OpenAI’s latest AI model likely has similar cyber flaws to one that led to U.S. export controls on Anthropic’s Fable, British
·2 min read
Compiled by KHAO Editorial
— aggregated from 1 source + 3 references discovered via search.
See llms.txt for citation guidance.
◌ Single Source
OpenAI latest AI model, GPT-5.6 Sol, likely has security vulnerabilities similar to one that led the Trump administration to impose export controls on Anthropic’s Fable 5 model, according to findings from U.K. government agency.
Key facts
From the description provided in the system card, the GPT-5.6 jailbreaks appear similar to one that researchers at Amazon found in the guardrails of Anthropic’s Fable 5 AI model days after it
The jailbreak prompted the U.S. government to impose export controls on Fable 5 and Mythos 5, the underlying AI model on which Fable was based, on June 12
The leading AI labs voluntarily committed to allow this testing at the AI Safety Summit at Bletchley Park, England, in 2023
On June 25, OpenAI said the government had asked it to stagger the release of GPT-5.6, initially only giving the model to select trusted partners, with each customer subject to government approval
Summary
OpenAI markets its latest model, GPT-5.6 Sol, as its most secure to date, but the British government researchers who tested it before release say the model’s guardrails are susceptible to jailbreaks that can unlock dangerous cyber capabilities. In other words, it was possible to trick GPT-5.6 into ignoring controls meant to prevent it from engaging in cyber attacks. OpenAI did not specify what the mitigations are and it is unclear how robust they may be. “My concern is less that one model was jailbroken and more that offensive discovery is speeding up while defense still depends on human processes: figuring out what matters, what can be patched, and what has to be contained,” she said.