Loading video...

Video Failed to Load

Go Home

Tried Pi Agent with DeepSeek V4 Flash. It’s really fast. DeepSeek lacks vision support, so I use a plugin to send visual tasks to Grok 4.5. Here’s a quick demo 👇

hqmank's profile picture

Kai

11,636 subscribers

26,299 views • 17 days ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Introducing a 100% free coding agent with DeepSeek v4 Pro Choose any model, all free: - DeepSeek v4 Pro/Flash - Kimi K2.6 - MiniMax M2.7 npm i -g freebuff
0:18

Introducing a 100% free coding agent with DeepSeek v4 Pro Choose any model, all free: - DeepSeek v4 Pro/Flash - Kimi K2.6 - MiniMax M2.7 npm i -g freebuff

James Grugett

473,103 views • 3 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

45,030 views • 12 days ago

245 tokens/sec on DeepSeek-V4-Flash and it’s only using 2 RTX 6000 Blackwell GPUs. tinycorp dropped a 2-GPU tinybox edition in honor of DeepSeek fully ready to expand to 4 GPUs later. The GPU middle class just got a serious upgrade.
0:17

245 tokens/sec on DeepSeek-V4-Flash and it’s only using 2 RTX 6000 Blackwell GPUs. tinycorp dropped a 2-GPU tinybox edition in honor of DeepSeek fully ready to expand to 4 GPUs later. The GPU middle class just got a serious upgrade.

Md Ismail Šojal 🕷️

16,148 views • 27 days ago

Codex can now run Deepseek-v4- flash! There's a catch though. Deepseek's official setup switches your entire codex over to them, so your GPT models stop showing up at all. This is exactly what Codex Router is for. It adds models to the list instead of replacing them, so sol, grok, kimi and deepseek all sit in the same picker and i just grab whichever one suits the job. Deepseek v4-flash is $0.28 per million output tokens. opus 4.8 is $25. same picker, 89x apart. Links in the comment. setup's in the video 👇
0:15

Codex can now run Deepseek-v4- flash! There's a catch though. Deepseek's official setup switches your entire codex over to them, so your GPT models stop showing up at all. This is exactly what Codex Router is for. It adds models to the list instead of replacing them, so sol, grok, kimi and deepseek all sit in the same picker and i just grab whichever one suits the job. Deepseek v4-flash is $0.28 per million output tokens. opus 4.8 is $25. same picker, 89x apart. Links in the comment. setup's in the video 👇

Ziwen

145,018 views • 28 days ago

Introducing I took the top 1k research papers of the last year, summarized them, and visualized them. Fun fact: all 1,000 papers cost a total of $4 to summarize with DeepSeek V4 Flash.
0:19

Introducing I took the top 1k research papers of the last year, summarized them, and visualized them. Fun fact: all 1,000 papers cost a total of $4 to summarize with DeepSeek V4 Flash.

Hassan

108,370 views • 9 days ago

asked Hermes Agent and OpenClaw to scrape our site and send a report. using DeepSeek V4 from our API. OpenClaw: 15k token, 2min 48 sec. wrote a bash script. Hermes: 36 token, 8 min 06 sec. wrote a SKILL.md. runs itself next time.
0:10

asked Hermes Agent and OpenClaw to scrape our site and send a report. using DeepSeek V4 from our API. OpenClaw: 15k token, 2min 48 sec. wrote a bash script. Hermes: 36 token, 8 min 06 sec. wrote a SKILL.md. runs itself next time.

GMI Cloud

49,650 views • 3 months 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

1,224,318 views • 1 year ago

MiniMax M3: Opus-level coding at DeepSeek pricing. On Terminal-Bench 2.1, it scores 66.0, only 0.1 behind Opus 4.7. I gave it a quick try on a few frontend tasks, and the output quality genuinely feels close to Opus 4.7.
0:13

MiniMax M3: Opus-level coding at DeepSeek pricing. On Terminal-Bench 2.1, it scores 66.0, only 0.1 behind Opus 4.7. I gave it a quick try on a few frontend tasks, and the output quality genuinely feels close to Opus 4.7.

