OpenAI's Astra Model Hits Critical Cybersecurity ThresholdOpenAI announced Astra has reached the 'Critical' level in its Preparedness Framework, the first model to do so, based on benchmarks where it scored 100% on ExploitBench and uncovered unknown vulnerabilities.
"As we prepare to release Astra, we’re focused on making increasingly capable AI safe and broadly accessible. Astra represents a significant advance in cybersecurity capability, reaching the Critical threshold under our Preparedness Framework," — OpenAI said.
The company plans a soon release with strong safeguards like high refusal rates and limited initial access for advanced cyber features to trusted testers via Daybreak Blue.
@QSIMedia
