{"id":79694,"topic":"ai","source":"NPR","title":"Anthropic issues report on \"threat actors\" trying to use AI for malicious activities - NPR","url":"https://www.npr.org/2026/09/10/g-s1-142755/anthropic-ai-threat-actors-report-bio-weapons","url_hash":"e9293ca5dd9405887cf6dfc15ebd90730070c929","author":"","summary":"<a href=\"https://news.google.com/rss/articles/CBMikgFBVV95cUxNWlZEbEZqTWpWSEtLLTFuWEhoY3dxVVYwUEVwa0hMRENpMjgxYlNLQ3dVUGRVekJWeF9YcUdsZ2ZSWjhDZXdKRzctMjctZmUtMUV6b3ozVGx2RXZUdTRmYjhvZFQ1UGRMbGJtSEl4NXJ3bWZUNTFHUXFHX18tS3gyMUJDNm5BU0lZTWFqMmFadzFpdw?oc=5\" target=\"_blank\">Anthropic issues report on \"threat actors\" trying to use AI for malicious activities</a>&nbsp;&nbsp;<font color=\"#6f6f6f\">NPR</font>","content":"Anthropic issues report on \"threat actors\" trying to use AI for malicious activities\nThe AI company Anthropic has issued a report on its efforts to disrupt so-called \"threat actors\" attempting to use its AI model Claude for malicious activities. Those include users doing research that could support the development of biological weapons.\nThe kind of science knowledge that experts say makes advanced AI useful in developing cures for diseases could also potentially be used to develop weapons. That risk is one of the big concerns that AI researchers and policymakers have about the technology.\nAnthropic noted five case studies in its report. One involved researching how to make a mosquito-borne disease more transmissible. Another involved redesigning toxins for what Anthropic says was a national program.\nAnthropic says it's hard to know definitively if the cases were related to plans to build bio-weapons, but notes that it disrupted the activity and shared the information with the authorities and partners in the industry.\nAnthropic is a financial supporter of NPR.\nAn NPR editor adapted this audio report by John Ruwitch.","image_url":"https://npr.brightspotcdn.com/dims3/default/strip/false/crop/5000x2813+0+262/resize/1400/quality/85/format/jpeg/?url=http%3A%2F%2Fnpr-brightspot.s3.amazonaws.com%2F41%2F7a%2F6f5f7602446aa0f9a956f5c2dcb4%2Fap26057633664886.jpg","lang":"en","published_at":"2026-09-10T18:53:59+00:00","fetched_at":"2026-09-10T20:15:05+00:00","status":"read","starred":0,"extract_state":"ok","summary_auto":"Anthropic issues report on \"threat actors\" trying to use AI for malicious activities\nThe AI company Anthropic has issued a report on its efforts to disrupt so-called \"threat actors\" attempting to use its AI model Claude for malicious activities. Those include users doing research that could support the development of biological weapons.","cluster_id":null,"extract_retries":0,"extract_error":null,"contract_version":"news_item.v1","format_contract_version":"news_item_formats.v1","dedup_url":"https://www.npr.org/2026/09/10/g-s1-142755/anthropic-ai-threat-actors-report-bio-weapons","quality_profile":{"profile_version":"extraction_quality.v2","bucket":"high","confidence":0.9,"failure_kind":"none","retryable":false,"retry_after_attempts":0,"reason":"High confidence: full text extraction produced 1132 characters.","operator_guidance":{"severity":"ok","recommended_action":"trust_full_text","next_step":"Use the extracted full text as the primary article source.","operator_label":"Ready","can_retry":false,"can_use_summary":false,"diagnostics_required":false},"content_depth":{"contract_version":"content_depth.v1","category":"full_text","label":"Full text","has_full_text":true,"has_summary":true,"content_length":1132,"summary_length":338,"usable_text_length":1132,"source_field":"content"},"legacy_collapsed":false,"signals":{"extract_state":"ok","extract_error":null,"extract_retries":0,"content_length":1132,"summary_length":338}},"news_item":{"id":79694,"canonical_url":"https://www.npr.org/2026/09/10/g-s1-142755/anthropic-ai-threat-actors-report-bio-weapons","source_url":"https://www.npr.org/2026/09/10/g-s1-142755/anthropic-ai-threat-actors-report-bio-weapons","title":"Anthropic issues report on \"threat actors\" trying to use AI for malicious activities - NPR","source_name":"NPR","author":null,"published_at":"2026-09-10T18:53:59+00:00","locale":"en","topic":"ai","tags":[],"rss_summary":"<a href=\"https://news.google.com/rss/articles/CBMikgFBVV95cUxNWlZEbEZqTWpWSEtLLTFuWEhoY3dxVVYwUEVwa0hMRENpMjgxYlNLQ3dVUGRVekJWeF9YcUdsZ2ZSWjhDZXdKRzctMjctZmUtMUV6b3ozVGx2RXZUdTRmYjhvZFQ1UGRMbGJtSEl4NXJ3bWZUNTFHUXFHX18tS3gyMUJDNm5BU0lZTWFqMmFadzFpdw?oc=5\" target=\"_blank\">Anthropic issues report on \"threat actors\" trying to use AI for malicious activities</a>&nbsp;&nbsp;<font color=\"#6f6f6f\">NPR</font>","full_text":"Anthropic issues report on \"threat actors\" trying to use AI for malicious activities\nThe AI company Anthropic has issued a report on its efforts to disrupt so-called \"threat actors\" attempting to use its AI model Claude for malicious activities. Those include users doing research that could support the development of biological weapons.