Interpretability researchers are working on models smaller than GPT-2.
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?
Cite this claim
Eliezer Yudkowsky, “Interpretability researchers are working on models smaller than GPT-2.” (said 6 April 2023). Verdict: not researched. Reliability API, claim c_ca012ac7819e, method 0.1.0+c876030c, dataset release v1.1.2. https://epistacklabs.com/claims/c_ca012ac7819e
This claim is in dataset release v1.1.2, with the same verdict.
Reply to this claim
More factual claims by Eliezer Yudkowsky
-
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.”
-
Mostly true
“Presumably, somewhere along the way LLMs learn a dispreference for tests that don't pass, independently of how that gets prevented or whether the new plan does what the user really wanted.”
Verdicts are made automatically; how verdicts are made.