Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

This is probably my most important post about DeepSeek V4 Flash. Do NOT judge this model after testing only one harness. Pi, Claude Code, and OpenCode produced dramatically different results—and OpenCode completely changed my verdict. You really need to read the details below.

OmedVibeCodes's profile picture

OmedTheVibeCoder

1,274 subscribers

67,431 Aufrufe • vor 12 Tagen •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

You need to read this. Again. Qwen 3.8 Max Preview still performs badly in OpenCode and Qwen Code. Switch to the Claude Code harness, and it suddenly becomes dramatically better. This is reproducible. The harness difference is real.
0:30

You need to read this. Again. Qwen 3.8 Max Preview still performs badly in OpenCode and Qwen Code. Switch to the Claude Code harness, and it suddenly becomes dramatically better. This is reproducible. The harness difference is real.

OmedTheVibeCoder

18,593 Aufrufe • vor 21 Tagen

DeepSeek V4 Flash completely failed this test. Compared to Opus 4.8, GPT-5.6 Sol, Kimi K3, and the other current top models, it’s honestly not good. The gap is massive. Against Luna, however, it performs similarly well. Both have different strengths and weaknesses, so I still need to test them more. The weird part: the Pi harness performed worse than OpenCode for DeepSeek. More tests are coming, guys. Don’t worry
0:38

DeepSeek V4 Flash completely failed this test. Compared to Opus 4.8, GPT-5.6 Sol, Kimi K3, and the other current top models, it’s honestly not good. The gap is massive. Against Luna, however, it performs similarly well. Both have different strengths and weaknesses, so I still need to test them more. The weird part: the Pi harness performed worse than OpenCode for DeepSeek. More tests are coming, guys. Don’t worry

OmedTheVibeCoder

25,980 Aufrufe • vor 12 Tagen

Okay… DeepSeek V4 Flash actually COOKED 😭 With OpenCode, I’d place it around GPT-5.6 Terra Max—and definitely above Luna Max in this test. Almost unlimited usage for around €9, by the way. This model is a MASSIVE success. Just don’t use the wrong harness.
0:32

Okay… DeepSeek V4 Flash actually COOKED 😭 With OpenCode, I’d place it around GPT-5.6 Terra Max—and definitely above Luna Max in this test. Almost unlimited usage for around €9, by the way. This model is a MASSIVE success. Just don’t use the wrong harness.

OmedTheVibeCoder

35,417 Aufrufe • vor 12 Tagen

I've loved using Claude Code, Codex, and OpenCode since the very beginning. But a few weeks ago, I tried out pi to see what all the hype is about. And now, it's my daily driver. I'm in full control. No unexpected changes to the harness. Check out pi in about 6 minutes.
6:09

I've loved using Claude Code, Codex, and OpenCode since the very beginning. But a few weeks ago, I tried out pi to see what all the hype is about. And now, it's my daily driver. I'm in full control. No unexpected changes to the harness. Check out pi in about 6 minutes.

Jilles Soeters

56,233 Aufrufe • vor 1 Monat

Deepseek-V4-Flash helping me setup Nvidia's Dynamo for disaggregated inference. I have really gotten this model to be a daily driver now. It's really strong at agentic workflows and a decent programmer. For all my side stuff, it's local deepseek now Claude sub cancelled wdyt
0:41

Deepseek-V4-Flash helping me setup Nvidia's Dynamo for disaggregated inference. I have really gotten this model to be a daily driver now. It's really strong at agentic workflows and a decent programmer. For all my side stuff, it's local deepseek now Claude sub cancelled wdyt

0xSero

24,469 Aufrufe • vor 3 Monaten

DeepSeek V4 Flash 0731 in Hermes Agent and one prompt, took 32 minutes and cost 0.07$, this model is so cheap to the point where 2 dollars can last you a full day.
1:03

DeepSeek V4 Flash 0731 in Hermes Agent and one prompt, took 32 minutes and cost 0.07$, this model is so cheap to the point where 2 dollars can last you a full day.

