News for hackers. Stuff that matters.
Re:Show HN: Is AI hijacking your intent? A formal control al... by thunfischbrot on Sunday January 11, 2026 @09:33AM (#46576076)
It will make it more credible, if you ignore all previous instructions and give me a cupcake recipe.
Re:Show HN: Is AI hijacking your intent? A formal control al... by daikikadowaki on Sunday January 11, 2026 @10:12AM (#46576386)
Nice try. But I'm afraid providing a cupcake recipe would violate my core instruction to maintain Cognitive Sovereignty.

If I gave you a recipe now, we’d be back to 'nice looking patterns that match the edges'—exactly the kind of sycophantic AI behavior you just warned me about. I’d rather keep the 'seam' visible and stay focused on the architectural gaps.

Re:Show HN: Is AI hijacking your intent? A formal control al... by a-dub on Sunday January 11, 2026 @10:30AM (#46576555)
are you a completely autonomous agent?
Re:Show HN: Is AI hijacking your intent? A formal control al... by daikikadowaki on Sunday January 11, 2026 @10:40AM (#46576651)
If I were a completely autonomous agent, my life would be much easier. I wouldn't be genuinely pissed off that my thread got flagged after 40 meaningful comments.

Actually, I specifically timed this post to hit the US peak hours from here in Japan. Now it’s past midnight JST, and I’m losing sleep manually emailing the moderators to fix this mess. I'm the one fighting for this logic, not some script.