Commenters question terminology and probe for undisclosed incidents
2 Sep 17 12:38 PM · 9d ago · 4 comments · 1 source · development 2 of 3
Hacker News discussion raised questions about the framing of 'misalignment' and whether the framework was a genuine transparency measure. One commenter, bix6, noted the most interesting point was that none of the six disclosed case studies affected real users, asking 'What are they not releasing that has affected real users?' citing anecdotal reports of AI causing user harm.
“What are they not releasing that has affected real users? We've seen some individual reports from people (eg AI wiped my HD).”
bix6OpenAI AI company releasing frameworkKerrickStaley OpenAI framework contributorGoogle, Meta, Anthropic Competing AI firms
The whole story articlespostscomments the bright band is this development · numbered dots are the others · click one to jump
What people said 4 voices · best of 5 · verbatim
-
Am I the only one who dislikes the term "misalignment"?On one front it implies the model has a "mind of its own" (whether it does or not is besides the point). Why do we perceive human judgement as somehow more trustworthy than that of a model? I feel like I've experienced human misalignment somewhat regularly in life.On another front I'm failing…
-
What's with all this make believe delusional bullshit? The LLM is not gonna wake up and become AI. Get real guys.[edit] to be clear, I believe regulation is necessary and urgently important for the software engineering field. The damage being done by the unregulated psychological experiments run by social media and adtech companies is awful and…
-
This entire situation is such a huge PR disaster that you have to wonder what the initial expectations from these founders were about a decade ago.
-
i think the lower bound on the end state is there cant be opaque reasonibg steps ever.
All 3 developments of OpenAI releases misalignment framework to disclose model… →
MastodonHacker NewsNewswires