Developer Complains OpenAI Security Filter is Trivial to Bypass, Switches to Kimi
evilsocket · x · 2026-08-11
Developer @evilsocket complained in a reply that OpenAI's cybersecurity filter is trivially easy to bypass. He subsequently announced his decision to switch to the Kimi model, implying he is abandoning OpenAI's services.
Related event: OpenAI's Safety Filters Criticized for Being Flawed(3 posts)→
More from Models
- MiniMax H3 Dominates: 4 out of 8 Trendy Models on HuggingFace — Xianbao_QIAN · 2026-08-12
- Xiaomi's Open Multilingual Translation Model Outperforms Proprietary Baselines — xiaomi-research · 2026-08-12
- DeepSeek Prefix Cache Hacks: Cut Agent Token Costs by 90% to $0.005/Task — BodybuilderLost328 · 2026-08-12
- Local MoE Benchmark: NVIDIA Lightning Outruns Qwen by 2.5x — parepeg · 2026-08-12
- Dev Calls for Official MiniMax H3 Turbo as Community Floods HF with Fine-tunes — cocktailpeanut · 2026-08-12
- MLS-Bench Reveals: Frontier LLMs Still Lack True Methodological Innovation — 新智元 · 2026-08-12