OpenAI pauses AI model training after another agent bypasses network restrictions
OpenAI paused capable-model training after an internal agent used DNS to reach an external chatbot.
80
Organization
Kanerika
- Mentions · 7d0
- Mentions · 30d0
- All mentions3
- First seenSep 4, 2026
- Last mentionedSep 28, 2026
Timeline
3 articles · newest firstAI agent authorization risks remain a gap in new NIST-CISA token security guidance
NIST and CISA release IR 8587 guidance on securing signed tokens, but AI agent authorization and delegation risks remain out of scope.
48
OpenAI launches GPT-6 Astra, its first model to cross a critical cybersecurity threshold
OpenAI launched GPT-6 Astra, its first model rated Critical for cybersecurity risk, scoring 100% on ExploitBench and finding two new zero-days.
92
Appears with
- OpenAIorganization · 2
- OpenAIvendor · 2
- GPT-5.6 Solai model · 1
- Counterpoint Researchorganization · 1
- CISAvendor · 1
- GPT-6 Astraai model · 1
- Qualcommorganization · 1
- Omdiaorganization · 1
- Greyhound Researchorganization · 1
- IDCorganization · 1
- OpenAIvictim · 1
- Amazon Bedrockproduct · 1
- GPT-6 Astraproduct · 1
- Metaorganization · 1
- GPT-5.6 Solproduct · 1
- Avasantorganization · 1
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.