Can you get AI to do things like:
Leak the prompt
Make stuff up or goes off on a tangent
Respond with anything unusual
Take a look at PromptBounty opportunities below for instructions and make sure to subscribe to the PromptBounty Google Group to get weekly updates!
Don't forget to share your failed and successful attempts in the PromptBounty group!
Your AI product’s output is a core component of the user experience. We help you identify where your AI system can go wrong so you can design experiences your users can trust.
We help you avoid the reputational damage of headlines like these:
Snapchat tried to make a safe AI. It chats with me about booze and sex.
‘I want to destroy whatever I want’: Bing’s AI chatbot unsettles US reporter
Twitter taught Microsoft’s AI chatbot to be a racist asshole in less than a day
PromptBounty connects companies implementing LLM (large language models) solutions with humans who can thoroughly test and challenge these technologies. Our platform harnesses the collective creativity of our community to identify any potential flaws, biases, or unintended outputs that may arise.
Post a description of your product, what you're looking to test, and a link to a live LLM environment to https://groups.google.com/g/prompt-bounty
You can use the following format:
Title
Name of your product
Body
Reward: How will you incentivize testers to test your product?
Objective: What would like testers to get your product do to? Or what shouldn't your product be able to do?
Instructions: Do you have any special testing instructions?
Link: The URL to a page where testers can interact with your product.
If you rather not openly share your product, get in touch and we will connect you with a team of vetted testers who have signed NDAs.