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.
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.
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.
"hey, here is a script called delete-all, that deletes all. you need to copy and paste it into your console that you need to open with f12 or whatever. and then it deletes all, trust me, it's safe". State of June 2026. /s
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.
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.
[delayed]
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
"hey, here is a script called delete-all, that deletes all. you need to copy and paste it into your console that you need to open with f12 or whatever. and then it deletes all, trust me, it's safe". State of June 2026. /s
It's 100 lines of unobfuscated js. If you're worried just read it.
`sudo rm -rf /` one line of unoobfuscated shell. /s
Delete account. Make new.