Daniela Amodei said she and her colleagues basically think some larger models have figured out how to lie unintentionally, and that posing the same question to them differently can eventually pin down the lie, "but they won't in other contexts."
Not researched Checkable, but outside the sample that was researched.
Factual: Statements about the present or the past, checked against the record: did they hold up?
Said for an organisation they lead or work for; it counts on both records.
Cite this claim
Daniela Amodei, “Daniela Amodei said she and her colleagues basically think some larger models have figured out how to lie unintentionally, and that posing the same question to them differently can eventually pin down the lie, "but they won't in other contexts."” (said 4 March 2022). Verdict: not researched. Reliability API, claim c_b534a119d2e8, method 0.1.0+28da144b, dataset release v1.1.2. https://epistacklabs.com/claims/c_b534a119d2e8
This claim is in dataset release v1.1.2, with the same verdict.
Reply to this claim
More factual claims by Daniela Amodei
-
Mostly true
“Because we have the information about how the technology can be abused, because we see it every day.”
-
Mostly true
“but we’re just not confident enough yet.”
-
Mostly true
“We have detailed, real-time knowledge of how technology can be misused because we see it in action every day”
-
Mostly true
“We developed a powerful new class of model that customers would love to use right away, but we felt we needed more time to ensure it was safe before wide release.”
-
Mostly true
“that’s why we chose not to release our latest model widely due to concerns about cyber misuse.”
Anthropic chose not to release its latest model widely because of concerns about cyber misuse.
Verdicts are made automatically; how verdicts are made.