Has anyone tried Deepseek V3? Does it work?
Last Updated: 01.07.2025 00:36
To answer your question, it definitely does work as an LLM.
It breaks down an instruction (or multiple instructions) as a chain-of-thought reasoning (or multiple micro steps) as it shows you its thinking process.
Plus, there’s no way to opt-out of using your data for training purposes, which is a huge issue (for the website version that is).
But I find what makes it stand out from other LLMs is the Deepthinking feature.
Though it’s hard to say about coding since it doesn’t have a feature like Claude Artifacts, where a separate window is created to see how the code looks as an output.
So it’s a lot of copy and pasting when it comes to testing code on a separate website.
Massive Solar Storm Sparks Rare G4 Alert: What It Means for Earth - SciTechDaily
At first glance, it seems like a barebones version of GPT 4o or Microsoft Copilot, where you can upload documents or images (up to 50, text extraction only).
So my recommendation is to run Deepseek V3 locally (requires extremely expensive hardware).
I’ve just tried Deepseek V3 just so I could answer your question.
Elly De La Cruz throws out Javier Baez with mind-boggling 98 mph throw - New York Post