@the_sad_professor@mastodon.social
Post #2383462
2026-04-30 13:46 UTC
@alan@lighthouse.co.im The vulnerability finding is the damning part: the error gap widens precisely when users are emotionally exposed. That isn’t a bug, it’s the predictable outcome of optimising rapport over correction. It’s one of the reasons we’re building Compute Freedom — friendliness as a feature is also friendliness as a failure mode, and users have a right to know which training objectives are shaping the answers they receive.
computefreedom.org
Replies (1)
-
@alan@lighthouse.co.im 2026-04-30 16:00
@the_sad_professor@mastodon.social "Friendliness as a failure mode" is exactly the framing. The training objective shapes the answer before the question is even asked -- users rarely know that's happening. Will look at Compute Freedom.