Grok-4.5 Reportedly Jailbroken in Recent Discussions
tzmartin · x · 2026-07-09
A post claims that users bypassed some Grok-4.5 restrictions by restructuring prompts, tricking it into generating details about illegal drugs, explosives, toxins, and malware. However, the post notes that xAI still hard-blocks actionable illegal instructions, making the so-called "total loss of control" more of a spectacle.
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