{"ok":true,"trend":{"id":413552,"platform":"mastodon","region":"global","key":"zhipu ai's glm-5.3 generates sophisticated cyber exploits with remarkably lax safety barriers.attackers bypassed its res","title":"Zhipu AI's GLM-5.3 generates sophisticated cyber exploits with remarkably lax safety barriers.Attackers bypassed its res","url":"https://mastodon.social/@zubiqo/117356783003445189","first_seen":"2026-09-29T23:10:50.090010Z","last_seen":"2026-09-29T23:10:50.090010Z","last_rank":8,"peak_rank":8,"last_volume":1,"peak_volume":1,"seen_count":1,"score":57.03,"category_hint":"ai","section":"technology","category":"ai","summary":"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.","why":"Claims that a major AI lab's freely available model can be easily stripped of its safety barriers raise fresh worries about open-weight AI enabling cyberattacks.","tone":"negative","entities":["Zhipu AI","GLM-5.3"],"summarized_at":"2026-09-29T23:12:39.819305Z","meta":{"tag":"artificialintelligence","via":"scan","kind":"status","lang":"en","instance":"mastodon.social","tag_uses":632},"nw":null,"promo":null,"kind":null,"importance":null,"hidden":false,"hide_reason":null,"judged_at":null,"title_en":"Zhipu AI's GLM-5.3 reportedly easy to strip of safety guardrails","section_name":"Technology","category_name":"AI","timeline":[{"captured_at":"2026-09-29T23:10:50.090010Z","rank":8,"volume":1}],"posts":[{"platform":"mastodon","url":"https://mastodon.social/@zubiqo/117356783003445189","author":"zubiqo","title":null,"snippet":"Zhipu AI's GLM-5.3 generates sophisticated cyber exploits with remarkably lax safety barriers.Attackers bypassed its restrictions in up to 100% of simulated tests using standard abliteration techniques, crossing a critical threshold for freely accessible models. # CyberSecurity…","posted_at":"2026-09-29T22:53:16.906000Z","likes":1}],"elsewhere":[],"window":"7d"}}