News for hackers. Stuff that matters.
Re:AlphaProof Code by doginasuit on Tuesday November 10, 2026 @09:47AM (#50441149)
Not the OP, but I was asking gemini about a Google subscription I had, trying to figure out whether I would lose a particular feature if I changed the subscription. I asked whether my subscription was "grandfathered" and it assured me it was not, then later on acknowledged that I was on a legacy subscription that I would not be able to go back to.

Compared to the other LLMs I've used, it seems to have system instructions that are far more adversarial to the user.

Re:AlphaProof Code by cwmoore on Tuesday November 10, 2026 @10:27AM (#50441745)
Ask for “grandmothered” for a more forgiving response
Re:AlphaProof Code by qlte on Tuesday November 10, 2026 @05:23PM (#50447145)
Claude frequently gets basic details wrong about current policies/CC behavior/etc. It's an LLM issue in general trying to keep the system prompt enriched with enough recent docs about itself. Or else it may blurt out misleading/wrong info from blogspam SEO-maxed Google results from a year ago and stuff.