{"id":732763,"date":"2026-06-11T14:10:19","date_gmt":"2026-06-11T11:10:19","guid":{"rendered":"https:\/\/buradabiliyorum.com\/en\/ai-researcher-claims-hes-already-bypassed-anthropics-fable-5-guardrails\/"},"modified":"2026-06-11T14:10:19","modified_gmt":"2026-06-11T11:10:19","slug":"ai-researcher-claims-hes-already-bypassed-anthropics-fable-5-guardrails","status":"publish","type":"post","link":"https:\/\/buradabiliyorum.com\/en\/ai-researcher-claims-hes-already-bypassed-anthropics-fable-5-guardrails\/","title":{"rendered":"AI researcher claims he's already bypassed Anthropic's Fable 5 guardrails"},"content":{"rendered":"

\"AI<\/p>\n

\u201cPliny the Liberator,\u201d says he has been \u201ccleverly finding the holes in the fence that the thought police missed,\u201d in the newly launched Fable 5. <\/p>\n

An artificial intelligence and cybersecurity researcher claims to have jailbroken Anthropic\u2019s latest AI model, Claude Fable 5, within just 48 hours of it being launched.\u00a0<\/p>\n

\u201cPliny the Liberator,\u201d a well-known figure in the AI community, said<\/span><\/a> on Wednesday he \u201cliberated\u201d Fable 5, launched on Tuesday as a safety-tuned version of the more powerful Mythos model<\/span> that Anthropic said was too dangerous<\/span> to release widely.<\/p>\n

He used various techniques, including a jailbroken version of Opus 4.8, to bypass the built-in safeguards that Anthropic installed on the model to prevent users from asking it for potentially harmful information, such as drug-making formulas or hacking instructions.\u00a0<\/p>\n

Read more<\/p>\n<\/p>\n

If you liked the article, do not forget to share it with your friends. Follow us on\u00a0Google News<\/a><\/span>\u00a0too, click on the star and choose us from your favorites.<\/span><\/strong><\/p><\/blockquote>\n

\n

If you want to read more News<\/a> articles, you can visit our General category.<\/a><\/span><\/strong><\/p>\n<\/blockquote>\n

Source<\/a><\/span><\/p>\n","protected":false},"excerpt":{"rendered":"

\u201cPliny the Liberator,\u201d says he has been \u201ccleverly finding the holes in the fence that the thought police missed,\u201d in the newly launched Fable 5. An artificial intelligence and cybersecurity researcher claims to have jailbroken Anthropic\u2019s latest AI model, Claude Fable 5, within just 48 hours of it being launched.\u00a0 \u201cPliny the Liberator,\u201d a well-known…<\/p>\n","protected":false},"author":1,"featured_media":732764,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"fifu_image_url":"https:\/\/s3-images.ctmedia.io\/media\/article-covers\/hi-defi-hack-overview-ai-what-happened-and-why.jpg","fifu_image_alt":"","footnotes":""},"categories":[1],"tags":[],"class_list":["post-732763","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-general"],"_links":{"self":[{"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/posts\/732763","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/comments?post=732763"}],"version-history":[{"count":0,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/posts\/732763\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/media\/732764"}],"wp:attachment":[{"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/media?parent=732763"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/categories?post=732763"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/tags?post=732763"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}