Please don’t meat-proxy.

What is meat-proxying?

A meat proxy is a human who forwards questions to an AI and forwards the answers back — adding nothing but latency.

• https://meatproxy.me/

Firefox includes/supports translation models, IIRC on mobile as well. They’re pretty small and probably good.

Another place I would check is f-droid - serving OSS apps so can be inspected. I thought I had a translator app installed like that, but it doesn’t seem to use models. I probably mixed it up with a different app that uses models for voice to text.

R1dacted: Investigating Local Censorship in DeepSeek’s R1 Language Model

Quoting from the abstract:

While existing LLMs often implement safeguards to avoid generating harmful or offensive outputs, R1 represents a notable shift—exhibiting censorship-like behavior on politically charged queries. […]

Our findings reveal possible additional censorship integration likely shaped by design choices during training or alignment, raising concerns about transparency, bias, and governance in language model deployment.

lightning fast tokens per second

lightning fast sounds fast, tokens per second sounds slow…

For those interested in the desktop-capable requirements: 16 GB GPU. 9070 XT?

For lighting fast performance with the OpenAI GPT-OSS 20B model, users can use the AMD Radeon™ 9070 XT 16GB graphics card in a desktop system.

Does it require that gen?

No time for commas with how fast this tech is developing