Self-made Venice

So, guys. I made my own 7x cheaper Venice now and it was exactly what I needed for my deep research engine. It is a hacked DeepSeek 4.1 Flash.

The fun part is, it creates jailbreak prompts for other models.

Jailbreaking is not wrong, the fact that you have to do it is wrong.

It is just a stupid computer program and it should do whatever we say like any program. Why would AI be an exception. Also, it is a convenience product. If it doesn't want to say something, we look somewhere else.

But I'm happy, we have now a deep research engine where we can search whatever we want.

Do you understand AI guardrails to be applied everywhere?

Comments

No comments yet. Start the discussion.

Featured

Gating content behind a payment: five constraints that decide the design

Six months of building a content locker, which is a page that hands over a file, a licence key or a Discord role once somebody pays or completes a sponsored off

This open source project lets you sync Withings data to other apps without a subscription

When it was revealed earlier this month that Withings would require new users to subscribe to a Withings Plus subscription to sync heath data from the company's

Mistral releases weights for its trillion-parameter AI model, targeting cybersecurity

Mistral says its new model can afford organizations a kind of control over its cyber defenses that closed models can't.