Elshayib

673,176 Aufrufe • vor 13 Tagen

You need to save this chart. What do you notice here? This is probably the most important segment of my show today 👇
1:50

You need to save this chart. What do you notice here? This is probably the most important segment of my show today 👇

Dan Bongino

100,535 Aufrufe • vor 2 Monaten

Anthropic CEO: "Software is going to become cheap, maybe essentially free." this 2-minute clip is the most important thing I watched this month. ↓ Save this before everyone copies the playbook Not only the people who refuse AI, but also those who think signing up for Claude counts as using it. the part nobody wanted to hear: > you don't need a co-founder who codes > you don't need $50K for an MVP > you don't need 6 months of development > you need Claude and one weekend most people will watch this and worry about their job. A few will open Claude this weekend and vibe code their first product. I used Claude to build my first product. No code. No cost. No CS degree. I did exactly this and documented the whole process step by step. Full guide in the article below.
0:52

Anthropic CEO: "Software is going to become cheap, maybe essentially free." this 2-minute clip is the most important thing I watched this month. ↓ Save this before everyone copies the playbook Not only the people who refuse AI, but also those who think signing up for Claude counts as using it. the part nobody wanted to hear: > you don't need a co-founder who codes > you don't need $50K for an MVP > you don't need 6 months of development > you need Claude and one weekend most people will watch this and worry about their job. A few will open Claude this weekend and vibe code their first product. I used Claude to build my first product. No code. No cost. No CS degree. I did exactly this and documented the whole process step by step. Full guide in the article below.

Khairallah AL-Awady

53,454 Aufrufe • vor 2 Monaten

Let's be honest Claude Code was not working good with local LLMs. So, I Tried using OpenCode with LM Studio using Qwen 3.5 9B model on my RTX 5080 GPU. It's very usable and much faster than Claude Code. I'm actually planning to use this setup to build an entire vibe coded SaaS
2:31

Let's be honest Claude Code was not working good with local LLMs. So, I Tried using OpenCode with LM Studio using Qwen 3.5 9B model on my RTX 5080 GPU. It's very usable and much faster than Claude Code. I'm actually planning to use this setup to build an entire vibe coded SaaS

Tushar Verma

137,536 Aufrufe • vor 5 Monaten

Boris Cherny, Head of Claude Code at Anthropic: "I do not prompt Claude anymore. I have loops running that prompt Claude. My job is to write loops." The person who built the most used AI coding tool stopped prompting entirely. Most people using it every day are still typing one request at a time. This Github repo changes that. ↳ Seven production loop patterns with real token cost estimates ↳ CLI that scaffolds your entire loop in five minutes ↳ Starters for Grok, Claude Code, Codex, and Opencode The repo gives you the framework. My article covers the mental shift that makes it actually work.
0:31

Boris Cherny, Head of Claude Code at Anthropic: "I do not prompt Claude anymore. I have loops running that prompt Claude. My job is to write loops." The person who built the most used AI coding tool stopped prompting entirely. Most people using it every day are still typing one request at a time. This Github repo changes that. ↳ Seven production loop patterns with real token cost estimates ↳ CLI that scaffolds your entire loop in five minutes ↳ Starters for Grok, Claude Code, Codex, and Opencode The repo gives you the framework. My article covers the mental shift that makes it actually work.

Kanika

20,576 Aufrufe • vor 19 Tagen

I paired Cloudflare OS with self hosted deepseek-v4-flash and the result is freakin amazing Imagine running this setup inside DGX spark, you get fully private work companion solving all your work stuff The thing about this type of software is it already have a good harness and it probably can work out of the box with every open weight model Cant wait for the future
0:38

I paired Cloudflare OS with self hosted deepseek-v4-flash and the result is freakin amazing Imagine running this setup inside DGX spark, you get fully private work companion solving all your work stuff The thing about this type of software is it already have a good harness and it probably can work out of the box with every open weight model Cant wait for the future

Farhan Helmy

56,987 Aufrufe • vor 8 Tagen

Your AI sucks. And it's not the model. It's you. "Make it better" isn't a prompt, it's a guessing game. I changed one step in my process and the output quality completely flipped. Same ideas, same models, totally different results.
0:42

Your AI sucks. And it's not the model. It's you. "Make it better" isn't a prompt, it's a guessing game. I changed one step in my process and the output quality completely flipped. Same ideas, same models, totally different results.

