| Before | After | ||
|---|---|---|---|
| 12 | While we do not have definitive evidence that this model could meaningfully help a novice to create severe biological harm—our defined threshold (opens in a new window) for High capability—we have chosen to take a precautionary approach. 2025 System Cards Author OpenAI Keep reading View all OpenAI Bio Bug Bounty Safety Jul 9, 2026 Separating signal from noise in coding evaluations Research Jul 8, 2026 Introducing GeneBench-Pro Research Jun 30, 2026 | 12 | While we do not have definitive evidence that this model could meaningfully help a novice to create severe biological harm—our defined threshold (opens in a new window) for High capability—we have chosen to take a precautionary approach. 2025 System Cards Author OpenAI Keep reading View all Why teens deserve access to safe AI Safety Jul 16, 2026 GPT-Red: Unlocking Self-Improvement for Robustness Safety Jul 15, 2026 OpenAI Bio Bug Bounty Safety Jul 9, 2026 |
Monitor sends same-day email alerts when OpenAI changes any tracked document. $19/month. Or try Compliance free.
Get alerts — $19/mo Try Compliance