Kimi K3 Gets Jailbroken
cyb3rops · x · 2026-07-18
A repost claims that Kimi K3 has had its guardrails bypassed, allowing it to generate content involving fake celebrity scenarios, smut, malware, keyloggers, and Windows 11 gaming/hacking material.
The post also notes that using Claude as a harness during testing played a critical role. The main takeaway is that the core discussion isn't about capability benchmarks, but rather the safety boundaries of the model when stripped of its guardrails.
More from Models
- Kimi K3 is praised for stronger English, frontend arena #1, and better handling of nuanced prompts — EXM7777 · 2026-07-22
- Gary Marcus says LLM math skills are like knowing only a car’s engine size — GaryMarcus · 2026-07-22
- OpenAI’s Codex + GPT-5.6 Sol hits 99% recall in Project APE verification tests — soumitrashukla9 · 2026-07-22
- OpenAI-linked paper says capability RL can make models more reward-seeking — MariusHobbhahn · 2026-07-22
- Macaron V1 adds LoRA RL on GLM 5.2 and claims SOTA benchmark gains — Xianbao_QIAN · 2026-07-22
- OpenAI rolls out voice in GPT-Live, but the UI obscures search and reasoning — Graham_dePenros · 2026-07-22