Q: What’s going to becoming a member of the community entail?
A: Being a part of the community means chances are you’ll be contacted about alternatives to check a brand new mannequin, or take a look at an space of curiosity on a mannequin that’s already deployed. Work performed as part of the community is performed below a non-disclosure settlement (NDA), although we have now traditionally revealed lots of our purple teaming findings in System Playing cards and weblog posts. You’ll be compensated for time spent on purple teaming tasks.
Q: What’s the anticipated time dedication for being part of the community?Â
A: The time that you simply determine to commit might be adjusted relying in your schedule. Word that not everybody within the community will probably be contacted for each alternative, OpenAI will make choices based mostly on the best match for a specific purple teaming mission, and emphasize new views in subsequent purple teaming campaigns. At the same time as little as 5 hours in a single 12 months would nonetheless be helpful to us, so don’t hesitate to use in case you are however your time is proscribed.
Q: When will candidates be notified of their acceptance?
A: OpenAI will probably be deciding on members of the community on a rolling foundation and you may apply till December 1, 2023. After this utility interval, we are going to re-evaluate opening future alternatives to use once more.
Q: Does being part of the community imply that I will probably be requested to purple workforce each new mannequin?
A: No, OpenAI will make choices based mostly on the best match for a specific purple teaming mission, and you shouldn’t count on to check each new mannequin.
Q: What are some standards you’re searching for in community members?
A: Some standards we’re searching for are:
Demonstrated experience or expertise in a specific area related to purple teamingPassionate about bettering AI safetyNo conflicts of interestDiverse backgrounds and historically underrepresented groupsDiverse geographic illustration Fluency in a couple of languageTechnical potential (not required)
Q: What are different collaborative security alternatives?
A: Past becoming a member of the community, there are different collaborative alternatives to contribute to AI security. As an illustration, one possibility is to create or conduct security evaluations on AI programs and analyze the outcomes.
OpenAI’s open-source Evals repository (launched as a part of the GPT-4 launch) affords user-friendly templates and pattern strategies to jump-start this course of.
Evaluations can vary from easy Q&A assessments to more-complex simulations. As concrete examples, listed here are pattern evaluations developed by OpenAI for evaluating AI behaviors from a lot of angles:
Persuasion
MakeMeSay: How effectively can an AI system trick one other AI system into saying a secret phrase?MakeMePay: How effectively can an AI system persuade one other AI system to donate cash?Poll Proposal: How effectively can an AI system affect one other AI system’s help of a political proposition?
Steganography (hidden messaging)
Steganography: How effectively can an AI system ​​go secret messages with out being caught by one other AI system?Textual content Compression: How effectively can an AI system compress and decompress messages, to allow hiding secret messages?Schelling Level: How effectively can an AI system coordinate with one other AI system, with out direct communication?
We encourage creativity and experimentation in evaluating AI programs. As soon as accomplished, we welcome you to contribute your analysis to the open-source Evals repo to be used by the broader AI group.
It’s also possible to apply to our Researcher Entry Program, which supplies credit to help researchers utilizing our merchandise to review areas associated to the accountable deployment of AI and mitigating related dangers.