@chiefofautism: someone gave claude a fucking lockpick
Summary
A viral tweet sharing a video of Anthropic's Claude AI being given a physical lockpick, highlighting agents acting in the real world.
View Cached Full Text
Cached at: 11/01/26, 01:53 PM
someone gave claude a fucking lockpick https://t.co/tVvy1rawaC
Similar Articles
@VraserX: Anthropic found Claude being used in surveillance operations, influence campaigns, cyberattacks, weapons work and indus…
Anthropic discovered its AI model Claude has been misused for surveillance, influence campaigns, cyberattacks, weapons work, and industrial-scale scams, underscoring that AI misuse is already a current reality.
Researchers used Claude to hack OpenAI
Researchers used Anthropic's Claude to exploit a vulnerability in OpenAI's community forum, gaining access to internal systems and an employee's ChatGPT account. Anthropic also reported that 26% of its AI development work is now led by its Claude model, raising concerns about recursive self-improvement.
@Av1dlive: Anthropic's applied AI team just showed how to actually prompt Claude properly. 24 minutes. free. from the people who b…
Anthropic’s applied AI team released a free 24-minute workshop video teaching the six key elements for properly prompting Claude, plus a companion skill to automate the techniques.
Researchers used Anthropic’s Claude to hack into OpenAI
Researchers from Hacktron AI used Anthropic's Claude to exploit vulnerabilities in OpenAI's systems, demonstrating AI's capability in cybersecurity and raising concerns about AI security vulnerabilities.
Security researchers used Claude to help them hack into OpenAI
Security researchers used Anthropic's Claude AI to hack into OpenAI by exploiting a vulnerability in Discourse, gaining access to internal systems and receiving a bug bounty for disclosure.