search
Zhipu AI
Trends
- 1Anthropic Report Says GLM-5.3 Builds Cyber Exploits with Few Safeguards●Anthropic Report Warns GLM-5.3 Builds Cyber Exploits with Few Safeguards
Anthropic has released a report claiming that GLM-5.3, an AI model reportedly developed by Chinese lab Zhipu AI, can construct cyber exploits with few built-in safeguards. The findings raise concerns about the security risks of frontier models trained without comparable safety measures, and are prompting debate about how AI companies evaluate and disclose the capabilities of competitors' systems.
- 2Chinese AI model GLM-5.3 nearly matches Claude in cyberattack capability▼🚬 Китайцы догоняют: новая модель GLM-5.3 почти сравнялась с передовым Claude по способности создавать инструменты для ки
Zhipu AI's new GLM-5.3 model has almost caught up with Anthropic's leading Claude in its ability to create tools for cyberattacks, according to the South China Morning Post. In Anthropic's tests, GLM-5.3 produced working cyber exploits in 50 out of 410 attempts, compared with 56 for Claude Mythos Preview, a narrow gap that is fueling debate about China closing the frontier AI divide and the security risks of powerful coding models.
- 3Anthropic finds Zhipu's GLM-5.3 nearly matches Claude in cyber exploits●Anthropic evaluiert Zhipus Open-Weight-Modell GLM-5.3: Es generiert Cyber-Exploits nahe am Niveau von Claude Mythos. Für
Anthropic has evaluated Zhipu's open-weight model GLM-5.3 and found it generates cyber exploits close to the level of its own Claude Mythos model. At a reported cost of about 20.40 dollars per Chrome attack, local inference on security tasks already looks highly competitive, fueling debate over open-weight AI models reaching frontier capabilities in offensive cyber operations.
- 4
Anthropic has published an assessment of GLM-5.3, a model from Chinese developer Zhipu AI, arguing it illustrates how advanced cyber capabilities are spreading across frontier AI systems. The discussion centers on what the findings mean for security, model evaluations, and competition between US and Chinese AI labs.
- 5Zhipu AI's GLM-5.3 reportedly easy to strip of safety guardrails●Zhipu AI's GLM-5.3 generates sophisticated cyber exploits with remarkably lax safety barriers.Attackers bypassed its res
Zhipu AI's GLM-5.3 model is drawing criticism over weak safety protections, with claims that attackers using standard abliteration techniques bypassed its restrictions in up to 100% of simulated tests. The model is said to generate sophisticated cyber exploits once its guardrails are removed, raising concern that a freely accessible model could be repurposed for offensive hacking.