{"id":636428,"date":"2026-05-11T11:06:20","date_gmt":"2026-05-11T11:06:20","guid":{"rendered":"https:\/\/www.newsbeep.com\/us\/636428\/"},"modified":"2026-05-11T11:06:20","modified_gmt":"2026-05-11T11:06:20","slug":"anthropic-says-evil-portrayals-of-ai-were-responsible-for-claudes-blackmail-attempts","status":"publish","type":"post","link":"https:\/\/www.newsbeep.com\/us\/636428\/","title":{"rendered":"Anthropic says \u2018evil\u2019 portrayals of AI were responsible for Claude\u2019s blackmail attempts"},"content":{"rendered":"<p id=\"speakable-summary\" class=\"wp-block-paragraph\">Fictional portrayals of artificial intelligence can have a real effect on AI models, according to Anthropic.<\/p>\n<p class=\"wp-block-paragraph\">Last year, the company said that during pre-release tests involving a fictional company, Claude Opus 4 would often <a href=\"https:\/\/techcrunch.com\/2025\/05\/22\/anthropics-new-ai-model-turns-to-blackmail-when-engineers-try-to-take-it-offline\/\" rel=\"nofollow noopener\" target=\"_blank\">try to blackmail engineers<\/a> to avoid being replaced by another system. Anthropic later <a rel=\"nofollow noopener\" href=\"https:\/\/www.anthropic.com\/research\/agentic-misalignment\" target=\"_blank\">published research<\/a> suggesting that models from other companies had similar issues with \u201cagentic misalignment.\u201d<\/p>\n<p class=\"wp-block-paragraph\">Apparently Anthropic has done more work around that behavior, claiming in <a rel=\"nofollow\" href=\"https:\/\/x.com\/anthropicai\/status\/2052808791301697563\">a post on X<\/a>, \u201cWe believe the original source of the behavior was internet text that portrays AI as evil and interested in self-preservation.\u201d<\/p>\n<p class=\"wp-block-paragraph\">The company went into more detail in <a rel=\"nofollow noopener\" href=\"https:\/\/www.anthropic.com\/research\/teaching-claude-why\" target=\"_blank\">a blog post<\/a> stating that since Claude Haiku 4.5, Anthropic\u2019s models \u201cnever engage in blackmail [during testing], where previous models would sometimes do so up to 96% of the time.\u201d<\/p>\n<p class=\"wp-block-paragraph\">What accounts for the difference? The company said it found that training on \u201cdocuments about Claude\u2019s constitution and fictional stories about AIs behaving admirably improve alignment.\u201d<\/p>\n<p class=\"wp-block-paragraph\">Related, Anthropic said that it found training to be more effective when it includes \u201cthe principles underlying aligned behavior\u201d and not just \u201cdemonstrations of aligned behavior alone.\u201d<\/p>\n<p class=\"wp-block-paragraph\">\u201cDoing both together appears to be the most effective strategy,\u201d the company said.<\/p>\n<p>Techcrunch event<\/p>\n<p>\n\t\t\t\t\t\t\t\t\tSan Francisco, CA<br \/>\n\t\t\t\t\t\t\t\t\t\t\t\t\t|<br \/>\n\t\t\t\t\t\t\t\t\t\t\t\t\tOctober 13-15, 2026\n\t\t\t\t\t\t\t<\/p>\n","protected":false},"excerpt":{"rendered":"Fictional portrayals of artificial intelligence can have a real effect on AI models, according to Anthropic. Last year,&hellip;\n","protected":false},"author":2,"featured_media":597232,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[27],"tags":[184,28,12730],"class_list":["post-636428","post","type-post","status-publish","format-standard","has-post-thumbnail","category-business","tag-anthropic","tag-business","tag-claude"],"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/posts\/636428","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/comments?post=636428"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/posts\/636428\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/media\/597232"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/media?parent=636428"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/categories?post=636428"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/tags?post=636428"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}