Seeing the private information in this footnote increased our worry about risks from what Anthropic refers to as “Broad/diffuse sandbagging on safety-relevant R&D” and “Targeted undermining of safety-relevant R&D” from models covered by the report.
METR says a footnote raised its worry about Anthropic-flagged sandbagging risks
AIMETR says a footnote in an Anthropic report increased its concern about two risks: broad, diffuse sandbagging on safety-relevant R&D, and targeted undermining of safety-relevant R&D by covered models. The post does not provide further details about the footnote's contents.
Source details
METR · x.comPublished
Original title: Seeing the private information in this footnote increased our worry about risks from what Anthropic refers to as “Broad/diffuse sandbaggi...