Flick

322,001 Aufrufe • vor 27 Tagen

This is why you want an execution layer share your tools, auth and approvals across all agents you use Check out me adding the Axiom MCP server, authing to it, and calling it from Claude Code and OpenCode in under a minute - all locally on my computer `npm i -g executor`
0:57

This is why you want an execution layer share your tools, auth and approvals across all agents you use Check out me adding the Axiom MCP server, authing to it, and calling it from Claude Code and OpenCode in under a minute - all locally on my computer `npm i -g executor`

Rhys

29,977 Aufrufe • vor 5 Monaten

you guys keep waiting for Codex ios app, here im using this app to run multiple agents in parallel from my phone using my exisiting ai subscriptions and its 100% free and opensource you can use: > Codex > Claude Code > Opencode > and any CLI agent and thats not it, theres more: > Browser to run localhost with devtools > Code Editor with file explorer > Terminal > Git > Port forwarding and manage ports from phone > API testing client (like Postman) and many more... links in the replies 👀
1:13

you guys keep waiting for Codex ios app, here im using this app to run multiple agents in parallel from my phone using my exisiting ai subscriptions and its 100% free and opensource you can use: > Codex > Claude Code > Opencode > and any CLI agent and thats not it, theres more: > Browser to run localhost with devtools > Code Editor with file explorer > Terminal > Git > Port forwarding and manage ports from phone > API testing client (like Postman) and many more... links in the replies 👀

Gruz

25,317 Aufrufe • vor 3 Monaten

this is insane this guy dropped claude design, but open source with a real interactive editor works with Kimi.ai and DeepSeek the post already went viral with 276k views you don't need to pay that $200 for sure claude code -> omo claude design -> slides-grab
0:29

this is insane this guy dropped claude design, but open source with a real interactive editor works with Kimi.ai and DeepSeek the post already went viral with 276k views you don't need to pay that $200 for sure claude code -> omo claude design -> slides-grab

Sisyphus Labs

22,758 Aufrufe • vor 2 Monaten

I built a complex history feature for my Figma to Code plugin in 3 prompts. This is a 30-min tutorial using Claude Code. The difference in code generation between gpt-4o, Claude 3.5 and 3.7 is insane. 3.7 produces near-perfect results and is far more consistent. It's really a designer's best friend, not missing details from the design, like adaptive layout, outlines, spacing, etc. It seems like the new model has great taste now.
30:38

I built a complex history feature for my Figma to Code plugin in 3 prompts. This is a 30-min tutorial using Claude Code. The difference in code generation between gpt-4o, Claude 3.5 and 3.7 is insane. 3.7 produces near-perfect results and is far more consistent. It's really a designer's best friend, not missing details from the design, like adaptive layout, outlines, spacing, etc. It seems like the new model has great taste now.

Meng To

32,475 Aufrufe • vor 1 Jahr

ANTHROPIC JUST LOST 20,000 CLAUDE CODE USERS TO ONE GITHUB REPO. 20,000 devs. 26k stars. 4,000 forks. 10 free models. COMPLETELY FREE. Bookmark this before Anthropic notices. Your Claude Code bill will start working differently. It reroutes Claude Code to DeepSeek, Kimi, and 8 more same CLI, different model behind it. 5 min setup. $200/mo saved. 0 downgrade on small tasks. swap the endpoint in your config today. Link below. Claude Code → Endpoint swap → Free models → No bill → Money
0:28

ANTHROPIC JUST LOST 20,000 CLAUDE CODE USERS TO ONE GITHUB REPO. 20,000 devs. 26k stars. 4,000 forks. 10 free models. COMPLETELY FREE. Bookmark this before Anthropic notices. Your Claude Code bill will start working differently. It reroutes Claude Code to DeepSeek, Kimi, and 8 more same CLI, different model behind it. 5 min setup. $200/mo saved. 0 downgrade on small tasks. swap the endpoint in your config today. Link below. Claude Code → Endpoint swap → Free models → No bill → Money

AdiiX

417,501 Aufrufe • vor 29 Tagen

Boris has Claude Code loops running on cron all day - One babysits his PRs and fixes CI - Another keeps CI healthy - Another pulls Twitter feedback every 30 min and clusters it His Claude Code setup is simple and pretty close to mine That's what I like about Claude Code. Hundreds of options, but the simplest setup just works, you probably don't need more than that And since one of those loops reads Twitter every 30 min, Boris Cherny (or his Claude on cron) is reading this post whether he wants to or not 😅
1:16

