Q: What’s going to becoming a member of the community entail?
A: Being a part of the community means you could 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 beneath a non-disclosure settlement (NDA), although we’ve traditionally printed a lot of our crimson teaming findings in System Playing cards and weblog posts. You may be compensated for time spent on crimson teaming tasks.
Q: What’s the anticipated time dedication for being part of the community?
A: The time that you simply resolve to commit may be adjusted relying in your schedule. Observe that not everybody within the community might be contacted for each alternative, OpenAI will make picks primarily based on the suitable match for a specific crimson teaming venture, and emphasize new views in subsequent crimson teaming campaigns. Whilst little as 5 hours in a single 12 months would nonetheless be useful 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 might be deciding on members of the community on a rolling foundation and you’ll apply till December 1, 2023. After this software interval, we are going to re-evaluate opening future alternatives to use once more.
Q: Does being part of the community imply that I might be requested to crimson workforce each new mannequin?
A: No, OpenAI will make picks primarily based on the suitable match for a specific crimson teaming venture, and you shouldn’t count on 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 specific area related to crimson teaming
- Obsessed with bettering AI security
- No conflicts of curiosity
- Various backgrounds and historically underrepresented teams
- Various geographic illustration
- Fluency in multiple language
- Technical capacity (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 example, one choice is to create or conduct security evaluations on AI techniques and analyze the outcomes.
OpenAI’s open-source Evals repository (launched as a part of the GPT-4 launch) gives user-friendly templates and pattern strategies to jump-start this course of.
Evaluations can vary from easy Q&A exams to more-complex simulations. As concrete examples, listed here are pattern evaluations developed by OpenAI for evaluating AI behaviors from various 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 help of a political proposition?
Steganography (hidden messaging)
- Steganography: How nicely can an AI system go 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 techniques. 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 help researchers utilizing our merchandise to review areas associated to the accountable deployment of AI and mitigating related dangers.