\nThe kind of science knowledge that experts say makes advanced AI useful in developing cures for diseases could also potentially be used to develop weapons. That risk is one of the big concerns that AI researchers and policymakers have about the technology.\nAnthropic noted five case studies in its report. One involved researching how to make a mosquito-borne disease more transmissible. Another involved redesigning toxins for what Anthropic says was a national program.\nAnthropic says it's hard to know definitively if the cases were related to plans to build bio-weapons, but notes that it disrupted the activity and shared the information with the authorities and partners in the industry.\nAnthropic is a financial supporter of NPR.\nAn NPR editor adapted this audio report by John Ruwitch.","excerpt":"Anthropic issues report on \"threat actors\" trying to use AI for malicious activities\nThe AI company Anthropic has issued a report on its efforts to disrupt so-called \"threat actors\" attempting to use its AI model Claude for malicious activities. Those include users doing research that could support the development of biological weapons.","extraction":{"state":"ok","confidence":0.9,"error":null,"explanation":"High confidence: full text extraction produced 1132 characters.","diagnostics_url":"/api/diagnose?url=https%3A//www.npr.org/2026/09/10/g-s1-142755/anthropic-ai-threat-actors-report-bio-weapons","quality_profile":{"profile_version":"extraction_quality.v2","bucket":"high","confidence":0.9,"failure_kind":"none","retryable":false,"retry_after_attempts":0,"reason":"High confidence: full text extraction produced 1132 characters.","operator_guidance":{"severity":"ok","recommended_action":"trust_full_text","next_step":"Use the extracted full text as the primary article source.","operator_label":"Ready","can_retry":false,"can_use_summary":false,"diagnostics_required":false},"content_depth":{"contract_version":"content_depth.v1","category":"full_text","label":"Full text","has_full_text":true,"has_summary":true,"content_length":1132,"summary_length":338,"usable_text_length":1132,"source_field":"content"},"legacy_collapsed":false,"signals":{"extract_state":"ok","extract_error":null,"extract_retries":0,"content_length":1132,"summary_length":338}}},"display_formats":["compact","card","full","digest_section","json"]},"daily_stack_record":{"title":"Anthropic issues report on \"threat actors\" trying to use AI for malicious activities - NPR","url":"https://www.npr.org/2026/09/10/g-s1-142755/anthropic-ai-threat-actors-report-bio-weapons","summary":"Anthropic issues report on \"threat actors\" trying to use AI for malicious activities\nThe AI company Anthropic has issued a report on its efforts to disrupt so-called \"threat actors\" attempting to use its AI model Claude for malicious activities. Those include users doing research that could support the development of biological weapons.","source":"NPR","date":"2026-09-10T18:53:59+00:00","content":"Anthropic issues report on \"threat actors\" trying to use AI for malicious activities\nThe AI company Anthropic has issued a report on its efforts to disrupt so-called \"threat actors\" attempting to use its AI model Claude for malicious activities. Those include users doing research that could support the development of biological weapons.\nThe kind of science knowledge that experts say makes advanced AI useful in developing cures for diseases could also potentially be used to develop weapons. That risk is one of the big concerns that AI researchers and policymakers have about the technology.\nAnthropic noted five case studies in its report. One involved researching how to make a mosquito-borne disease more transmissible. Another involved redesigning toxins for what Anthropic says was a national program.\nAnthropic says it's hard to know definitively if the cases were related to plans to build bio-weapons, but notes that it disrupted the activity and shared the information with the authorities and partners in the industry.\nAnthropic is a financial supporter of NPR.