All: There's no valid use cases for local LLM, unless you're doing something illegal or unethical, you creepy pervert and/or criminal
Also all: How come LLM (and the company that runs it and provides a way for me to access and use it) knows so much about me? That's creepy. And there's just no way anybody could predict that would happen
Isn’t this just outputting the same information that you can find on my “administre memories” section of ChatGPT settings?
> User’s account is 237 weeks old.
ChatGPT was released to the public on November 30, 2022.
Otherwise, this reads like an FBI file:
FWIW, Grok answers this when asked "what do you know about me?" (I do have an account):
I don’t have any personal information about you, as I don’t have access to user data unless it’s explicitly shared in the conversation. If you’ve posted publicly on X, I could potentially look up your profile or posts to learn more, but I’d need your X handle to do that. Alternatively, if you want to share something about yourself—like your interests, location, or what you’re curious about—I can tailor my responses based on that. What would you like me to know or explore about you?
This is like the prompts which ask the LLM to act as a spy / FBI agent, to expose what it knows about the user, right?
I still don't know what integrous means.
Same old but there has been surprisingly little attention paid to it in the present context.
I just asked Mistral.ai, using it without an account:
what do you know about me? 2:50pm
I don't know anything about you unless you share information with me. How can I assist you today? 2:50pm you do not know my IP and its location? 2:50pm
That's correct, I don't have access to your IP address or your location. If you need assistance with something specific, feel free to let me know!
People's privacy expactations are miscalculated in a world with LLMs. Before LLMs there was little reason to care if you were leaving breadcrumbs, because no one with access was going to investigate them and draw conclusions from them.
The fact that the LLMs are prone to hallucinations and fanciful conclusion jumping probably make things worse, because the only way to be safe from it wrongfully concluding things about you is to just be invisible to it.
The solution is to use www.duck.ai.
Full privacy, no data collection, no User profiling, no surveillance, no training with your data.
Plus, you can chose your preferred AI model: Claude, GPT, etc.
And it's even free of charge.
When I speak to ChatGPT and other LLMs, I am mindful of the profile they build on me and what I ask about. And even how I ask it.
It is the same as I have been doing for 15 years on public social media.
LLM's knowing things about us is genuinely useful - what's the alternative here?
The link should probably be: https://www.schneier.com/blog/archives/2025/06/what-llms-kno...