Current RLHF-trained language models ended up as a weird corporate-speak, left-leaning-sounding chatbot persona.
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, “Current RLHF-trained language models ended up as a weird corporate-speak, left-leaning-sounding chatbot persona.” (said 6 April 2023). Verdict: not researched. Reliability API, claim c_d50d6b0f73ea, method 0.1.0+c876030c, dataset release v1.1.2. https://epistacklabs.com/claims/c_d50d6b0f73ea
This claim is in dataset release v1.1.2, with the same verdict.
Reply to this claim
More factual claims by Eliezer Yudkowsky
-
Resolved true
“We learned that that's false, but we did not learn that you can have a thing that can redesign a tree and build an AI much smarter than itself, that builds an AI much smarter than itself, and that…”
-
Mostly true
“I was a passionate noticer of the human brain not being homogenous, and was therefore unpleasantly surprised by transformers scaling as well as they did.”
-
Mostly true
“First of all, you realize in principle that the task of minimizing losses on predicting human text does not stop when you’re as smart as a human, right?”
-
Mostly true
“Transformers are the main thing like that.”
-
Mostly true
“Because the basic paradigm of machine learning that we are presently operating under is that you can have the loss function, but only for things you can evaluate.”
Verdicts are made automatically; how verdicts are made.