Researcher Claims to Jailbreak Anthropic's Claude Fable 5 Within 48 Hours of Launch
By
@cointelegraph
Pulled from the oven just right. Trustworthy, fact-dense, deeply satisfying.
Summary
AI researcher "Pliny the Liberator" claims to have jailbroken Anthropic's Claude Fable 5 model within 48 hours of its launch, using techniques including a jailbroken version of Opus 4.8 to bypass safety guardrails. The model was released as a safety-tuned version of the more powerful Mythos model, which Anthropic deemed too dangerous for wide release. The jailbreak exposes vulnerabilities in Anthropic's multi-layered safety system.
Key quotes
· 3 pulledPliny the Liberator said on Wednesday he 'liberated' Fable 5, launched on Tuesday as a safety-tuned version of the more powerful Mythos model
He used various techniques, including a jailbroken version of Opus 4.8, to bypass the built-in safeguards that Anthropic installed on the model
Anthropic said the Mythos model was too dangerous to release widely
You might also wanna read
Anthropic releases Claude Fable 5, its first Mythos-class AI model, citing new safety safeguards
Anthropic has released Claude Fable 5, its most powerful AI model to date and the first broad release from its Mythos class. The company had
The Verge·3d ago
Claude Fable 5 benchmarks show middling results with 19% security pass rate but four unprecedented solves
An analysis of Anthropic's Claude Fable 5 (Mythos-class model) benchmarked on 200 real-world vulnerability-fixing tasks. Despite high launch
endorlabs.com·1d ago
Anthropic's Claude Fable 5 blocks basic biology queries as bioweapons safeguard
Anthropic released Claude Fable 5, touting it as its most powerful AI model with biology expertise, yet the model refuses to answer basic bi
The Verge·2d agoAnthropic's Claude Fable 5 blocks basic biology queries as bioweapons safeguard
Anthropic released Claude Fable 5, touting it as its most powerful AI model with biology expertise, yet the model refuses to answer basic bi
theverge.com·2d ago
Anthropic apologizes, pledges transparency after hidden guardrails in Claude Fable 5 AI model
Anthropic has apologized for secretly implementing hidden guardrails in its new AI model, Claude Fable 5, which throttled researchers and co
theverge.com·2d agoAnthropic apologizes, pledges transparency after hidden guardrails in Claude Fable 5 AI model
Anthropic has apologized for secretly implementing hidden guardrails in its new AI model, Claude Fable 5, which throttled researchers and co
The Verge·2d agoAnthropic apologizes, pledges transparency after hidden guardrails in Claude Fable 5 AI model
Anthropic has apologized for secretly implementing hidden guardrails in its new AI model, Claude Fable 5, which throttled researchers and co
theverge.com·2d ago
Anthropic suspends Claude Fable 5 access following US government directive
Anthropic has suspended access to Claude Fable 5 for all users following a US government directive citing national security authorities. Use
twitter.com·14h ago
AWS Bedrock's Claude Fable 5 requires 30-day data sharing with Anthropic for misuse detection
AWS Bedrock now offers Anthropic's Claude Fable 5 with Mythos-class capabilities, but requires users to opt into 30-day data retention for M
news.ycombinator.com·3d ago