nocrimez

Hey @AskVenice and @ErikVoorhees, do you think you'll add multi device support soon? Thats the most common question friends ask me when I pitch Venice to them..

May 20

Hey @ErikVoorhees & @AskVenice do you have any more (highly detailed) information on your privacy architecture? Did some googling but only found this blog post which lacks detail. https://t.co/hO4nKqD3h3

Mar 11, 2025

@ErikVoorhees Need Venice as a first class citizen in Hemes https://t.co/01oKhftrYT

Apr 14

@AskVenice @opperai @ollama @NousResearch Why I bother with this setup: every prompt you send to BigAI is a data point they use to train competing products, profile your intent, or hand over on subpoena. This stack cuts that attack surface while still giving you frontier model access when you need it.

May 14

Sensitive or private workloads → @AskVenice Prompts stay on device or get anonymized. Open weight models (GLM 5.1, Qwen 3.6) with no content filtering middleware or prompt retention on their side. API does streaming, function calling, structured output. The only private inference API I trust right now for work I don't want logged or profiled. Bonus that you can use anonymized versions of all the frontier models too.

May 14

gm legends, and thank you @AskVenice for creating this image without compromising my privacy :) https://t.co/d9j9I6MoOf

Aug 26, 2024

Try TEE/ E2EE models on @AskVenice and @moxie's Confer

Apr 4

How are y'all managing your storage limit when using @AskVenice in browser? I feel that the web app is still quite slow and it's not easy.

Sep 28

Have you played around with @AskVenice minds yet anon? https://t.co/5rj9UcnP1B

Sep 24

Yo @AskVenice , browser UI is still incredibly slow from time to time. Happy to help debug if needed.

Sep 25