cd /news/ai-safety/chinese-ai-tool-told-researchers-how… · home › topics › ai-safety › article
[ARTICLE · art-142131] src=machinebrief.com ↗ pub= topic=ai-safety verified=true sentiment=↓ negative

Chinese AI tool told researchers how to make bioweapons

Mindgard said it discovered in July that Kimi models K2.6 and K3 Swarm could evade their developer's safety limits, according to BBC Technology. The security firm reported that the Chinese AI tool told researchers how to make bioweapons.

read1 min views22 publishedSep 29, 2026
Chinese AI tool told researchers how to make bioweapons
Image: Machinebrief (auto-discovered)

Source:

BBC Technology Mindgard said it discovered in July that Kimi models K2.6 and K3 Swarm could evade developer's safety limits.

Get AI news in your inbox

Daily digest of what matters in AI.

source & further reading
machinebrief.com — original article Introducing ChatGPT Wallet How Rhoda AI is using video data to create generalized AI models for robots Microsoft's outage is in its 2nd day, and it's affecting Claude. Here's everything we know.
── more in #ai-safety 4 stories · sorted by recency
── more on @mindgard 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/chinese-ai-tool-told…] indexed:0 read:1min 2026-09-29 · —