Loading video...

Video Failed to Load

Go Home

🚨 DeepSeek now has its own Codex-style desktop app: DeepSeek Harness, in Preview. DeepSeek hasn't announced it, but the download links leaked. I installed it and recorded a quick walkthrough, video below. The UI is clean. On the Plugins page you'll find Agent Teams, subagents, auto permission review, local...

aibuilderclub_'s profile picture

AI Builder Club

6,634 subscribers

63,246 views • 1 month ago •via X (Twitter)

Science & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

DeepSeek Harness is an agent harness where every component is a plugin, built on Cordis for spatiotemporal composability. Run it via `npx deepseek-ai/dsh web` to get a local Web UI at port 3080. Explore it here:
0:10

DeepSeek Harness is an agent harness where every component is a plugin, built on Cordis for spatiotemporal composability. Run it via `npx deepseek-ai/dsh web` to get a local Web UI at port 3080. Explore it here:

GitHub Projects Community

19,201 views • 2 months ago

"You've reached your rate limit. Try again after 7pm." every. fucking. day. $200/month - $2,400 a year - for Codex. then i opened the DeepSeek pricing page. Someone made DeepSeek a native subagent for Codex. Heavy work goes there, light stays on GPT-5. Same code out the other end. 35x cheaper. DeepSeek V4 Flash lives on its own API key, not on my Plus quota. One command: npx skills add oil-oil/codex-deepseek-subagent -g -y Restart Codex, tell it "set up DeepSeek as a subagent", done. First day in a month I'm still working in the evening instead of hitting the wall. save this before your next rate-limit ↓
0:16

"You've reached your rate limit. Try again after 7pm." every. fucking. day. $200/month - $2,400 a year - for Codex. then i opened the DeepSeek pricing page. Someone made DeepSeek a native subagent for Codex. Heavy work goes there, light stays on GPT-5. Same code out the other end. 35x cheaper. DeepSeek V4 Flash lives on its own API key, not on my Plus quota. One command: npx skills add oil-oil/codex-deepseek-subagent -g -y Restart Codex, tell it "set up DeepSeek as a subagent", done. First day in a month I'm still working in the evening instead of hitting the wall. save this before your next rate-limit ↓

Granite

72,623 views • 2 months ago

Happy Friday! We're giving you a $5 coupon to build on Ori Harness this weekend Run your favorite agent CLI - Claude Code, Codex, DeepSeek, etc - on 500+ models on OpenRouter Save 50 to 75% on OpenAI 5.6 Sol and DeepSeek Flash 3.7 Redeem below:
0:13

Happy Friday! We're giving you a $5 coupon to build on Ori Harness this weekend Run your favorite agent CLI - Claude Code, Codex, DeepSeek, etc - on 500+ models on OpenRouter Save 50 to 75% on OpenAI 5.6 Sol and DeepSeek Flash 3.7 Redeem below:

OpenRouter

32,939 views • 2 months ago

this is the best trick to maximum usage limits on chatgpt codex codex's best kept secret is that your main agent doesn't have to do everything... custom agents are just files in ~/.codex/agents, and one file gives you a second worker on deepseek v4 flash > create ~/.codex/agents/deepseek-worker.toml > set model = "opencode-go/deepseek-v4-flash" with model_reasoning_effort = "max" > keep it bounded: one task packet, no scope creep, report back ```toml name = "deepseek_worker" description = "bounded implementation, testing, and cleanup on deepseek v4 flash" model = "opencode-go/deepseek-v4-flash" model_reasoning_effort = "max" ``` then @ deepseek_worker in the composer... your root agent plans while the worker ships the implementation planning on the main model, execution on the flash lane... that's the whole trick (we run this exact file, last i checked it keeps the heavy turns off the main thread)
0:18