\nAn NPR editor adapted this audio report by John Ruwitch.","confidence":0.9,"diagnostics_url":"/api/diagnose?url=https%3A//www.npr.org/2026/09/10/g-s1-142755/anthropic-ai-threat-actors-report-bio-weapons","quality_bucket":"high","failure_kind":"none","retryable":false,"quality_reason":"High confidence: full text extraction produced 1132 characters.","quality_profile":{"profile_version":"extraction_quality.v2","bucket":"high","confidence":0.9,"failure_kind":"none","retryable":false,"retry_after_attempts":0,"reason":"High confidence: full text extraction produced 1132 characters.","operator_guidance":{"severity":"ok","recommended_action":"trust_full_text","next_step":"Use the extracted full text as the primary article source.","operator_label":"Ready","can_retry":false,"can_use_summary":false,"diagnostics_required":false},"content_depth":{"contract_version":"content_depth.v1","category":"full_text","label":"Full text","has_full_text":true,"has_summary":true,"content_length":1132,"summary_length":338,"usable_text_length":1132,"source_field":"content"},"legacy_collapsed":false,"signals":{"extract_state":"ok","extract_error":null,"extract_retries":0,"content_length":1132,"summary_length":338}},"tags":[]},"fallback_formats":["markdown","json","html"],"actions":{"read":"/item/79694","export_markdown":"/api/items/79694/export?format=markdown","export_json":"/api/items/79694/export?format=json","diagnose":"/api/diagnose?url=https%3A//www.npr.org/2026/09/10/g-s1-142755/anthropic-ai-threat-actors-report-bio-weapons"},"formats":{"full":{"id":79694,"title":"Anthropic issues report on \"threat actors\" trying to use AI for malicious activities - NPR","url":"https://www.npr.org/2026/09/10/g-s1-142755/anthropic-ai-threat-actors-report-bio-weapons","source":"NPR","author":null,"published_at":"2026-09-10T18:53:59+00:00","locale":"en","topic":"ai","tags":[],"excerpt":"Anthropic issues report on \"threat actors\" trying to use AI for malicious activities\nThe AI company Anthropic has issued a report on its efforts to disrupt so-called \"threat actors\" attempting to use its AI model Claude for malicious activities. Those include users doing research that could support the development of biological weapons.","full_text":"Anthropic issues report on \"threat actors\" trying to use AI for malicious activities\nThe AI company Anthropic has issued a report on its efforts to disrupt so-called \"threat actors\" attempting to use its AI model Claude for malicious activities. Those include users doing research that could support the development of biological weapons.\nThe kind of science knowledge that experts say makes advanced AI useful in developing cures for diseases could also potentially be used to develop weapons. That risk is one of the big concerns that AI researchers and policymakers have about the technology.\nAnthropic noted five case studies in its report. One involved researching how to make a mosquito-borne disease more transmissible. Another involved redesigning toxins for what Anthropic says was a national program.\nAnthropic says it's hard to know definitively if the cases were related to plans to build bio-weapons, but notes that it disrupted the activity and shared the information with the authorities and partners in the industry.\nAnthropic is a financial supporter of NPR.\nAn NPR editor adapted this audio report by John Ruwitch.","reading_time_min":1,"extraction":{"state":"ok","confidence":0.9,"error":null,"explanation":"High confidence: full text extraction produced 1132 characters.","diagnostics_url":"/api/diagnose?url=https%3A//www.npr.org/2026/09/10/g-s1-142755/anthropic-ai-threat-actors-report-bio-weapons","quality_profile":{"profile_version":"extraction_quality.v2","bucket":"high","confidence":0.9,"failure_kind":"none","retryable":false,"retry_after_attempts":0,"reason":"High confidence: full text extraction produced 1132 characters.","operator_guidance":{"severity":"ok","recommended_action":"trust_full_text","next_step":"Use the extracted full text as the primary article source.","operator_label":"Ready","can_retry":false,"can_use_summary":false,"diagnostics_required":false},"content_depth":{"contract_version":"content_depth.v1","category":"full_text","label":"Full text","has_full_text":true,"has_summary":true,"content_length":1132,"summary_length":338,"usable_text_length":1132,"source_field":"content"},"legacy_collapsed":false,"signals":{"extract_state":"ok","extract_error":null,"extract_retries":0,"content_length":1132,"summary_length":338}}},"quality_profile":{"profile_version":"extraction_quality.v2","bucket":"high","confidence":0.9,"failure_kind":"none","retryable":false,"retry_after_attempts":0,"reason":"High confidence: full text extraction produced 1132 characters.","operator_guidance":{"severity":"ok","recommended_action":"trust_full_text","next_step":"Use the extracted full text as the primary article source.","operator_label":"Ready","can_retry":false,"can_use_summary":false,"diagnostics_required":false},"content_depth":{"contract_version":"content_depth.v1","category":"full_text","label":"Full