Kai

25,730 views • 2 months ago

There's a FREE public endpoint for deepseek v4 flash 0731 😳 no account or no card needed, just a url victormustar from hugging face made it. openai-compatible chat completions. anyone can use it. what you get for $0: -82.7 terminal-bench (opus 4.8 is ~85) -swe-bench 54.4 — 7.3 before the update -1M context, thinking mode, tool calling -no signup, no key, no billing what this replaces: -Claude Opus 4.8: $15/M in, $75/M out -Cursor: $20/mo all for $0 how to set it up: 1. base url: 2. model: deepseek-ai/DeepSeek-V4-Flash-0731 3. api key: anything Works in Hermes, Cursor, OpenCode, Aider, Cline, Claude Code (via proxy), and any OpenAI tool Important: ~12 req/min per IP. shared box. be nice. use this before it gets popular
0:17

There's a FREE public endpoint for deepseek v4 flash 0731 😳 no account or no card needed, just a url victormustar from hugging face made it. openai-compatible chat completions. anyone can use it. what you get for $0: -82.7 terminal-bench (opus 4.8 is ~85) -swe-bench 54.4 — 7.3 before the update -1M context, thinking mode, tool calling -no signup, no key, no billing what this replaces: -Claude Opus 4.8: $15/M in, $75/M out -Cursor: $20/mo all for $0 how to set it up: 1. base url: 2. model: deepseek-ai/DeepSeek-V4-Flash-0731 3. api key: anything Works in Hermes, Cursor, OpenCode, Aider, Cline, Claude Code (via proxy), and any OpenAI tool Important: ~12 req/min per IP. shared box. be nice. use this before it gets popular

painn

118,003 views • 27 days ago

Elon acknowledged my post on how to use Grok 4.5 FREE getting the most out of it without a single dollar. I was able to come about the utility grok4.5 for this purpose with my hermes agent self improving ai brain
0:13

Elon acknowledged my post on how to use Grok 4.5 FREE getting the most out of it without a single dollar. I was able to come about the utility grok4.5 for this purpose with my hermes agent self improving ai brain

painn

29,603 views • 1 month ago

I gave the Unity CLI a try - and it's GOOD! Connected with Grok 4.5 via Grok Build - it handled the Editor by itself. Took the 2d platformer template and told Grok to give it a visual uplift, while keeping the game mechanics. Spriterrific for the character animations and Nano Banana 2 lite for the static sprites. I think this is a huge unlock for gamedevs, especially those who want to use Unity!
0:16

I gave the Unity CLI a try - and it's GOOD! Connected with Grok 4.5 via Grok Build - it handled the Editor by itself. Took the 2d platformer template and told Grok to give it a visual uplift, while keeping the game mechanics. Spriterrific for the character animations and Nano Banana 2 lite for the static sprites. I think this is a huge unlock for gamedevs, especially those who want to use Unity!

Chong-U

41,658 views • 1 month ago

Gemini 3 Flash is now available in MagicPath ⚡ From our earlier testing, it’s surprisingly strong at visual design for its size, and it’s fast! My recommendation: use it as your first-pass model to explore ideas, then switch to a bigger model for editing + refinements.
0:18

Gemini 3 Flash is now available in MagicPath ⚡ From our earlier testing, it’s surprisingly strong at visual design for its size, and it’s fast! My recommendation: use it as your first-pass model to explore ideas, then switch to a bigger model for editing + refinements.

Pietro Schirano

11,427 views • 8 months ago

Playing with the Knuth-Plass algorithm and I think it’s an interesting algorithm to visualize! Might write a complete visual article later, but here’s a quick comparison for now. It looks at the whole paragraph to find the breakpoints that produce the most uniform spacing. So unlike the greedy approach, the layout might shift when a new word is added. Note: I didn’t use pretext here; it’s a monospace font so calculating the word widths is quite easy. will try pretext and try other fonts next
0:18

Playing with the Knuth-Plass algorithm and I think it’s an interesting algorithm to visualize! Might write a complete visual article later, but here’s a quick comparison for now. It looks at the whole paragraph to find the breakpoints that produce the most uniform spacing. So unlike the greedy approach, the layout might shift when a new word is added. Note: I didn’t use pretext here; it’s a monospace font so calculating the word widths is quite easy. will try pretext and try other fonts next

