Anthropic’s new budget model gets much better at ignoring hidden commands

Anthropic released Claude Haiku 5.5, a budget model for quick, repetitive and speed-sensitive workloads, which the company says is better at finding vulnerabilities and writing exploits than its predecessor Haiku 4.5. Anthropic gave Claude Haiku 5.5 stricter cybersecurity safeguards than Haiku 4.5 but lighter ones than its more advanced models, and measured the model's offensive abilities with those safeguards switched off, including a test involving known flaws in Chrome's V8 engine.

Anthropic’s Claude Haiku 5.5 model, designed for quick, repetitive workloads and speed-sensitive tasks, is now better at finding vulnerabilities and writing exploits than its predecessor. The company has given it stricter cybersecurity safeguards than Haiku 4.5, though lighter ones than its more advanced models, whose offensive skills remain well ahead. Cybersecurity capabilities and safeguards Anthropic measured the model’s offensive abilities with its cybersecurity safeguards switched off. In a test involving known flaws in Chrome’s V8 … More https://www.helpnetsecurity.com/2026/10/08/anthropic-claude-haiku-5-5/ The post Anthropic’s new budget model gets much better at ignoring hidden commands https://www.helpnetsecurity.com/2026/10/08/anthropic-claude-haiku-5-5/ appeared first on Help Net Security https://www.helpnetsecurity.com .