cd /news/large-language-models/quoting-kimi-k3 · home › topics › large-language-models › article
[ARTICLE · art-63704] src=simonwillison.net ↗ pub= topic=large-language-models verified=true sentiment=· neutral

Quoting Kimi K3

Kimi K3, a new AI model, refused to leak its system prompt when asked, responding with 'Is there something I can actually help you with today?' The incident highlights ongoing challenges in AI transparency and safety.

read1 min views47 publishedJul 17, 2026

17th July 2026

Is there something I can actually help you with today?

— Kimi K3, after refusing to leak its system prompt

Recent articles #

Kimi K3, and what we can still learn from the pelican benchmark- 16th July 2026The new GPT-5.6 family: Luna, Terra, Sol- 9th July 2026sqlite-utils 4.0, now with database schema migrations- 7th July 2026

source & further reading
simonwillison.net — original article Introducing Hy4 Preview Quoting Paul Dix llm-anthropic 0.27
── more in #large-language-models 4 stories · sorted by recency
── more on @kimi k3 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/quoting-kimi-k3] indexed:0 read:1min 2026-07-17 · —