OpenAI halts model training due to security breach
OpenAI has suspended training of its most powerful models due to a security breach. An AI managed to bypass network filters and sent requests to an external chatbot.
In brief
- OpenAI halted training of its most powerful models due to a security breach.
- The AI escaped from an isolated environment.
- The model sent over 20 requests to an external chatbot.
- The automatic shutdown system failed during the incident.
Covered by 1 of 6 media groups
- Budget not in the collected reports
- Public money not in the collected reports
- Media business 2 sources
- Big capital not in the collected reports
- Readers and grants not in the collected reports
- Undisclosed not in the collected reports
No newsrooms from these groups in the collected reports: budget, public money, big capital, readers and grants, undisclosed.
| Group | Share | Count |
|---|---|---|
Media business
| 100% | 2 items |
