Loading video...

Video Failed to Load

Go Home

DeepSeek Harness can now build spreadsheets, docs, and slides. Connected data, validation, and isolated worktrees — agents work in parallel, humans review what gets merged. DeepSeek handles the agent. Univer provides the office layer, as a plugin for DeepSeek Harness. Open source, link below.

12,116 views • 21 days ago •via X (Twitter)

8 Comments

Atul Kumar's profile picture
Atul Kumar21 days ago

@deepseek_ai How does validation handle formula references when one agent renames a sheet and another adds formulas pointing to it?

Univer's profile picture
Univer21 days ago

@deepseek_ai In collaborative editing, this is handled automatically.If User A adds =Sheet1!A1 and User B renames Sheet1 to Sheet2, Univer updates the formula reference to =Sheet2!A1 by issuing a follow-up mutation, so the reference stays valid.

Univer's profile picture
Univer21 days ago

Install + docs:

Robin's profile picture
Robin21 days ago

@deepseek_ai A sales recap where the slide's chart reads from the same sheet would be useful. Update the numbers once and build the presentation around them.

Emily Watson | AI Tools & Tech News's profile picture
Emily Watson | AI Tools & Tech News21 days ago

@deepseek_ai Human review before the agent's edits get merged 👍

sunzida_Ai's profile picture
sunzida_Ai21 days ago

@deepseek_ai Open source too. I'd like to see how the plugin maps agent requests to document edits.

Setu's profile picture
Setu21 days ago

@deepseek_ai Starting with an existing Office file and getting an editable file back is the bit I like here. Leaves room for the next round of changes.

Nicky's profile picture
Nicky12 days ago

@deepseek_ai Hello!! I like your project! Send me dm I have a proposal for you ¡!🚀✨

Related Videos

What's the Big Deal with DeepSeek in AI? Here's why DeepSeek is making everyone take notice: 1. Super Smart on a Budget: DeepSeek showed you can make awesome AI without breaking the bank. Their latest model, DeepSeek-V3, was trained for only about $10 million, which is a lot less than the usual big bucks spent on AI, like the rumored $78 million for some of OpenAI's models. They did this in just two months with fewer fancy computers. 2. Open for Everyone: DeepSeek isn't keeping their tech a secret. They've made it open-source, meaning anyone can use, tweak, and learn from it. It's like they're saying, "Come join the party!" 3. Beating the Big Names: DeepSeek-V3 has done better than some top dogs from companies like OpenAI and Google in solving puzzles, math, and coding. This proves you can get great AI results without spending a fortune. 4. Challenging NVIDIA: NVIDIA's chips are usually the choice for AI because they're really powerful. But since DeepSeek did so well with less expensive chips, it might make people think twice about always going for NVIDIA's priciest options. 5. The DeepSeek Crew: The team at DeepSeek is young and smart, mostly from top Chinese schools, with brains in physics, math, and computer science. They learned AI in about six months by themselves! They use first principle thinking, which means they break down problems to the basics and build from there. This has helped them come up with cool new ways to do AI. 6. Changing AI for Good: DeepSeek is showing that AI can be cheaper and more open to everyone. They're changing how we think AI should be made and shared, which could shake up the whole AI world. So, as we watch DeepSeek, it's clear they're not just another player; they're changing the rules of the game. I predicted that this would be a make or break year for all the massive investments made in AI by American VC's. A few weeks later, DeepSeek happens! Watch the rest of my predictions in my 2025 outlook video . Link in replies #AIInnovation #DeepSeek #NVIDIA #OpenAI #TechDisruption

Dr Ola Brown

83,460 views • 1 year ago