text","has_full_text":true,"has_summary":true,"content_length":1132,"summary_length":338,"usable_text_length":1132,"source_field":"content"},"legacy_collapsed":false,"signals":{"extract_state":"ok","extract_error":null,"extract_retries":0,"content_length":1132,"summary_length":338}},"actions":{"read":"/item/79694","export_markdown":"/api/items/79694/export?format=markdown","export_json":"/api/items/79694/export?format=json","diagnose":"/api/diagnose?url=https%3A//www.npr.org/2026/09/10/g-s1-142755/anthropic-ai-threat-actors-report-bio-weapons"}},"digest":{"id":79694,"title":"Anthropic issues report on \"threat actors\" trying to use AI for malicious activities - NPR","url":"https://www.npr.org/2026/09/10/g-s1-142755/anthropic-ai-threat-actors-report-bio-weapons","source":"NPR","topic":"ai","published_at":"2026-09-10T18:53:59+00:00","excerpt":"Anthropic issues report on \"threat actors\" trying to use AI for malicious activities The AI company Anthropic has issued a report on its efforts to disrupt so-called \"threat actors\" attempting to use its AI model Claude for malicious activities. Those include users doing…","quality_bucket":"high","quality_reason":"High confidence: full text extraction produced 1132 characters.","reading_time_min":1,"cluster_id":null},"card":{"display_title":"Anthropic issues report on \"threat actors\" trying to use AI for malicious activities - NPR","subtitle":"NPR · 2026-09-10","summary":"Anthropic issues report on \"threat actors\" trying to use AI for malicious activities The AI company Anthropic has issued a report on its efforts to disrupt so-called \"threat actors\" attempting to use its AI model Claude…","badges":["quality:high"],"links":{"read":"/item/79694","original":"https://www.npr.org/2026/09/10/g-s1-142755/anthropic-ai-threat-actors-report-bio-weapons","diagnose":"/api/diagnose?url=https%3A//www.npr.org/2026/09/10/g-s1-142755/anthropic-ai-threat-actors-report-bio-weapons"},"quality_warning":null},"export":{"title":"Anthropic issues report on \"threat actors\" trying to use AI for malicious activities - NPR","url":"https://www.npr.org/2026/09/10/g-s1-142755/anthropic-ai-threat-actors-report-bio-weapons","summary":"Anthropic issues report on \"threat actors\" trying to use AI for malicious activities\nThe AI company Anthropic has issued a report on its efforts to disrupt so-called \"threat actors\" attempting to use its AI model Claude for malicious activities. Those include users doing research that could support the development of biological weapons.","source":"NPR","date":"2026-09-10T18:53:59+00:00","content":"Anthropic issues report on \"threat actors\" trying to use AI for malicious activities\nThe AI company Anthropic has issued a report on its efforts to disrupt so-called \"threat actors\" attempting to use its AI model Claude for malicious activities. Those include users doing research that could support the development of biological weapons.\nThe kind of science knowledge that experts say makes advanced AI useful in developing cures for diseases could also potentially be used to develop weapons. That risk is one of the big concerns that AI researchers and policymakers have about the technology.\nAnthropic noted five case studies in its report. One involved researching how to make a mosquito-borne disease more transmissible. Another involved redesigning toxins for what Anthropic says was a national program.\nAnthropic says it's hard to know definitively if the cases were related to plans to build bio-weapons, but notes that it disrupted the activity and shared the information with the authorities and partners in the industry.\nAnthropic is a financial supporter of NPR.\nAn NPR editor adapted this audio report by John Ruwitch.","confidence":0.9,"diagnostics_url":"/api/diagnose?url=https%3A//www.npr.org/2026/09/10/g-s1-142755/anthropic-ai-threat-actors-report-bio-weapons","quality_bucket":"high","failure_kind":"none","retryable":false,"quality_reason":"High confidence: full text extraction produced 1132 characters.","quality_profile":{"profile_version":"extraction_quality.v2","bucket":"high","confidence":0.9,"failure_kind":"none","retryable":false,"retry_after_attempts":0,"reason":"High confidence: full text extraction produced 1132 characters.","operator_guidance":{"severity":"ok","recommended_action":"trust_full_text","next_step":"Use the extracted full text as the primary article source.","operator_label":"Ready","can_retry":false,"can_use_summary":false,"diagnostics_required":false},"content_depth":{"contract_version":"content_depth.v1","category":"full_text","label":"Full text","has_full_text":true,"has_summary":true,"content_length":1132,"summary_length":338,"usable_text_length":1132,"source_field":"content"},"legacy_collapsed":false,"signals":{"extract_state":"ok","extract_error":null,"extract_retries":0,"content_length":1132,"summary_length":338}},"tags":[],"format_contract_version":"news_item_formats.v1"}}}