What happened
OpenAI published preliminary cybersecurity evaluations for its Astra system. The company also announced steps to strengthen its safeguards and security controls. The release focuses on assessing risks related to critical cyber capabilities.
The context
Safety evaluations help measure technical risks before systems broaden access. Publishing early test results gives outside observers insight into how OpenAI benchmarks system security.
Sources
- Official source, https://openai.com/index/responding-next-frontier-critical-cyber-capabilities Primary source