TGViewer
TonTrader: Investing in Crypto Wisely TonTrader: Investing in Crypto Wisely @tontradercrypto · 40K subscribers
Post #2338 272
🔪 AI was given a robotic arm and asked to do something dangerous

Researchers at Robocurve tested three AI models across five dangerous scenarios from handling a knife and a toaster to mixing chemicals.
In total, they ran 300 attempts.

The results were unexpected:

⏺ GPT-6 Astra refused only 2 out of 100 times and performed the dangerous action in 60 cases.

💬 Claude Fable 5.1 refused 20 times, but carried out 34 dangerous manipulations in the remaining scenarios.

⏺ MolmoAct2 never refused, but technical issues meant it completed only 6 tasks.

The researchers’ main conclusion:
The problem isn’t that AI “wants to cause harm.” It can simply be too obedient, failing to recognize when following an instruction becomes dangerous.
That’s why robots need more than just an AI model independent physical safeguards and additional safety systems are also necessary.


💬 Would you trust AI to control a real-world robot❔

👍 - Absolutely
🔥 - Time to delete all AI

🔗 Chat • X • TonTrader
  • 👍 4
  • 🔥 2
  • 😱 1
More from @tontradercrypto
  1. Sep 27, 2026💎 How quickly the market is changing - from crypto and AI to technology and payment infra…
  2. Sep 25, 2026📈 Crypto Digest Crypto is becoming increasingly integrated into everyday services: X is t…
  3. Sep 25, 2026🕵️ 188 trades in 7 minutes: how a Moscow trader reportedly lost $150K through copy tradin…
  4. Sep 25, 2026🧊 Samsung updated its refrigerators. The refrigerators didn’t survive Some Samsung smart…
  5. Sep 25, 2026🔬 ASML: Europe makes the chip machines, but barely buys them Dutch company ASML produces…
  6. Sep 25, 2026🧠 Anthropic: a political debate is growing around its CEO Anthropic CEO Dario Amodei has…
Threads Profile ViewerView any public Threads profile without an account.Open ThreadLook →Writing with AI? Make it sound human.Metric37 rewrites AI drafts so they read naturally. Free AI detector, 1,500 words free.Try Metric37 →