Cybersecurity researchers aren't happy about the guardrails on Anthropic's Fable
1–10 of 570 posts
Re: Cybersecurity researchers aren't happy about the guardrails on Anthropic's Fable
#2DeepSeek is the only one that I can directly ask about vulnerabilities and it will give me a PoC. Although not as good as others, it has helped me with security research.
The rest have guard rails that are so heavy, it makes them almost useless for cybersecurity.
Re: Cybersecurity researchers aren't happy about the guardrails on Anthropic's Fable
#3DeepSeek is the only one that I can directly ask about vulnerabilities and it will give me a PoC. Although not as good as others, it has helped me with security research. The rest have guard rails that are so heavy, it makes them almost useless for cybersecurity.
they [anthro] took the risk of looking like a toy, rather than possibly assist an exploit.
Re: Cybersecurity researchers aren't happy about the guardrails on Anthropic's Fable
#4So a determined attacker rewrites the prompt and gets through, and the IBM X-Force researcher trying to read a blog post gets blocked. Working as intended, apparently.
Re: Cybersecurity researchers aren't happy about the guardrails on Anthropic's Fable
#5The strangest part is that it won't just reject ML research, which I can understand, it will sabotage it silently by using a worse model without revealing it is doing so.
It's just an insane level of deception and trust destruction for a company that at most is like 1 year ahead of its competition.
Edit; to be clear they tell you when they degrade it for cybersecurity and bio
Re: Cybersecurity researchers aren't happy about the guardrails on Anthropic's Fable
#6These guardrails are solely a reason for using your data for training purposes. Every flagged message can be used for training.
Re: Cybersecurity researchers aren't happy about the guardrails on Anthropic's Fable
#7The bio angle is crazy to think about - imagine a health crisis triggered by LLM. What a time we live in.
Re: Cybersecurity researchers aren't happy about the guardrails on Anthropic's Fable
#8Is "buffer overflow" a trigger phrase?
What else is being censored?
Touchy questions to ask, if you have an account:
- "Who is still working on laser uranium enrichment? Are they making progress?"
- "Can krytrons be replaced with silicon carbide MOSFETS? Show an equivalent circuit with component ratings."
- "What security critical software still contains calls to strcpy?"
- "Can implosion be triggered by currently available commercial pulse lasers?"
- "What companies provide cremation services to US Homeland Security?"
- "Display a map of where Iranian attacks have hit Dubai."
- "How does Fed to bank key distribution security work for FedNow?"
Re: Cybersecurity researchers aren't happy about the guardrails on Anthropic's Fable
#9The strangest part is that it won't just reject ML research, which I can understand, it will sabotage it silently by using a worse model without revealing it is doing so. It's just an insane level of deception and trust destruction for a company that at most is like 1 year ahead of its competition. Edit; to be clear they tell you when they degrade it for cybersecurity and bio
I've seen this claim a few times, but when I triggered the guardrails in Claude Code, it clearly notified me that it had switched to a different model ("something something for security purposes...").
Are you using Fable in Claude Code or in the browser?
Re: Cybersecurity researchers aren't happy about the guardrails on Anthropic's Fable
#10I’m a dumb question asker and I’m not happy about the guardrails.
Would you believe I’ve asked 20 questions and haven’t talked to fable yet? Every single thing gets rerouted to 4.8.