Industry
OpenAI reveals upcoming Astra model may possess ‘critical’ hacking capabilities
OpenAI Group PBC today disclosed that one of its unreleased large language models may pose a significant cybersecurity risk. The algorithm, which is known as Astra, was first detailed last week. OpenA
OpenAI Group PBC today disclosed that one of its unreleased large language models may pose a significant cybersecurity risk. The algorithm, which is known as Astra, was first detailed last week. OpenAI revealed in a Sunday blog post that the LLM had solved 10 long-running math problems. The company published the proofs and revealed that […] The post OpenAI reveals upcoming Astra model may possess ‘critical’ hacking capabilities appeared first on SiliconANGLE.
Related
- OpenAI details GPT-Red, an AI that attacks its own models to find flaws
- Cisco report finds no closed frontier AI model is safe from multi-turn attacks
- Florida AG sues OpenAI and Sam Altman over claims the technology is dangerous and exploits its users
Source: SiliconANGLE | 2026-08-08