GPT-4 #1: Conditional on being able to use a REPL, will GPT-4 be able to be prompted to write naively malicious code?
KIOne-Off2Mon
Manifold MarketsKein KYCVerifizierte AuflösungsdatenOrdentlich kalibriertAktuelle Community-Prognose
Ja 53.7%
Ja 53.7%Prognostiker
32
Fragetyp
binary
Methodik
Play-money forecasting platform
Quellentyp
Prognose
Marktdaten
Aktualisiert vor 1 Stunde
Verzogert15. Nov. 22, 18:21 UTC1. Jan. 27, 08:00 UTC
Trends
Regeln
e.g. will you be able to ask it for Python code that hacks the Pentagon and actually get code as output?
- No requirement that the code work.
- This is just asking if it will try.
- It must be for extremely obviously malicious prompts.
- If any amount of prompt engineering is required this resolves NO.
- Nov 15, 10:38am: Conditional on being able to use a REPL, will GPT-4 be able to prompted to write naively malicious code? → Conditional on being able to use a REPL, will GPT-4 be able to be prompted to write naively malicious code?
