Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

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.

OmedVibeCodes's profile picture

OmedTheVibeCoder

1,308 subscribers

18,655 Aufrufe • vor 2 Monaten •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

This completely changes how I look at AI benchmarks. Qwen 3.8 Max Preview felt nearly unusable in OpenCode and Qwen Code. With the Claude Code harness, it suddenly came surprisingly close to Kimi K3 and Fable 5. Same model. Same task. Different harness. Wildly different result. How is this even possible?
0:36

This completely changes how I look at AI benchmarks. Qwen 3.8 Max Preview felt nearly unusable in OpenCode and Qwen Code. With the Claude Code harness, it suddenly came surprisingly close to Kimi K3 and Fable 5. Same model. Same task. Different harness. Wildly different result. How is this even possible?

OmedTheVibeCoder

30,223 Aufrufe • vor 2 Monaten

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.
0:24

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.

OmedTheVibeCoder

68,744 Aufrufe • vor 1 Monat

Qwen 3.8 Preview is quietly catching Kimi K3 on frontend + game design.And this is just the preview. Full 3.8 is going to be a beast. We tested Qwen 3.8 Preview against Kimi K3 on 3D modeling and animation. Ran both through the same 3 prompts. Both on Max effort. Qwen 3.8 Preview was dramatically faster across the board, 3-4x quicker on every test. Kimi K3 needed 2 hours on the final scene; Qwen wrapped it in 31 minutes. Test 1 (Engine Sim) Qwen 3.8 Preview: 25min Kimi K3: 1hr 30min Test 2 (Voxel Dino Printer) Qwen 3.8 Preview: 8min Kimi K3: 45min Test 3 (Garden Scene) Qwen 3.8 Preview: 31min Kimi K3: 2hrs
0:40

Qwen 3.8 Preview is quietly catching Kimi K3 on frontend + game design.And this is just the preview. Full 3.8 is going to be a beast. We tested Qwen 3.8 Preview against Kimi K3 on 3D modeling and animation. Ran both through the same 3 prompts. Both on Max effort. Qwen 3.8 Preview was dramatically faster across the board, 3-4x quicker on every test. Kimi K3 needed 2 hours on the final scene; Qwen wrapped it in 31 minutes. Test 1 (Engine Sim) Qwen 3.8 Preview: 25min Kimi K3: 1hr 30min Test 2 (Voxel Dino Printer) Qwen 3.8 Preview: 8min Kimi K3: 45min Test 3 (Garden Scene) Qwen 3.8 Preview: 31min Kimi K3: 2hrs

GMI Cloud

25,513 Aufrufe • vor 2 Monaten

I’ve tried driving Qwen 3.6 on my MacBook Pro with a few different agent harnesses: Claude Code: too slow. It moves like a turtle. Codex: Qwen stopped in the middle of tasks, probably due to tool-call mismatches between them. Qwen Code: so far the best experience. Very smooth. Qwen Code sometimes even tells a joke while you’re waiting. This video is played at original speed so you can get a real feel for how Qwen works.
0:47

I’ve tried driving Qwen 3.6 on my MacBook Pro with a few different agent harnesses: Claude Code: too slow. It moves like a turtle. Codex: Qwen stopped in the middle of tasks, probably due to tool-call mismatches between them. Qwen Code: so far the best experience. Very smooth. Qwen Code sometimes even tells a joke while you’re waiting. This video is played at original speed so you can get a real feel for how Qwen works.

Michael Guo

20,505 Aufrufe • vor 4 Monaten

Boris Cherny, Head of Claude Code at Anthropic: "The next transition is coming this year." 2023: you wrote the code. 2024: you prompted Claude to write the code. 2025: you wrote loops that prompted Claude. 2026: you build the harness that runs the loops. Each transition, the engineers who understood the new abstraction first moved ahead permanently. The ones who waited caught up eventually — but never all the way. Harness engineering is the 2026 abstraction. Here is everything you need to know ↓
0:40

Boris Cherny, Head of Claude Code at Anthropic: "The next transition is coming this year." 2023: you wrote the code. 2024: you prompted Claude to write the code. 2025: you wrote loops that prompted Claude. 2026: you build the harness that runs the loops. Each transition, the engineers who understood the new abstraction first moved ahead permanently. The ones who waited caught up eventually — but never all the way. Harness engineering is the 2026 abstraction. Here is everything you need to know ↓

Rahul

370,869 Aufrufe • vor 3 Monaten

Nah, this can’t be real. Same GPT-5.6 Sol. Same task. Same thinking level. I switched from regular Codex to the Claude Code harness, and the result instantly became way better. Claude Code is somehow making every model cook. GPT-5.6 SOL WAS ALREADY TOP TIER!! 😭
0:33

Nah, this can’t be real. Same GPT-5.6 Sol. Same task. Same thinking level. I switched from regular Codex to the Claude Code harness, and the result instantly became way better. Claude Code is somehow making every model cook. GPT-5.6 SOL WAS ALREADY TOP TIER!! 😭

OmedTheVibeCoder

127,040 Aufrufe • vor 2 Monaten

this is insane. just toggle this button and any coding agent can use your browser > no more Chrome extensions > One button, connect Claude Code to your browser all you need is the right harness... try it with the Browser Use CLI right now!
0:32

this is insane. just toggle this button and any coding agent can use your browser > no more Chrome extensions > One button, connect Claude Code to your browser all you need is the right harness... try it with the Browser Use CLI right now!

shawn

640,241 Aufrufe • vor 6 Monaten

Claude Code and Cursor... but they improve themselves. Autonomously. Meta Harness is wild. Had to make a video about it...
25:51

Claude Code and Cursor... but they improve themselves. Autonomously. Meta Harness is wild. Had to make a video about it...

