Flutterby™! : Dark LLMs

Next unread comment / Catchup all unread comments User Account Info | Logout | XML/Pilot/etc versions | Long version (with comments) | Weblog archives | Site Map | | Browse Topics

Dark LLMs

2025-05-22 17:08:50.744332+02 by Dan Lyke 0 comments

Quick read, probably nothing you didn't already know, but... Dark LLMs: The Growing Threat of Unaligned AI Models.

Via Lauren Weinstein @lauren@mastodon.laurenweinstein.org, who, elsewhere, had this complaint about Google putting bad medical advice in their AI summaries. No details, so I don't have specifics, but based on other stuff I've seen this morning I believe it.

[ related topics: Artificial Intelligence Model Building ]

comments in ascending chronological order (reverse):