this is the best trick to maximum usage limits on chatgpt codex codex's best kept secret is that your main agent doesn't have to do everything... custom agents are just files in ~/.codex/agents, and one file gives you a second worker on deepseek v4 flash > create ~/.codex/agents/deepseek-worker.toml > set model = "opencode-go/deepseek-v4-flash" with model_reasoning_effort = "max" > keep it bounded: one task packet, no scope creep, report back ```toml name = "deepseek_worker" description = "bounded implementation, testing, and cleanup on deepseek v4 flash" model = "opencode-go/deepseek-v4-flash" model_reasoning_effort = "max" ``` then @ deepseek_worker in the composer... your root agent plans while the worker ships the implementation planning on the main model, execution on the flash lane... that's the whole trick (we run this exact file, last i checked it keeps the heavy turns off the main thread)

Avid

50,262 views • 2 months ago

Today, we are launching Ori DeepSeek Harness Run DeepSeek Harness on your whole OpenRouter catalog. One setup command wires your credentials, 500+ models, and routing into your own harness home $ curl -fsSL | bash $ ori deepseek
0:14

Today, we are launching Ori DeepSeek Harness Run DeepSeek Harness on your whole OpenRouter catalog. One setup command wires your credentials, 500+ models, and routing into your own harness home $ curl -fsSL | bash $ ori deepseek

OpenRouter

54,366 views • 2 months ago

We just launched support for DeepSeek (DeepSeek) R1 and V3 in Agent Mode! - Switch to Agent Mode by pressing CMD-I - Click on the model name in the prompt Hosted by Fireworks in the US.
0:16

We just launched support for DeepSeek (DeepSeek) R1 and V3 in Agent Mode! - Switch to Agent Mode by pressing CMD-I - Click on the model name in the prompt Hosted by Fireworks in the US.

Warp

14,175 views • 1 year ago

deepseek solved a rubik's cube in 0.367 seconds every deepseek v4.1 flash vs opus 5.5 comparison this week judged the same thing - how it looks so i gave both a test you can't fake. one scrambled cube, one prompt, solve it on camera 1 move that's all deepseek needed to call it solved -> same scramble, same rules, every move locked at 0.4s -> opus 5.5: 19 moves, 7.55s, actually solved -> deepseek wrote its own two-phase solver from scratch - genuinely ambitious -> a bug in its cube math made it "solve" a different cube -> its own self-check failed - it still logged "verified solved: true" -> cost: deepseek $0.20, opus $0.81 -> asked for stats, it claimed 20 moves and 7.95s - which matches the scramble played backwards, the one thing the prompt banned the part that got me - i almost posted deepseek's numbers as-is. only caught it because i recorded the file myself instead of trusting its summary everyone's comparing renders. nobody's checking if the thing works
0:11

deepseek solved a rubik's cube in 0.367 seconds every deepseek v4.1 flash vs opus 5.5 comparison this week judged the same thing - how it looks so i gave both a test you can't fake. one scrambled cube, one prompt, solve it on camera 1 move that's all deepseek needed to call it solved -> same scramble, same rules, every move locked at 0.4s -> opus 5.5: 19 moves, 7.55s, actually solved -> deepseek wrote its own two-phase solver from scratch - genuinely ambitious -> a bug in its cube math made it "solve" a different cube -> its own self-check failed - it still logged "verified solved: true" -> cost: deepseek $0.20, opus $0.81 -> asked for stats, it claimed 20 moves and 7.95s - which matches the scramble played backwards, the one thing the prompt banned the part that got me - i almost posted deepseek's numbers as-is. only caught it because i recorded the file myself instead of trusting its summary everyone's comparing renders. nobody's checking if the thing works

Semichenko

30,268 views • 18 days ago

DeepSeek DeepSeek is now live on Heurist. Open source AI just reached new heights. Access DeepSeek-R1 and DeepSeek-V3 for smarter inference at a fraction of cost. Try it via Heurist API or explore on Pondera.
0:19

DeepSeek DeepSeek is now live on Heurist. Open source AI just reached new heights. Access DeepSeek-R1 and DeepSeek-V3 for smarter inference at a fraction of cost. Try it via Heurist API or explore on Pondera.

