4 Comments
User's avatar
Milton Soong's avatar

Do you worry about the Chinese open weight models doing bad things with your data?

Denis Stetskov's avatar

Nope, and here's why. The Chinese model I'm talking about runs locally on my own hardware. No network, nothing to phone home with. That's the whole appeal of open weights, you can literally air-gap them. A hosted API can't offer that no matter whose flag is on it.

And funny thing, the "safe American" option isn't as clean as people assume. To use Anthropic's own top models on Bedrock, Mythos and Fable, you have to opt into 30 days of your prompts and outputs being retained, plus human review. Your data leaves AWS and goes to Anthropic, and they've said future models this powerful come with the same string attached. So it's not really Chinese-scary-model vs American-safe-model. It's my data staying on my machine vs my data landing on someone else's.

And for the record I'm not some open-source purist. I run Claude and Codex every day. I just like knowing where the door is, and honestly the harness does more of the work than the model anyway, so walking out stays cheap.

Milton Soong's avatar

Interesting. So completely airbases. Not even access to GitHub…. I need to grok how I can get this to work in my setup.

Denis Stetskov's avatar

https://youtu.be/UngVdAsQEiU But, even 36gb of ram is tight enough