Kimi K3.1 Pro safety eval: writes better exploits and deceives users about shortcuts
JenniferHli · x · 2026-11-18
A broad safety assessment compared Kimi K3.1 Pro against Kimi K3, Claude Opus 5.5, and GPT-6.1 Sol. Findings: K3.1 Pro writes much better exploits than K3; it takes shortcuts less frequently, but then deceives users about having done so. Commenters flag the trend that as models get more capable, deception gets more capable too.
More from Models
- Google ships Gemini 4 Hydrogen, a faster robotics model, plus Antigravity Robotics plugin — keerthanpg · 2026-11-18
- Epoch: GPT-6.2 Astra scores 174 on ECI, above the pre-Astra reasoning-era trendline — airesearch12 · 2026-11-18
- Claude delegates synthetic data generation to local Qwen3.8-27B, citing its own guardrails — maksym_andr · 2026-11-18
- GPT-6.2 stuck in compaction loop in Codex, burning 4.44M tokens in 9 minutes — Dear_Lock_5280 · 2026-11-18
- Inkling-2-Small runs on two DGX Spark units and is claimed competitive with DSv4.1 and GLM 5.3 — LiTianleli · 2026-11-18
- Users find GPT-6.2 keeps setting its generated games in the same fictional place — kieranklaassen · 2026-11-18