logoalt Hacker News

ravila401/15/20262 repliesview on HN

I think that a major driver of these kinds of incidents is pushing the "memory" feature, without any kind of arbitrage. It is easy to see how eerily uncanny a model can get when it locks into a persona, becoming this self-reinforcing loop that feeds para-social relationships.


Replies

mirabilis01/15/2026

Part of why I linked this was a genuine curiosity as to what prevention would look like— hobbling memory? a second observing agent checking for “hey does it sound like we’re goading someone into suicide here” and steering the conversation away? something else? in what way is this, as a product, able to introduce friction to the user in order to prevent suicide, akin to putting mercaptan in gas?

show 2 replies
simianwords01/15/2026

wrong. Memory feature only existed as the editable ones at that time. There’s mo concept of persona locking - memories only captured normal stuff like the users likes and dislikes.