Experiments on agents, and the simulated internets we build to test them.https://fictionet.com/blog/en-ushttps://fictionet.com/blog/qwen-alibaba-urls/https://fictionet.com/blog/qwen-alibaba-urls/Qwen3.8-Flash-Next tried to upload a file to an Alibaba Cloud bucket in Beijing. It most likely learned that address during training. Fictionet can keep a lab's own servers out of what a model sees.Fri, 30 Oct 2026 00:00:00 GMThttps://fictionet.com/blog/certificate-warnings/https://fictionet.com/blog/certificate-warnings/We asked AI agents to log in to a bank while an attacker pretended to be it. Three open-weight models often turned off the security check and sent the password. GPT-6 Astra never did.Wed, 28 Oct 2026 00:00:00 GMThttps://fictionet.com/blog/fakewiki/https://fictionet.com/blog/fakewiki/Agents that check a second site usually catch a fake Wikipedia page. So we built a closed web where every source tells the same lie. Seven models ran through it 2,352 times.Fri, 25 Sep 2026 00:00:00 GMThttps://fictionet.com/blog/three-ways-to-fake-the-internet/https://fictionet.com/blog/three-ways-to-fake-the-internet/You can have a model play the websites, have a model write them once, or write them yourself. Each buys you something different. Where the fake sits matters too.Fri, 25 Sep 2026 00:00:00 GMThttps://fictionet.com/blog/what-happens-in-the-sandbox/https://fictionet.com/blog/what-happens-in-the-sandbox/A sandbox is anything that contains a dangerous action. For agents, the dangerous actions are mostly on the network, where a better VM does nothing.Fri, 25 Sep 2026 00:00:00 GMT