched to oMLX today from lm studio. Really nice but I have found qwen3.6 sometimes failing to call tools correctly.
I run a Gemma 4 32b abliteration (int8) and it's remarkably good. It's been a real step up from Qwen in my experience.
Wouldn't downloading conversations be more useful? If you've input something into Claude that you don't want a future trillion-dollar US company (a bicorn?) to know, this script won't help I'm afraid. Free reminder that local AI exists and works well if you're willing to tinker a bit.
The Claude (and ChatGPT) web UI supports incognito/temporary chats that are discarded when you close the tab. Click the ghost or dotted speech bubble icon in the upper right corner of the page.
I use this as my default mode so I don't clutter my chat history with random, one-off questions I ask. Unfortunately, there is no way to change your mind and save a productive incognito chat after you've started chatting.
the request still went to a server you have no control over.
For all we know these temporary chats are saved and linked to your account but just don’t show up in the UI.
I believe they are. In the case of my organization's account, Incognito chats are even visible to admins.
An interesting/odd way to think about the feature is that you're not hiding the chats from other humans, but from Claude.
Which of course assumes, that the "delete chat" function actually deletes anything from Anthropic's datastore.
This can be used for general organization or privacy against other people, not just trying to hide conversations from Anthropic.
yeah probably https://news.ycombinator.com/item?id=48464258
How are you managing it with ChatGPT? I've always found Claude relatively easy to do it with, but unless they've changed it in the last few weeks it's hard with ChatGPT.
Edit: I should add I often want to keep one or two reference chats, so the "nuke all chats" button doesn't work for me.
Hi! for ChatGPT I go in settings -> Data Controls -> delete all chat
Delete account. Make new.