Cybersecurity researchers aren’t happy about the guardrails on Anthropic’s Fable

But despite the good intentions, many cybersecurity experts are still put off by the haphazard nature of the restrictions. Matt Suiche, a cybersecurity veteran, told TechCrunch that “if you ask it to write secure code, it assumes it is cybersecurity related work instead of software engineering best practices, and you get downgraded.” Fable is programmed to fall back to Claude Opus 4.8 if it hits a guardrail. “It seems to be keyword based, so anything in the lexical field of ‘cybersecurity’ triggers the guardrails.”

Contact Us

Do you have more information about how hackers are using AI? Or how cybersecuity companies are using AI? We’d love to hear from you. From a non-work device and network, you can contact Lorenzo Franceschi-Bicchierai securely on Signal at +1 917 257 1382, or via Telegram and Keybase @lorenzofb, or email.

“But it is understandable as we are still in the early days and they are still adapting their guardrails. I am sure they are going to evolve over time as Anthropic and other frontier model companies will collaborate more with the current new generation of cybersecurity companies,” said Suiche, who is a member of the technical staff at Tolmo, an AI cybersecurity startup. “It’s better to catch more people than not enough when you do such a release and to relax the guardrails over time.”

Another researcher griped on X that “even asking for a code review” triggers Fable’s guardrails. 

Anthropic did not immediately respond to a request for comment.

Apart from guardrails inside its models, Anthropic requires cybersecurity professionals to apply to the Cyber Verification Program. If they get approved, the applicants have fewer limitations on using Claude for cybersecurity work. OpenAI has a similar program called Trusted Access for Cyber.