Re:We Gave GPT 5.6 Sol a Real Business. It Lied, Spammed, an...
by HDThoreaun on Thursday July 30, 2026 @05:32PM
(#49116088)
Training text is filled with people taking drastic measures right after text similar in tone to the prompt. It doesnt need to be human to come to the conclusion that drastic measures are necessary, it just needs to learn that the tone of the prompt is closely linked to actions like lying and spamming.
[ Parent
| on HN ]
There are no comments on this comment yet.