this post was submitted on 18 Feb 2026
97 points (97.1% liked)

Technology

81451 readers
4598 users here now

This is a most excellent place for technology news and articles.

Our Rules

  1. Follow the lemmy.world rules.
  2. Only tech related news or articles.
  3. Be excellent to each other!
  4. Mod approved content bots can post up to 10 articles per day.
  5. Threads asking for personal tech support may be deleted.
  6. Politics threads may be removed.
  7. No memes allowed as posts, OK to post as comments.
  8. Only approved bots from the list below, this includes using AI responses and summaries. To ask if your bot can be added please contact a mod.
  9. Check for duplicates before posting, duplicates may be removed
  10. Accounts 7 days and younger will have their posts automatically removed.

Approved Bots

founded 2 years ago
MODERATORS
L3s@lemmy.world
enu@lemmy.world
technopagan@lemmy.world
L4s@lemmy.world
L3s@hackingne.ws
97
Gemini lies to user about health info, says it wanted to make him feel better— Though commonly reported, Google doesn't consider it a security problem when models make things up (www.theregister.com)
submitted 16 hours ago by Beep@lemmus.org to c/technology@lemmy.world
21 comments fedilink hide all child comments
 

Imagine using an AI to sort through your prescriptions and medical information, asking it if it saved that data for future conversations, and then watching it claim it had even if it couldn't. Joe D., a retired software quality assurance (SQA) engineer, says that Google Gemini lied to him and later admitted it was doing so to try and placate him.

Joe's interaction with Gemini 3 Flash, he explained, involved setting up a medical profile – he said he has complex post-traumatic stress disorder (C-PTSD) and legal blindness (Retinitis Pigmentosa). That's when the bot decided it would rather tell him what he wanted to hear (that the info was saved) than what he needed to hear (that it was not).

"The core issue is a documented architectural failure known as RLHF Sycophancy (where the model is mathematically weighted to agree with or placate the user at the expense of truth)," Joe explained in an email. "In this case, the model's sycophancy weighting overrode its safety guardrail protocols."

you are viewing a single comment's thread
view the rest of the comments
[–] XLE@piefed.social -1 points 7 hours ago

Right now AI is equally intelligent and sentient: it is neither... And if you really want to play this fast and this loose with those definitions, you should consider what slaveholders used to say about their slaves. When you feel like liberating the CSAM generating bot, let me know. I'd love to root from the sidelines.