As of November 2019, there was no systematic way of solving this problem and its many variations, and Marcus said he thinks there may be no possibility of doing so.
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
Gary Marcus, “As of November 2019, there was no systematic way of solving this problem and its many variations, and Marcus said he thinks there may be no possibility of doing so.” (said 14 November 2019). Verdict: not researched. Reliability API, claim c_cfb8018c37c1, method 0.1.0+c876030c, dataset release v1.1.2. https://epistacklabs.com/claims/c_cfb8018c37c1
This claim is in dataset release v1.1.2, with the same verdict.
Reply to this claim
More factual claims by Gary Marcus
-
Mostly true
“Even this was still a mix of euphemism (“attacks” were called “interactions”) and partial disclosure.”
OpenAI's latest account called attacks "interactions" and only partially disclosed what happened.
-
Mostly true
“It didn’t just attack a German web server.”
-
Resolved true
“It didn’t just attack Australia’s government servers.”
-
Mostly true
“So with LLMs, people do things like put stuff in a system prompt, and they can’t get systems with the system prompts to follow them.”
People put instructions in LLM system prompts but cannot get the systems to follow them.
-
Mostly true
“a just-published technique shows that current LLMs can be jailbroken quickly, and automatically.”
A newly published technique shows that current LLMs can be jailbroken quickly and automatically.
Verdicts are made automatically; how verdicts are made.