Has anyone tried Deepseek V3? Does it work?
Last Updated: 30.06.2025 00:59
I’ve just tried Deepseek V3 just so I could answer your question.
To answer your question, it definitely does work as an LLM.
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).
Study tightens King plot-based constraints on hypothetical fifth force - Phys.org
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.
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).
So it’s a lot of copy and pasting when it comes to testing code on a separate website.
Yankees will have to find ninth-inning serenity in Luke Weaver’s absence - New York Post
So my recommendation is to run Deepseek V3 locally (requires extremely expensive hardware).
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.
But I find what makes it stand out from other LLMs is the Deepthinking feature.
20-Year Mystery of The Muon's Wiggle May Finally Be Solved - ScienceAlert