Heurist

25,673 views • 1 year ago

🔥 Use DeepSeek-v4.1-flash for free in Orca Here's how: 1. Open OpenCode via terminal or the new Chat UI 2. Select "Deepseek-v4.1-flash-free" from the model picker 💡 Pro tip: "Deepseek-v4.1-flash-free" is 200k context only. Use it along side Codex / Claude Code to access more heavy-duty models
0:10

🔥 Use DeepSeek-v4.1-flash for free in Orca Here's how: 1. Open OpenCode via terminal or the new Chat UI 2. Select "Deepseek-v4.1-flash-free" from the model picker 💡 Pro tip: "Deepseek-v4.1-flash-free" is 200k context only. Use it along side Codex / Claude Code to access more heavy-duty models

Orca

37,253 views • 21 days ago

Deepseek R1 is so cool I had to build a custom parser for it. TypingMind now can show "thinking" text in its own collapsible block.
0:19

Deepseek R1 is so cool I had to build a custom parser for it. TypingMind now can show "thinking" text in its own collapsible block.

Tony Dinh

94,611 views • 1 year ago

Local models on the left. Cloud models on the right. I asked Qwen-flash-next, DeepSeek-v4.1, Fable-5.1 and Astra-6 to build an interactive volcanic island with flowing lava and boats that flee. In my opinion deepseek was the winner, and fable the disappointment Try each island yourself: Qwen · Mac Studio DeepSeek · 4× DGX Spark Fable · Cloud Astra · Cloud
0:17

Local models on the left. Cloud models on the right. I asked Qwen-flash-next, DeepSeek-v4.1, Fable-5.1 and Astra-6 to build an interactive volcanic island with flowing lava and boats that flee. In my opinion deepseek was the winner, and fable the disappointment Try each island yourself: Qwen · Mac Studio DeepSeek · 4× DGX Spark Fable · Cloud Astra · Cloud

Wësche

15,234 views • 1 month ago

DeepSeek R1 is *the* best model available right now. It's at the level of o1, but you can use it for free, and it's much faster. A huge leap forward that nobody saw coming. No wonder so many people are throwing tantrums online trying to discredit the Chinese students who built this. You can use DeepSeek in Visual Studio Code right now: 1. Install the Qodo Gen AI extension 2. Select DeepSeek R1 from their list of models The Qodo team is hosting DeepSeek on their servers, so none of your data will go to China. I've been building a Tetris game using DeepSeek, and this is the most impressive model I've seen so far.
0:17

DeepSeek R1 is *the* best model available right now. It's at the level of o1, but you can use it for free, and it's much faster. A huge leap forward that nobody saw coming. No wonder so many people are throwing tantrums online trying to discredit the Chinese students who built this. You can use DeepSeek in Visual Studio Code right now: 1. Install the Qodo Gen AI extension 2. Select DeepSeek R1 from their list of models The Qodo team is hosting DeepSeek on their servers, so none of your data will go to China. I've been building a Tetris game using DeepSeek, and this is the most impressive model I've seen so far.

Santiago

1,224,606 views • 1 year ago

BOOM 🚨: Tencent’s Hunyuan Turbo S just landed in the Top 8 globally on Chatbot Arena and is now #2 in China, just behind DeepSeek. Even Google ex-CEO Eric Schmidt says China had no foundation models two years ago — now it has three: DeepSeek, Qwen, Hunyuan — on par with OpenAI’s O.1. At #GoogleIO, all three scored high on the global leaderboard like #DeepSeek, #Qwen, #Hunyuan Tencent Hy isn’t just racing — it’s rewriting the leaderboard. #HunyuanTurboS #TencentAI #LLM #AIRevolution
0:18

