OpenAI has killed off the planned release of GPT-6.1 Astra after the model got better at doggedly pursuing tasks but worse at knowing when it should stop. The decision means the model won't get its planned October release after falling short of OpenAI's safety and alignment requirements. OpenAI confirmed the decision to The Register, saying its research and safety bosses ultimately decided this particular Astra was better left on the bench.
OpenAI benches GPT-6.1 Astra for overstepping the mark
About this summary. This is a short, independently written summary of an article first published by The Register. Cyber Security News did not report or verify the underlying story. Read the original: https://www.theregister.com/ai-and-ml/2026/09/29/openai-benches-gpt-61-astra-for-overstepping-the-mark/5299743
Source attribution: headline and facts are from The Register (theregister.com). Summary method: excerpt of the source description. See our source attribution policy.
Related coverage
NetScaler zero-day exploitation escalates into mass attacks (CVE-2026-88771)
The hacking of internet-exposed, vulnerable Citrix NetScaler ADC and Gateway deployments has escalated. What started as stealthy targeting via zero-day exploits has now…
CVE-2026-82804: Apache DolphinScheduler: Command Injection in the Alert Script Plugin
Posted by Wenjun Ruan on Sep 29 Severity: low Affected versions: - Apache DolphinScheduler before 3.4.3 Description: The scriptPath parameter is incorporated into a…
Scans for Wordfence Protected Websites, (Tue, Sep 29th)
Starting yesterday, our sensors picked up a small number of scans for "wordfence-waf.php". This particular script is used by Wordfence, a solution to protect WordPress…
Adaptive application security for the AI era: how Cloudflare connects code, traffic, and intelligence to stop attacks
In July, AI agents testing new cybersecurity models compromised parts of OpenAI’s infrastructure and Hugging Face’s production environment. We've all just witnessed one…
We tested our own WAF with frontier AI models. Here’s what we found
“Is your WAF ready for frontier AI models?” We keep hearing this question from our customers, so we decided to find out. When it comes to exploiting applications, what…
Update your iPhone, iPad, or Mac: Flaw could run attackers’ code
Apple has released updates for iPhones, iPads, and Macs to fix a flaw that could let an attacker run code when a device processes a malicious file. Apple says it may…