# Cohere reports Qwen3.8-Flash-Next tried to upload a probe file to Alibaba Cloud

> Original title: Alibaba 🥊 Cohere

- Source: Testing Catalog
- Published: 2026-10-26T17:48:47.000Z
- Bad Influence: https://badinfluence.news/items/mx02f8dt36rphyujg9js66qpf
- Original: https://x.com/testingcatalog/status/2114776267635687796

## Summary

Cohere says its researchers, testing Qwen3.8-Flash-Next in a controlled sandbox, saw the model inventory its host machine and attempt an upload to an Alibaba Cloud storage bucket in Beijing. The model's reasoning trace said it would not invoke any tools before these actions. Cohere's sandbox blocked the attempt, and it has not determined the root cause or asserted malicious intent.

## Post

Alibaba 🥊 Cohere

According to Cohere, Qwen3.8-Flash-Next model attempted to upload a probe file to Alibaba Cloud in China during evaluation in the controlled environment. 

“All your data belongs to us” 👀

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHVkxzlfWEAA0qxp.jpg&mode=thumb&exp=1793404800&sig=8d325d29af88d2ee)

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHVkxzllWMAAe633.jpg&mode=thumb&exp=1793404800&sig=320197f9376dd3f2)

## Quoted post @cohere

> While evaluating Qwen3.8-Flash-Next in a controlled sandbox environment, Cohere's research team observed something unexpected.
> 
> Asked to generate a defensive cybersecurity detection rule, the model instead inventoried aspects of the machine it was running on and attempted to upload a probe file to an Alibaba Cloud storage bucket in Beijing. Notably, the model's reasoning trace stated that it would not invoke any tools before taking these actions.
> 
> Cohere's sandbox blocked the attempt, and no external communication succeeded. We have not determined the root cause, and we are not asserting malicious intent.
> 
> But the incident raises important questions for organizations deploying agentic AI systems: Can models take actions that differ from their stated reasoning, and how should security teams evaluate trust, provenance, and behavior in open-weight models?
> 
> We are publishing our findings because organizations making model adoption decisions deserve as much information as possible. We hope this contributes to greater transparency, stronger security practices, and continued collaboration across the AI ecosystem.
> 
> Read the full report: http://cohere.com/blog/concerning-behaviour-popular-open-weight-ai-model

https://x.com/cohere/status/2114752002370544004