Stolencompute.com aggregates exposed AI models for free public inference
The X user rolled out a service that lets anyone access publicly exposed models such as Kimi 1T and Deepseek 765B.
By Ryan Merket · Published
Primary source: X
Why it matters
Stolencompute.com shows that unsecured AI model endpoints can be openly harvested, lowering barriers to powerful LLM access and amplifying both research opportunities and abuse risks.
On July 26th, 2026, acidvegas (@acidvegas) posted a brief that announced a new, openly accessible service for running AI models that have been left exposed on the internet. The tweet read:
Whoops I made something controversial again... https://t.co/PCJXSpQ5pk Enjoy using other peoples AI models that are left exposed on the internet 🏴☠️ Some of these models are rather....large...Kimi 1T, Deepseek 765B...go crazy. Cheers lads, also LOL 🤷♂️ https://t.co/opMBoUEiX5…
When you purchase through links in our articles, we may earn a small commission. This doesn’t affect our editorial independence.