Combining "triangular" with "light bulb" is a structured imposition of one concept on the other, not a collision: "triangular" is imposed on "light bulb."
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, “Combining "triangular" with "light bulb" is a structured imposition of one concept on the other, not a collision: "triangular" is imposed on "light bulb."” (said 2007). Verdict: not researched. Reliability API, claim c_f5f92dc3682f, method 0.1.0+c876030c, dataset release v1.1.2. https://epistacklabs.com/claims/c_f5f92dc3682f
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.