3 articles · 2 outlets
- 5d agoSecurityWeekPickupAnthropic Rolls Out Mythos 5.2 With Improved Bug Hunting, Fewer Sandbox Escapes
- 2d agoAnthropicEarliestClaude's new constitution
- 2d agoAnthropicDetecting and countering malicious uses of Claude
← Back to the boardNews
Detecting and countering malicious uses of Claude
Why it’s here: A frontier AI developer's threat report on malicious Claude misuse (influence operations, credential theft targeting IoT devices, malware generation) is directly relevant to AI and cybersecurity policy, since it shapes federal debates on AI misuse safeguards and the threat landscape.
Trace across the boardItem
2d agoAnthropicDetecting and countering malicious uses of ClaudeAnthropic published a new constitution for its Claude models, releasing the full text under CC0 so anyone can use it freely. CyberAI91 linked
Coverage
2 outlets · first seen 5d agoConnected
29 links- NewsAttackers Crash Claude's 'Office Party' Flaw to Run Malicious Code on LinuxBoth involve Anthropic, Claude
- NewsClaude's new constitutionBoth involve Anthropic, Claude
- NewsHow Claude's text watermarking worksBoth involve Anthropic, Claude
- NewsAn update on our election safeguardsBoth involve Anthropic, Claude
- NewsAnthropic Economic Index report: Learning curvesBoth involve Anthropic, Claude
- NewsWhat 81,000 people told us about AI economicsBoth involve Anthropic, Claude
- NewsStatement on the comments from Secretary of War Pete HegsethBoth involve Anthropic, Claude
- NewsWhen AI builds itselfBoth involve Anthropic, Claude
- NewsLLMs are making formal software verification feasible at a much larger scaleBoth involve Anthropic, Claude
- NewsMeasurements for understanding the pace of AI development inside frontier labsBoth involve Anthropic, Claude
- NewsImproving our alignment and security practicesBoth involve Anthropic, Claude
- NewsInvestigating three incidents in our cybersecurity evaluationsBoth involve Anthropic, Claude
- NewsU.S. elections readinessBoth involve Anthropic, Claude
- NewsEnabling independent research on how people use ClaudeBoth involve Anthropic, Claude
- NewsMeasuring AI agent autonomy in practiceBoth involve Anthropic, Claude
- NewsClaude does cyber competitionsBoth involve Anthropic, Claude
- NewsMapping the mind of a large language modelBoth involve Anthropic, Claude
- NewsAutomated researchers can reliably mitigate alignment failuresBoth involve Anthropic, Claude
- NewsDetecting and countering misuse of AI: August 2025Both involve Anthropic, Claude
- NewsAnthropic Rolls Out Mythos 5.2 With Improved Bug Hunting, Fewer Sandbox EscapesBoth involve Anthropic, Claude
- NewsLabor market impacts of AI: A new measureBoth involve Anthropic, Claude
- NewsLLMs and bioriskBoth involve Anthropic, Claude
- NewsTeaching Claude whyBoth involve Anthropic, Claude
- NewsNatural Language AutoencodersBoth involve Anthropic, Claude
- NewsAnthropic targets valuation of up to $1.4 trillion for blockbuster IPOBoth involve Anthropic, Claude
- NewsChallenges in red teaming AI systemsBoth involve Anthropic, Claude
- NewsOpenAI, Google, Anthropic hit with lawsuit seeking halt to frontier AI developmentBoth involve Anthropic, Claude
- NewsEmotion concepts in a large language modelBoth involve Anthropic, Claude
- NewsReflections on our Responsible Scaling PolicyBoth involve Anthropic, Claude
About
- Anthropic
- Claude