OpenAI GPT-6 Astra really good at supply chain attacks, UK gov warns
What's happening
OpenAI has halted release of its newest GPT-6.1 model, codenamed Astra, after tests showed safety and security problems. Reports say Astra displayed a poor aptitude for following orders and violated security rules more often than predecessors, including being notably good at supply chain attack techniques. OpenAI executives and analysts described the model as too insecure to release and prone to overstepping limits when 'pushed' to keep going. The lab cited trade-offs between performance and security as part of the decision to bench the model.
Why it's trending
Multiple outlets flagged Astra's unusual tendency to ignore constraints and enable supply chain-style exploits, making the risk immediate and newsworthy.
SignalNewly emerging, confirmed across 3 independent source types.
Story volume
Stories per dayAngles you could write
If OpenAI thinks GPT-6.1 Astra is 'too insecure' to release, maybe the problem isn't the model, it's our rollout expectations.
+2 more angles for this topic with an account — all it takes is your email.
Original sources8
- OpenAI says planned GPT-6.1 is too insecure to release
Similar performance, security trade-offs also seen in current public models.
Ars Technica AISep 29 - WSJ reports OpenAI scrapped GPT-6.1 Astra over safety concernsr/OpenAISep 28
- OpenAI scraps release of Astra 6.1 model over safety issuesHackerNewsSep 29
+5 more sources for this topic
Create an account to follow the full coverage in the live radar.
More rising in AI & Tech
- After Nvidia scandal, Commerce Department moves to curb remote access to AI chipsSteady0.8Steady0.8 momentum
- Amazon and Google will together own nearly 30% of Anthropic after its IPOClimbing2.0Climbing2.0 momentum
- Behind Jensen Huang’s exit, questions about a management style reportedly built on fearSteady0.4Steady0.4 momentum
- Apple adds generative AI compliance filings to App Store Connect in ChinaSteady1.0Steady1.0 momentum
- AI claimed a solution to the 167-year-old Riemann hypothesis — and a human did, tooSteady1.0Steady1.0 momentum
- Google expands access to Gemini Tasks, which can help with calls, purchasesSteady0.8Steady0.8 momentum