BOOM 🚨: Tencent’s Hunyuan Turbo S just landed in the Top 8 globally on Chatbot Arena and is now #2 in China, just behind DeepSeek. Even Google ex-CEO Eric Schmidt says China had no foundation models two years ago — now it has three: DeepSeek, Qwen, Hunyuan — on par with OpenAI’s O.1. At #GoogleIO, all three scored high on the global leaderboard like #DeepSeek, #Qwen, #Hunyuan Tencent Hy isn’t just racing — it’s rewriting the leaderboard. #HunyuanTurboS #TencentAI #LLM #AIRevolution

Emily Watson | AI Tools & Tech News

24,853 views • 1 year ago

DeepSeek AI models are now in the GamerHash App! Powerful, fast, completely private and secure, fully local with no online connection required - available and running on your personal GPU 🚀
0:13

DeepSeek AI models are now in the GamerHash App! Powerful, fast, completely private and secure, fully local with no online connection required - available and running on your personal GPU 🚀

GamerHash AI

30,448 views • 1 year ago

Mika is now open source: a real phone agent that runs on your Android phone. Tell it what you want, and it gets it done in your apps and on the web, on a hidden background screen while you keep using your phone. No root, no computer, your own logins. In the videos, asked in plain English: • Amazon: find a USB-C charger under $30 with 4.5★+, add it to the cart, stop before checkout • Google Flights: cheapest nonstop SFO → New York next Friday • Hacker News: top 5 stories with points, in 22 seconds What's inside: • Operates any app on your phone, no per-app setup • Built-in browser for search, filters and batch work • Floating capsule you can call up from any app • Local Linux sandbox for Python and your files Bring your own model key (OpenAI, Anthropic, Gemini, DeepSeek, Qwen and more). Apache-2.0. Star it, download the APK, or build it with me:
0:54

Mika is now open source: a real phone agent that runs on your Android phone. Tell it what you want, and it gets it done in your apps and on the web, on a hidden background screen while you keep using your phone. No root, no computer, your own logins. In the videos, asked in plain English: • Amazon: find a USB-C charger under $30 with 4.5★+, add it to the cart, stop before checkout • Google Flights: cheapest nonstop SFO → New York next Friday • Hacker News: top 5 stories with points, in 22 seconds What's inside: • Operates any app on your phone, no per-app setup • Built-in browser for search, filters and batch work • Floating capsule you can call up from any app • Local Linux sandbox for Python and your files Bring your own model key (OpenAI, Anthropic, Gemini, DeepSeek, Qwen and more). Apache-2.0. Star it, download the APK, or build it with me:

王赞

97,357 views • 6 days ago

🚨#BREAKING: The U.S. Navy has banned its service members from using the Chinese AI chatbot DeepSeek, citing security and ethical concerns.
0:13

🚨#BREAKING: The U.S. Navy has banned its service members from using the Chinese AI chatbot DeepSeek, citing security and ethical concerns.

R A W S A L E R T S

437,541 views • 1 year ago

deepseek v4 pro is basically free right now 😳 teamorouter is offering deepseek v4 pro at almost no cost you can also use deepseek v4 flash for free what you get: - deepseek v4 pro free - deepseek v4 flash free - 1M context - openai compatible api - no subscription - credits never expire why this is worth checking: > v4 pro is currently listed at $0 input and output > flash is also available at $0 > works with claude code, codex and other tools > one api gives you access to multiple models getting started: 1. go to 2. create your account 3. open the dashboard 4. create your api key base url: 5. add it to your ai coding tool 6. select deepseek-v4-pro-free worth testing while it’s available
0:16

deepseek v4 pro is basically free right now 😳 teamorouter is offering deepseek v4 pro at almost no cost you can also use deepseek v4 flash for free what you get: - deepseek v4 pro free - deepseek v4 flash free - 1M context - openai compatible api - no subscription - credits never expire why this is worth checking: > v4 pro is currently listed at $0 input and output > flash is also available at $0 > works with claude code, codex and other tools > one api gives you access to multiple models getting started: 1. go to 2. create your account 3. open the dashboard 4. create your api key base url: 5. add it to your ai coding tool 6. select deepseek-v4-pro-free worth testing while it’s available

K2S

40,407 views • 2 months ago