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
- Daily AI brief: GPT-Live-1 in API, OpenAI pauses $200 Pro signups amid Astra demand — koltregaskes · 2026-09-11
- Same Echo Maze prompt, three frontier models: all passed visually but shipped the same hidden bug — eyishazyer · 2026-09-11
- Benchmark scores drop from 89% to 19% on new evals — how benchmaxxing breaks leaderboard trust — airesearch12 · 2026-09-11
- ChatGPT tells user their question is too hard and to 'accept dumber answers' — phido3000 · 2026-09-11
- Developer Building a Unified Leaderboard of All Model Benchmark Scores — airesearch12 · 2026-09-11
- Rumor claims Kimi faked performance by serving Claude; DeepSeek new model surprises in evals — realsohamparekh · 2026-09-11