现代大语言模型能否准确数出"blueberry"中有多少个字母"b"？
这是一个针对大语言模型的对抗性问题，但并非不公平的测试。文章探讨了现代LLM在处理看似简单的计数任务时面临的挑战，揭示了模型在基本推理能力方面的局限性。
相关报道
A compromised version of the LiteLLM Python package (version 1.82.8) was briefly available on PyPI, capable of exfiltrating sensitive credentials like SSH keys and cloud secrets. The malicious package affected any project that depended on LiteLLM, though it was only available for about an hour before discovery.
A supply chain attack has compromised the popular npm axios HTTP client library with 300 million weekly downloads. Malicious versions install a remote access trojan, though some users may have avoided infection through version pinning or older installations. Security experts warn this is a live compromise affecting one of npm's most depended-on packages.
A series of supply chain attacks has affected npm and PyPI repositories within two weeks. The use of large language models is exacerbating these security issues, and existing mitigation measures are insufficient to address the problem.
A new phishing-as-a-service called Starkiller uses disguised links to load real login pages from target brands. It acts as a relay between victims and legitimate sites, forwarding usernames, passwords, and MFA codes to bypass security measures.
A security researcher discovered a vulnerability that allowed obtaining full administrator rights in a Replit clone. The vulnerability stemmed from running untrusted code in an insecure manner. This highlights the importance of proper security practices when executing external code.