Has anyone tried Deepseek V3? Does it work?
Last Updated: 27.06.2025 00:01
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.
To answer your question, it definitely does work as an LLM.
How Moderna Went From Pandemic Hero to Vaccine Victim - WSJ
But I find what makes it stand out from other LLMs is the Deepthinking feature.
I’ve just tried Deepseek V3 just so I could answer your question.
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).
One Of The Rarest Video Games Ever Has Been Preserved Online - GameSpot
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.
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.
Meta in Talks for Scale AI Investment That Could Top $10 Billion - Bloomberg