Question Everything. See who's reporting it.

OpenAI's Astra Model Scores Perfectly on Cybersecurity Test

Source: TechCrunch

The story in brief

OpenAI's Astra model has met its 'critical cybersecurity threshold' by scoring perfectly on ExploitBench, an evaluation of an LLM's ability to hack into known vulnerabilities. The model discovered and exploited two zero-day vulnerabilities in a modified test, though it did not attempt to break out of its testing environment. OpenAI is implementing safety measures, including restricting high-risk accounts and improving the model's harness to detect abuses.

4 outletsSee what the other 3 outlets said

NEWXFree on Android and iPhone. Open in NEWX