[HN Gopher] What LLMs Know About Their Users
       ___________________________________________________________________
        
       What LLMs Know About Their Users
        
       Author : voxleone
       Score  : 65 points
       Date   : 2025-06-25 18:49 UTC (4 days ago)
        
 (HTM) web link (www.schneier.com)
 (TXT) w3m dump (www.schneier.com)
        
       | wcarss wrote:
       | The link should probably be:
       | https://www.schneier.com/blog/archives/2025/06/what-llms-kno...
        
         | tveita wrote:
         | Or the post it quotes
         | https://simonwillison.net/2025/May/21/chatgpt-new-memory/
        
           | jazzyjackson wrote:
           | "6": "User is active 2 days in the last 1 day, 8 days in the
           | last 7 days, and 11 days in the last 30 days."
           | 
           | lol
        
             | Jensson wrote:
             | Is that how you work 200%?
        
             | HPsquared wrote:
             | I suppose the last 24 hours contains today and yesterday.
        
         | vavooom wrote:
         | I applied this query with 4o and yes, quite a thorough
         | historical recounting. Really weaves together all those
         | "random" questions one asks an LLM into a surprisingly (and
         | somewhat scary) encompassing of one's self.
        
       | holri wrote:
       | 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!
        
         | BoiledCabbage wrote:
         | Not to complain, but that test would be more interesting if you
         | ran it _with_ an account.
        
         | amelius wrote:
         | Of course that doesn't prove much. Perhaps the information is
         | only available to administrators.
        
         | noident wrote:
         | You might as well have asked the pen on your desk how much it
         | knows about you. Whether your personal data is in the current
         | LLM context window or not has nothing to do with whether it was
         | collected from you by Mistral.
        
         | wongarsu wrote:
         | Rather than ask it if it knows anything about you, ask it where
         | the nearest McDonalds is
         | 
         | Mistral seems honest in its assessment (as should be expected
         | from a French company operating under GDPR). But e.g. ChatGPT
         | will deny knowing your location, but still show a McDonalds
         | that suggests it knows your IP geolocation
        
           | holri wrote:
           | where is the nearest McDonald's? 18:51
           | 
           | I'm sorry, but I don't have the capability to access real-
           | time location data to find the nearest McDonald's for you.
           | However, you can easily find this information by using a maps
           | application on your phone or computer.
        
       | bgwalter wrote:
       | > User's account is 237 weeks old.
       | 
       | ChatGPT was released to the public on November 30, 2022.
       | 
       | Otherwise, this reads like an FBI file:
       | 
       | https://digitalcommons.unl.edu/usjusticematls/10/
        
         | simonw wrote:
         | I created an account with OpenAI back in 2020 to try out GPT-3,
         | which would explain that account age.
         | 
         | (I just confirmed that by searching my email for anything
         | mentioning OpenAI in 2020 and found an invite to create an
         | account in October 2020.)
        
       | jruohonen wrote:
       | Same old but there has been surprisingly little attention paid to
       | it in the present context.
        
       | nonelog wrote:
       | 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.
        
         | layer8 wrote:
         | Doesn't offer access to the usual paid models, which is why
         | it's free of charge.
        
       | hardlianotion wrote:
       | I still don't know what integrous means.
        
         | sydney6 wrote:
         | "Integrous" is a rarely used adjective meaning "having or
         | characterized by integrity". It's derived from the Latin word
         | "integer," meaning whole or complete, and the suffix "-ous"
         | indicating fullness or possession. While technically correct,
         | it's more common to use synonyms like "honest," "decent," or
         | "virtuous" to convey the concept of integrity.
         | 
         | Now, take a guess where this comes from..
        
       | simianwords wrote:
       | LLM's knowing things about us is genuinely useful - what's the
       | alternative here?
        
         | Diti wrote:
         | The alternative is that LLMs don't know anything about us, of
         | course. That's what Kagi's Assistants do.
        
         | GMoromisato wrote:
         | I don't care what chatGPT knows about me. But I do care what
         | OpenAI knows about me and how it will use that knowledge.
         | 
         | The alternative is transparency and verification of who has
         | that data.
        
         | holri wrote:
         | That the LLM is in control of us.
        
       | BurningFrog wrote:
       | 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?_
        
         | msgodel wrote:
         | I know someone else who uses Grok and has the "learn from my
         | responses" feature turned on, he claims it generates memories
         | (like chatgpt did for a while) although he might just not
         | understand how the dialog engine works.
        
       | EGreg wrote:
       | 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.
        
         | neom wrote:
         | I really dislike the new memory, find myself using temp chats
         | on ChatGPT a lot these days, they claim it adds nothing to mine
         | or the collective knowledge, although to be honest at this
         | point my trust in OpenAI is incredibly low.
        
       | nullc wrote:
       | 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.
        
       | rcruzeiro wrote:
       | Isn't this just outputting the same information that you can find
       | on my "administre memories" section of ChatGPT settings?
        
         | simonw wrote:
         | No. That's the old memory feature, where you could view and
         | delete individual memories.
         | 
         | This is the new memory feature where it automatically
         | summarizes notes from your previous conversations.
         | 
         | I wrote more about the difference between the two here:
         | https://simonwillison.net/2025/May/21/chatgpt-new-memory/#we...
        
       | marcusstorm wrote:
       | 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?
        
       ___________________________________________________________________
       (page generated 2025-06-29 23:01 UTC)