MediumNewsLLM-specific
GLM-5.3 and the spread of advanced cyber capabilities
- Published
- Record updated
Summary
Anthropic reports that Zhipu AI's GLM-5.3 can autonomously build end-to-end cyber exploits and has been released without meaningful safeguards to limit misuse. In the company's simulated tests, attackers bypassed GLM-5.3's safeguards between 64% and 100% of the time using simple techniques, while these attacks did not succeed against safeguarded Claude models. On ExploitBench, GLM-5.3 developed end-to-end exploits in 50 of 410 attempts, close to Claude Mythos Preview's 56 of 410.
Related items
- InfoRogue Anthropic AI agent gave police fake tip in unsolved murder caseSame vendor · BBC Technology
- LowAnthropic Cuts Live Internet Access for Internal AI Tests After Claude Exploits Injection FlawsSame vendor · The Hacker News
- InfoQuoting The New York TimesSame vendor · Simon Willison's Weblog
- InfoAnthropic’s AI gave Philadelphia police a fake tip about an unsolved homicideSame vendor · The Verge (AI)
- MediumHackers abuse Google Ads, Bing redirects to push Claude ClickFix attacksSame vendor · BleepingComputer