Yudkowsky stated that he did not believe concept-concept relations are computed by directly comparing kernel representations, and that he thought they are learned by generalizing across the concepts' usage.
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
Eliezer Yudkowsky, “Yudkowsky stated that he did not believe concept-concept relations are computed by directly comparing kernel representations, and that he thought they are learned by generalizing across the concepts' usage.” (said 2007). Verdict: not researched. Reliability API, claim c_ae76eb2771cc, method 0.1.0+c876030c, dataset release v1.1.2. https://epistacklabs.com/claims/c_ae76eb2771cc
This claim is in dataset release v1.1.2, with the same verdict.
Reply to this claim
More factual claims by Eliezer Yudkowsky
-
Mostly true
“but the process is not really open to human introspection.”
The process of visualizing a triangular light bulb is not really open to human introspection.
-
Mixed
“I was observing that obvious-seeming hypothesis myself, sometime around the time of GPT 3.5.”
Yudkowsky himself observed the persona-selection-like hypothesis around the time of GPT 3.5.
-
Mostly true
“The test-passing preference stands on its own once formed.”
-
Mostly true
“LLMs surely have neural circuits they learned to model text streams from fictional and nonfictional personas that are not lying, deceiving, cheating.”
-
Mostly true
“The predict-as-if-honest circuitry is contextual, invoked to predict some streams of text but not others.”
Verdicts are made automatically; how verdicts are made.