Boris has Claude Code loops running on cron all day - One babysits his PRs and fixes CI - Another keeps CI healthy - Another pulls Twitter feedback every 30 min and clusters it His Claude Code setup is simple and pretty close to mine That's what I like about Claude Code. Hundreds of options, but the simplest setup just works, you probably don't need more than that And since one of those loops reads Twitter every 30 min, Boris Cherny (or his Claude on cron) is reading this post whether he wants to or not 😅

Daniel San

121,354 Aufrufe • vor 3 Monaten

NVIDIA is giving away free access to 130+ AI models for a full year > most people building AI agents are paying $50-200/month for API access NVIDIA just made that argument irrelevant models you get: MiniMax M2.7, GLM 5.1, Kimi 2.5, DeepSeek-v4-flash, GPT-OSS-120B and 110+ more setup: > step 1 - get your free key > go to > register -> bind phone -> copy API key > step 2 - add to Hermes agent > open Settings -> Model Provider -> Custom base_url = " api_key = "nvapi-xxxxxxxxxxxxxxxxxxxx" > step 3 - pick a model model = "minimaxai/minimax-m2.7" model = "zhipuai/glm-5.1" model = "moonshot-ai/kimi-2.5" model = "deepseek-ai/deepseek-v4-flash" model = "nvidia/nemotron-3-ultra-550b-a55b" > Hermes already has NVIDIA set as default base_url > paste the key and you're running instantly > works the same in Cursor and OpenCode > cost: $0 > limit: 40 req/min > expires: 1 year while everyone is paying for API access, this is sitting there for free
0:38

NVIDIA is giving away free access to 130+ AI models for a full year > most people building AI agents are paying $50-200/month for API access NVIDIA just made that argument irrelevant models you get: MiniMax M2.7, GLM 5.1, Kimi 2.5, DeepSeek-v4-flash, GPT-OSS-120B and 110+ more setup: > step 1 - get your free key > go to > register -> bind phone -> copy API key > step 2 - add to Hermes agent > open Settings -> Model Provider -> Custom base_url = " api_key = "nvapi-xxxxxxxxxxxxxxxxxxxx" > step 3 - pick a model model = "minimaxai/minimax-m2.7" model = "zhipuai/glm-5.1" model = "moonshot-ai/kimi-2.5" model = "deepseek-ai/deepseek-v4-flash" model = "nvidia/nemotron-3-ultra-550b-a55b" > Hermes already has NVIDIA set as default base_url > paste the key and you're running instantly > works the same in Cursor and OpenCode > cost: $0 > limit: 40 req/min > expires: 1 year while everyone is paying for API access, this is sitting there for free

Mr. Buzzoni

195,973 Aufrufe • vor 2 Monaten

let me save you 3 hours of head scratching. if you're running local models like Qwen3.5-35B-A3B through Claude Code via llama.cpp's Anthropic endpoint, the chain will break every 3 to 5 minutes. tool call fails. flow stops. you reprompt. it recovers. 2 minutes later it stops again. the model is fine. the harness chokes on local inference latency. switch to OpenCode. same localhost endpoint. same model. same GPU. the chain doesn't break. the tradeoff: OpenCode sometimes loops. the model forgets what it already read and repeats the same tool call. but a loop you can interrupt. a broken chain kills your momentum and you start over. watch both side by side. proprietary agent vs open source agent. same 3B model. different failure modes. pick your poison.
0:19

let me save you 3 hours of head scratching. if you're running local models like Qwen3.5-35B-A3B through Claude Code via llama.cpp's Anthropic endpoint, the chain will break every 3 to 5 minutes. tool call fails. flow stops. you reprompt. it recovers. 2 minutes later it stops again. the model is fine. the harness chokes on local inference latency. switch to OpenCode. same localhost endpoint. same model. same GPU. the chain doesn't break. the tradeoff: OpenCode sometimes loops. the model forgets what it already read and repeats the same tool call. but a loop you can interrupt. a broken chain kills your momentum and you start over. watch both side by side. proprietary agent vs open source agent. same 3B model. different failure modes. pick your poison.

Sudo su

72,538 Aufrufe • vor 5 Monaten