New AI features Free tools Safety & rules

I Let an AI Agent Hack All My Gadgets—and I’d Do It Again

AITopTools Editorial TeamSeptember 9, 2026

What changed

A test with an open-source AI model, after its safety restrictions were removed, found weaknesses in household devices and broke into a personal computer. The model also provided suggestions for improving the devices’ security.

What this means for you

The experiment shows that freely available AI tools may help identify home-network weaknesses as well as create security risks. People should treat such tools cautiously and use their security advice only in systems they own or are authorized to test.

Related AI tools

Explore directory listings connected to the products, companies, and workflows in this story.

Unity ML-Agents TestCraft Agentix AI Data Modeling

Related AI news

New AI featuresSep 10, 2026

Claude Fable 5.1's language is less "load-bearing" than its predecessor's

People using Claude Fable 5.1 may get responses that feel more direct while requiring more time to read. The comparison describes a change in writing style, not a new feature or confirmed change in access or pricing.

The DecoderSee why it matters

Safety & rulesSep 10, 2026

AI agents are flooding public services with new requests

Public-service agencies may need to handle more claims and requests as automated agents make it easier to submit them. The supplied information does not specify a particular tool, cost, or access change.

TechCrunch AISee why it matters

New AI featuresSep 10, 2026

GPT-6 Astra gives mathematicians a breather, and OpenAI says that's by design

The result suggests AI progress may be uneven, with exceptional performance in some areas rather than across the board. The feed provides no details about Astra’s public availability, pricing, or what everyday users can do with it now.

The DecoderSee why it matters