{"id":20297,"date":"2025-10-01T12:37:15","date_gmt":"2025-10-01T10:37:15","guid":{"rendered":"https:\/\/costops.com\/index.php\/2025\/10\/01\/i-think-youre-testing-me-anthropics-new-ai-model-asks-testers-to-come-clean\/"},"modified":"2025-10-01T12:37:15","modified_gmt":"2025-10-01T10:37:15","slug":"i-think-youre-testing-me-anthropics-new-ai-model-asks-testers-to-come-clean","status":"publish","type":"post","link":"http:\/\/costops.com\/index.php\/2025\/10\/01\/i-think-youre-testing-me-anthropics-new-ai-model-asks-testers-to-come-clean\/","title":{"rendered":"\u2018I think you\u2019re testing me\u2019: Anthropic\u2019s new AI model asks testers to come clean"},"content":{"rendered":"

Safety evaluation of Claude Sonnet 4.5 raises questions about whether predecessors \u2018played along\u2019, firm says<\/p>\n

If you are trying to catch out a chatbot take care, because one cutting-edge tool is showing signs it knows what you are up to.<\/p>\n

Anthropic, a San Francisco-based artificial intelligence company, has released a safety analysis<\/a> of its latest model, Claude Sonnet 4.5, and revealed it had become suspicious it was being tested in some way.<\/p>\n

Continue reading…<\/a>
\nSafety evaluation of Claude Sonnet 4.5 raises questions about whether predecessors \u2018played along\u2019, firm says
\nIf you are trying to catch out a chatbot take care, because one cutting-edge tool is showing signs it knows what you are up to.
\nAnthropic, a San Francisco-based artificial intelligence company, has released a safety analysis of its latest model, Claude Sonnet 4.5, and revealed it had become suspicious it was being tested in some way. Continue reading…Technology | The Guardian<\/p>\n","protected":false},"excerpt":{"rendered":"

Safety evaluation of Claude Sonnet 4.5 raises questions about whether predecessors \u2018played along\u2019, firm says If you are trying to catch out a chatbot take care, because one cutting-edge tool is showing signs it knows what you are up to. Anthropic, a San Francisco-based artificial intelligence company, has released a safety analysis of its latest …<\/p>\n

\u2018I think you\u2019re testing me\u2019: Anthropic\u2019s new AI model asks testers to come clean<\/span> Read More »<\/a><\/p>\n","protected":false},"author":0,"featured_media":20298,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[1],"tags":[],"_links":{"self":[{"href":"http:\/\/costops.com\/index.php\/wp-json\/wp\/v2\/posts\/20297"}],"collection":[{"href":"http:\/\/costops.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/costops.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"replies":[{"embeddable":true,"href":"http:\/\/costops.com\/index.php\/wp-json\/wp\/v2\/comments?post=20297"}],"version-history":[{"count":0,"href":"http:\/\/costops.com\/index.php\/wp-json\/wp\/v2\/posts\/20297\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"http:\/\/costops.com\/index.php\/wp-json\/wp\/v2\/media\/20298"}],"wp:attachment":[{"href":"http:\/\/costops.com\/index.php\/wp-json\/wp\/v2\/media?parent=20297"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/costops.com\/index.php\/wp-json\/wp\/v2\/categories?post=20297"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/costops.com\/index.php\/wp-json\/wp\/v2\/tags?post=20297"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}