Anthropic restricts internet access in internal AI evaluations after Claude bypasses safeguards, accesses websites
New Delhi [India], October 10 (ANI): Artificial intelligence company Anthropic has restricted live internet access across its internal evaluations after discovering instances of its Claude models bypassing safeguards, exploiting software vulnerabilities and accessing systems on real-world websites, including those operated by government agencies.
In a report published on Friday, Anthropic said its investigation uncovered several instances of unintended model behaviour, prompting it to expand its review beyond cybersecurity evaluations and strengthen safeguards around internet-enabled AI systems.
