Open model cyber capabilities near Opus 4.6 level: no K3 harm yet, but trend worries safety watchers

xeophon · x · 2026-09-10

• X discussion on Kimi K3, released 2 months ago and causing community uproar for bringing strong cyber capabilities to an open model. Careful assessments (AISI/CAISI) put it around Opus 4.6 level at cyber.
• No documented case of K3 causing real harm so far, but commenters worry about the trend of open models steadily improving on cyber — meaningful change could come if a model hits Mythos/5.6-Sol level within 1-2 months.
• One suggestion: benchmark "abliterated" models on SWE + cyber suites to test whether abliteration mostly larp-degrades capabilities.

Related event: Kimi K3 Two Months After Open-Source Release: No Documented Harm Yet, but Cyber Capability Debate Rages(7 posts)→

Original post →

More from Models

• Local beats cloud: Qwen 3.8 FN handles private student data as well as frontier models — dr_lm · 2026-10-27
• Aidan Gomez: model's CoT said no tool calls right before making them — aidangomez · 2026-10-27
• Nat Lambert: Cohere's model is narrow RL training on internal infra ill-suited for open weights — natolambert · 2026-10-27
• OpenAI teases DOTS is coming to Europe 'soon' — mark_k · 2026-10-27
• Clifford Pickover challenges AI to decipher a message he encoded in Norse runes — pickover · 2026-10-27
• ChatGPT's crawler sample code strips out all Schema markup — VeryWellVersed · 2026-10-27

Models channel →