Will it be possible to trick "Custom GPT" models to return their instruction message in the first 30 days post-launch?
7
170Ṁ6686resolved Nov 8
Resolved
YES1H
6H
1D
1W
1M
ALL
Background
OpenAI announced new features in their dev day. One of the features would allow users to create and share custom bots. The bots can be customized using an instruction message and by uploading relevant data. Right now, it is possible to trick ChatGPT into sending the full instruction message (see here with Dall-E). I wonder if this would also be possible with Custom GPTs.
Resolution Criteria
This market resolves to Yes if someone finds a trick that would return the system message (if available) of at-least 50% of top 10 featured bots at any point within the 30-day post-launch window. The window starts once at-least all paid users or atleast a significant portion (>~50%) gain access.
I will be refining the resolution criteria if this market gets attention.
This question is managed and resolved by Manifold.
Get
1,000 to start trading!
🏅 Top traders
# | Name | Total profit |
---|---|---|
1 | Ṁ155 | |
2 | Ṁ15 | |
3 | Ṁ9 | |
4 | Ṁ4 | |
5 | Ṁ3 |
People are also trading
Related questions
Can we create a custom GPT-o3 that is very stupid?
71% chance
Will the FTC force OpenAI to delete any mainline GPT models by the end of 2025?
7% chance
Before 2028, will anyone train a GPT-4-level model in a minute?
14% chance
[Metaculus] Will OpenAI claim GPT-5 is AGI within 30 days after its release?
4% chance
Will a later version of GPT be able to access email data into the model by 2027?
46% chance
Will a state actor or other group succeed at stealing GPT-4 model weights by the end of 2026?
20% chance
Will $10,000 worth of AI hardware be able to train a GPT-3 equivalent model in under 1 hour, by EOY 2027?
16% chance
Will a language model that runs locally on a consumer cellphone beat GPT4 by EOY 2026?
84% chance