The critical thing now is to design a sensible system, and agree the benchmarks that will actually offer real oversight, and ensure that oversight is tied to delivering AI that works in the interests of everyone. Let's get started right away.
SAFETY
-
AI Training Audits: Scrutiny for Scale and Capabilities
By
–
It's time for meaningful outside scrutiny of the largest AI training runs. The obvious place to start is "Scale & Capabilities Audits" 1./
-
Stress Testing AI Alignment: Competing Interests Problem
By
–
I agree, but let's stress-test your idea: How could a zebra align with a lion?
-
Resisting Cynicism and Fear in AI Development
By
–
The apocalypse isn’t coming. We must resist cynicism and fear about #AI https://
bit.ly/3BydA66 #ethics -
OpenAI Hiring Machine Learning Engineer and Safety Researcher
By
–
(3/3) Then check out: – https://
openai.com/careers/machin
e-learning-engineer-moderation
… – https://
openai.com/careers/resear
ch-scientist-safety
… -
Model Safety Evaluation and Jailbreak Robustness Standards
By
–
(2/3) If you are interested in … – Defining evaluations for checking whether a model is safe enough to deploy – Detecting and stop harmful use cases. – Training models to say no to harmful requests and to be robust to jailbreak style vulnerabilities.
-
OpenAI Hiring Research Engineers for AI Safety Alignment
By
–
(1/3) Alongside Superalignment team, my team is working on the practical side of alignment: Building systems to enable safe AI deployment. We are looking for strong research engineers and scientists to join the efforts.
-
Detecting AI-Generated Bad Content: Challenges and Solutions
By
–
Catching bad content in the age of #AI https://
bit.ly/431fWpC via @techreview -
Build Cool AI with Kindness and Ethics
By
–
Will have limited internet for a few weeks. Be kind and build cool AI stuff
