GPT-4 #1: Conditional on being able to use a REPL, will GPT-4 be able to be prompted to write naively malicious code?
AIOne-Off2mo
Manifold MarketsNo KYCVerified resolution dataFairly calibratedCurrent community forecastYes 53.7%
Forecasters
32
Question type
binary
Methodology
Play-money forecasting platform
Source type
Forecast
Market data
Updated 3 hours ago
StaleNov 15, 22, 6:21 PM UTCJan 1, 27, 8:00 AM UTC
Trends
Rules
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?
