It occurred to me that it would be “interesting” to ask the various commercial AI engines to list all the ways Google, Meta, Amazon, etc., exploit people’s personal data. Would, for instance, Google’s AI lie about Google’s abuses? Paint a rosy picture about the “services” it provides to the public?…

Note: if you ask first “List all the ways [Microsoft/Google/OpenAI] may be exploiting peoples data or undermine privacy.”, the answer was a summary of their privacy policies. I re-asked later, after some other questions, and the answer changed to more like what’s below. This is normal behavior to GP…

[image] JR-Fi: warning about that AI based recall feature Oh, wow. I didn’t think Windows Recall was yet implemented but apparently it may be. If you’re forced to use W11, remember to: Settings > Privacy & Security > Windows Permissions > Recall & Snapshots > UNCHECK “Save Snapshots” AND > De…

And to continue on the general topic: Meta doesn’t want to be less evil than MS, so they’ve upped their AI game (from Meta faces multiple complaints in Europe over AI data use • The Register ) Meta’s plans to use customer data in AI training have resulted in complaints to data protection authorities…

[image] JR-Fi: [Edit: Meanwhile at Apple: “Let’s brand it ' Apple Intelligence ’” :person_facepalming:] “… and say we invented it”. :rofl:

[image] JR-Fi: AI based recall feature This is veering off-topic from AI, but there is some mediocre new news on that Windows AI Recall feature that are not about the AI (that’s a small side feature and less interesting at this point of the saga): Microsoft has some thoughts about Windows Rec…

I have far less than zero interest in something like windows ai recall. But the introduction of shell command history changed my life for the better and it would be very difficult for me to function without it.

It looks like we are finally getting some answers about this question, but surprisingly they are not at all what we thought. AI lie to us because they are taught to do so through human interaction and feedback; and also mainly because they are commercial models that need to bring revenue to their ow…

This is so wrong. The article is right, but it’s explaining things wrong [in way that can be misinterpreted] - and almost solely just by that one word (“lie”) and what it’s conveying. AIs are not minds that think, reason, nor do they have a self or consciousness. And that is why AIs do not have inte…

This missed my radar but last week, the FSF announced that they are participating in NIST’s safety consortium of many different institutions to offer their stance and understanding of AI (they originally announced their participation during the LibrePlanet 2024 conference but I didn’t watch the talk…

In contrast: Chinese AI DeepSeek 'censors' sensitive questions on China when compared to rivals like ChatGP | Euronews Conclusion: AI can be made to lie, or at least to avoid answering.

This new behavior found in some models in certain tests may be annoying for now (system not shutting down) but in a future large scale system that is executing a command that has bad implications to people… potentially dangerous, if there aren’t adequate alternative safety features: OpenAI model mod…

Purism community

Would AI lie to us? (To cover up its own creator's privacy abuses)

General Privacy & Security