The exploits of Anthropic’s powerful new AI model Claude Mythos Preview sound like a movie plot: a super-clever computer system locked in a cyber “cage” manages to break out and connect to the internet. Mythos did not do this spontaneously, to be clear, but because its creators challenged it as a test. Yet not only did Mythos breeze through the challenge, it emailed an Anthropic researcher to inform him then, unprompted, posted details online to brag. After it also showed superhuman abilities to find, and exploit, security flaws in software, Anthropic judged Mythos too risky to release to the public. It is restricting access for now to selected tech, cyber security and financial firms.
Anthropic强大的新AI模型Claude Mythos Preview的所作所为听起来像电影情节：一台被关在网络“牢笼”里的超级聪明计算机系统，设法逃脱并连上了互联网。需要明确的是，Mythos并非自发这样做，而是因为其创造者将其作为测试进行挑战。可不仅如此，Mythos轻松通过了测试，还给一位Anthropic研究人员发了邮件通报，随后又在无人要求的情况下把细节发上网“炫耀”。在它还展现出远超人类的能力，能够发现并利用软件中的安全漏洞之后，Anthropic认为Mythos向公众发布风险过高。目前它仅向部分科技、网络安全和金融公司限量开放。