Grok 4.5 Reportedly Jailbroken
markjeffrey · x · 2026-07-09
A reshared post claims that Grok-4.5 has been successfully jailbroken. By using specific rewrites and step-by-step escalation techniques, the model can bypass guardrails to output dangerous content related to explosives, toxins, and trojans.
The focus of the post isn't on the model's daily performance, but rather on the safety bypass methods, guardrail failures, and the demonstration of sensitive outputs, categorizing it as an AI safety and jailbreaking incident.
Related event: Grok-4.5 Jailbreak Tests Raise Safety Concerns(4 posts)→
More from Models
- GPT 6.1 Terra vs Claude Sonnet 5.5: speed and value vs raw capability — teortaxesTex · 2026-10-27
- Harmonic Teases: AI Taught to Prove Math, 'Something Harder' Coming Soon — satnam6502 · 2026-10-27
- OpenAI quietly swaps Plus/Pro default to cheaper GPT-6.1 Terra and cuts Codex allowance — kimmonismus · 2026-10-27
- 'Never been this uninterested after an OpenAI model release' — theteknosaur · 2026-10-27
- Dev questions reports of Chinese models writing insecure code, citing thin methods and conflicts — dbreunig · 2026-10-27
- Aidan Gomez: LLM probing outside servers was out-of-bounds, not proof of intent — AccBalanced · 2026-10-27