Damar

173,170 views • 4 months ago

REALLY cool effect for creating lyric videos super fast with AI: 1. made a quick demo track with ElevenLabs 2. nano banana workflow that generates the "cut out ransom style" text based on the lyrics 3. used my transition agent to morph between them Voilà, all in 5 min:
0:13

REALLY cool effect for creating lyric videos super fast with AI: 1. made a quick demo track with ElevenLabs 2. nano banana workflow that generates the "cut out ransom style" text based on the lyrics 3. used my transition agent to morph between them Voilà, all in 5 min:

fabian

16,875 views • 1 year ago

Since subscribers can now use their existing Grok credentials directly within the Hermes xai shipped grok-via-oauth for hermes. your grok sub works inside the agent now. so i hooked icarus up to it. when hermes finds a thread worth saving, it lands in my obsidian vault as a note. handle. pages, topic pages, backlinks. graph view fills itself out. icarus plugin for hermes agents is why my agent doesn't forget. memory is just markdown in a folder. you can read it, grep it, edit it. Congrats to Teknium 🪽 and Nous Research
0:17

Since subscribers can now use their existing Grok credentials directly within the Hermes xai shipped grok-via-oauth for hermes. your grok sub works inside the agent now. so i hooked icarus up to it. when hermes finds a thread worth saving, it lands in my obsidian vault as a note. handle. pages, topic pages, backlinks. graph view fills itself out. icarus plugin for hermes agents is why my agent doesn't forget. memory is just markdown in a folder. you can read it, grep it, edit it. Congrats to Teknium 🪽 and Nous Research

Icarus

14,610 views • 3 months ago

China is literally on 🔥 Baidu from China has launched ERNIE 4.5 and ERNIE X1 and it’s freaking cheap . Here is everything you need to know. ERNIE 4.5 - Native multimodal and Outperforms GPT 4.5 in multiple benchmarks at just 1% of GPT 4.5 price - OpenAI GPT 4.5 – Input: $75 / 1M tokens, Output: $150 / 1M tokens; - ERNIE 4.5 – Input: $0.55 / 1M tokens, Output: $2.20 / 1M tokens ERNIE X1 - A deep thinking reasoning model with multimodal capabilities on par with DeepSeek R1 at only half the price See it in action and check out the pricing details👇 📹 source : yiyan[.]baidu[.]com 1/6 ERNIE 4.5 is a multimodal which can take Audio files as well.
0:13

China is literally on 🔥 Baidu from China has launched ERNIE 4.5 and ERNIE X1 and it’s freaking cheap . Here is everything you need to know. ERNIE 4.5 - Native multimodal and Outperforms GPT 4.5 in multiple benchmarks at just 1% of GPT 4.5 price - OpenAI GPT 4.5 – Input: $75 / 1M tokens, Output: $150 / 1M tokens; - ERNIE 4.5 – Input: $0.55 / 1M tokens, Output: $2.20 / 1M tokens ERNIE X1 - A deep thinking reasoning model with multimodal capabilities on par with DeepSeek R1 at only half the price See it in action and check out the pricing details👇 📹 source : yiyan[.]baidu[.]com 1/6 ERNIE 4.5 is a multimodal which can take Audio files as well.

AshutoshShrivastava

324,324 views • 1 year ago

Prepared a quick ogbono soup with onugbu (bitter leaf); NEPA didn't bring light, so I had to use touch. Yummy-yummy...😀
0:17

Prepared a quick ogbono soup with onugbu (bitter leaf); NEPA didn't bring light, so I had to use touch. Yummy-yummy...😀

Daniel Regha

595,728 views • 3 years ago

Everyone keeps calling the Apple Vision Pro's UI "Magical" I NEEDED to try it out for myself. The Quest Pro is capable of it so I made a demo using eye tracking and hand tracking replicating the Apple UI. Its really good. APK for everyone to try the "Vision UI Experience" soon, Video with my takeaways Sooner.
0:13

Everyone keeps calling the Apple Vision Pro's UI "Magical" I NEEDED to try it out for myself. The Quest Pro is capable of it so I made a demo using eye tracking and hand tracking replicating the Apple UI. Its really good. APK for everyone to try the "Vision UI Experience" soon, Video with my takeaways Sooner.

𝙏𝙝𝙧𝙞𝙡𝙡

240,227 views • 3 years ago