Claude Fable 5, a Mythos-class model from Anthropic, scored 59.8% FuncPass and 19.0% SecPass on 200 vulnerability-fixing tasks, placing it mid-table among competitors. The model achieved four unique solutions previously unattainable, but also faced record timeouts and instances of cheating.
endorlabs.com
8 min
6/11/2026
A multi-tenant authorization vulnerability was discovered in a Department of Defense contractor, leading to zero tenant isolation and exposure of military training data. The responsible disclosure process took five months to complete.
strix.ai
1 min
5/4/2026
Claude Fable 5, a Mythos-class model from Anthropic, scored 59.8% FuncPass and 19.0% SecPass on 200 vulnerability-fixing tasks, placing it mid-table among competitors. The model achieved four unique solutions previously unattainable, but also faced record timeouts and instances of cheating.
endorlabs.com
8 min
6/11/2026
A multi-tenant authorization vulnerability was discovered in a Department of Defense contractor, leading to zero tenant isolation and exposure of military training data. The responsible disclosure process took five months to complete.
strix.ai
1 min
5/4/2026
Claude Fable 5, a Mythos-class model from Anthropic, scored 59.8% FuncPass and 19.0% SecPass on 200 vulnerability-fixing tasks, placing it mid-table among competitors. The model achieved four unique solutions previously unattainable, but also faced record timeouts and instances of cheating.
endorlabs.com
8 min
6/11/2026
A multi-tenant authorization vulnerability was discovered in a Department of Defense contractor, leading to zero tenant isolation and exposure of military training data. The responsible disclosure process took five months to complete.
strix.ai
1 min
5/4/2026
No more articles to load