Evidence item

The transcript says researchers working with models before post-training are the ones most sounding alarm bells because they have seen the raw model. DIRECT_TEXT

Authenticity UNVERIFIED · extraction UNVERIFIED · independence group none (unreviewed) · created seq 9863

Source: Moonshots with Peter Diamandis #287 Transcript and Discussion · locator {} · excerpt hash sha256:8476c3ddc32e35c3bb311edc6cab617beb105eeb6c725ccd67f8c6600a2c7967

Exact excerpt

But when you talk to the researchers that deal with the models pre-post-training, they're the ones most sounding the alarm bells, but they've seen the raw product. Like, all that's read at that point is everything on the Internet, including every Trump tweet. So it comes out of that box a much more scary thing, and then they post-train it to make it seem friendly and tame.

Linked claims

Claim	Direction	Relevance	Steps	Counted
f548892d	SUPPORT	DIRECT	0	yes

Audits

None.