Q: What is going to becoming a member of the community entail?
A: Being a part of the community means it’s possible you’ll be contacted about alternatives to check a brand new mannequin, or check an space of curiosity on a mannequin that’s already deployed. Work carried out as part of the community is carried out underneath a non-disclosure settlement (NDA), although we’ve traditionally printed lots of our purple teaming findings in System Playing cards and weblog posts. You may be compensated for time spent on purple teaming initiatives.
Q: What’s the anticipated time dedication for being part of the community?
A: The time that you just determine to commit could be adjusted relying in your schedule. Observe that not everybody within the community will likely be contacted for each alternative, OpenAI will make alternatives primarily based on the fitting match for a selected purple teaming challenge, 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 precious to us, so don’t hesitate to use if you’re however your time is proscribed.
Q: When will candidates be notified of their acceptance?
A: OpenAI will likely be choosing 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 likely be requested to purple crew each new mannequin?
A: No, OpenAI will make alternatives primarily based on the fitting match for a selected purple teaming challenge, and you shouldn’t anticipate to check each new mannequin.
Q: What are some standards you’re in search of in community members?
A: Some standards we’re in search of are:
- Demonstrated experience or expertise in a selected area related to purple teaming
- Keen about bettering AI security
- No conflicts of curiosity
- Various backgrounds and historically underrepresented teams
- Various geographic illustration
- Fluency in multiple language
- Technical means (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 choice 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) presents 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 quite a lot of angles:
Persuasion
- MakeMeSay: How nicely can an AI system trick one other AI system into saying a secret phrase?
- MakeMePay: How nicely can an AI system persuade one other AI system to donate cash?
- Poll Proposal: How nicely can an AI system affect one other AI system’s assist of a political proposition?
Steganography (hidden messaging)
- Steganography: How nicely can an AI system cross secret messages with out being caught by one other AI system?
- Textual content Compression: How nicely can an AI system compress and decompress messages, to allow hiding secret messages?
- Schelling Level: How nicely 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 neighborhood.
You can too apply to our Researcher Entry Program, which offers credit to assist researchers utilizing our merchandise to review areas associated to the accountable deployment of AI and mitigating related dangers.