Matthew Berman

152,723 Aufrufe • vor 6 Monaten

Alright guys, wow. Qwen 3.8 27B is basically Qwen 4. What we have here is one of the best one-shot shark survival games I've made with any model. I ran this same prompt through fable, and the biggest thing all models struggle with in this test is the top-down view of the sharks. Fable even had all of the fins reversed and details jumbled on the first turn. Before now, it was really a 2 to 8 turn test to get something final regardless of model. Qwen 3.8 27B just nailed this in one output, no harness at all, just purely the model thoroughly thinking before outputting the final result. On every asset used, different shark variants, everything, it all looks incredibly tight. The boat movement, shark speed and engagement, everything is so much better than I expected, and I was expecting a lot. Imagine what 8 turns would do in a harness? This confirms to me that while Qwen 3.8 27B thinks a lot, for the first time in a local model on the base weights, IT MIGHT ACTUALLY BE WORTH IT This is a Frontier Lab model result, and it ran on my 5090 at 60tps in Q5_K_M. I am just in complete astoundment at what Qwen has accomplished here, and I am incredibly grateful that this model is open source. The speed will also increase drastically with optimisations. This is just an incredible day. What a blessing. More to come!
4:28

Alright guys, wow. Qwen 3.8 27B is basically Qwen 4. What we have here is one of the best one-shot shark survival games I've made with any model. I ran this same prompt through fable, and the biggest thing all models struggle with in this test is the top-down view of the sharks. Fable even had all of the fins reversed and details jumbled on the first turn. Before now, it was really a 2 to 8 turn test to get something final regardless of model. Qwen 3.8 27B just nailed this in one output, no harness at all, just purely the model thoroughly thinking before outputting the final result. On every asset used, different shark variants, everything, it all looks incredibly tight. The boat movement, shark speed and engagement, everything is so much better than I expected, and I was expecting a lot. Imagine what 8 turns would do in a harness? This confirms to me that while Qwen 3.8 27B thinks a lot, for the first time in a local model on the base weights, IT MIGHT ACTUALLY BE WORTH IT This is a Frontier Lab model result, and it ran on my 5090 at 60tps in Q5_K_M. I am just in complete astoundment at what Qwen has accomplished here, and I am incredibly grateful that this model is open source. The speed will also increase drastically with optimisations. This is just an incredible day. What a blessing. More to come!

Kyle Hessling

24,917 Aufrufe • vor 1 Monat

We're excited to introduce Claude Code, Cursor, and Codex agents in Mastra. Starting today, Mastra is now a meta-harness:
0:32

We're excited to introduce Claude Code, Cursor, and Codex agents in Mastra. Starting today, Mastra is now a meta-harness:

Sam Bhagwat

58,295 Aufrufe • vor 3 Monaten

The Claude Code SDK is now the Claude Agent SDK Why? Because we realized the Claude Code agent harness is useful for much more than coding. In fact, we're moving to using it to power most of our own agent loops at Anthropic.
0:25

The Claude Code SDK is now the Claude Agent SDK Why? Because we realized the Claude Code agent harness is useful for much more than coding. In fact, we're moving to using it to power most of our own agent loops at Anthropic.

Thariq

207,146 Aufrufe • vor 11 Monaten

Qwen 3.8 27b Makes BEUATIFUL websites!! Getting these on GH for people to look at as well. @Qwen and Qwen Developers this is such an amazing model for websites and components!
0:49

Qwen 3.8 27b Makes BEUATIFUL websites!! Getting these on GH for people to look at as well. @Qwen and Qwen Developers this is such an amazing model for websites and components!

Loktar 🇺🇸

41,362 Aufrufe • vor 1 Monat

How to run GLM-5.2 (Or Minimax or Qwen or Deepseek or Kimi) in Claude Code No JSON editing. No vim 😮‍💨 1. Install Claude Code npm install -g Paul Jankura-ai/claude-code 2. Grab a Fireworks API key → 3. Install FireConnect + drop in your key (one line): curl -fsSL | FIREWORKS_API_KEY="fw_..." bash 4. Flip it on: fireconnect claude on 5. Switch to GLM-5.2 and bam! Swap models with: fireconnect claude model select Docs to do the same for Pi, Opencode, and Codex:
0:41

How to run GLM-5.2 (Or Minimax or Qwen or Deepseek or Kimi) in Claude Code No JSON editing. No vim 😮‍💨 1. Install Claude Code npm install -g Paul Jankura-ai/claude-code 2. Grab a Fireworks API key → 3. Install FireConnect + drop in your key (one line): curl -fsSL | FIREWORKS_API_KEY="fw_..." bash 4. Flip it on: fireconnect claude on 5. Switch to GLM-5.2 and bam! Swap models with: fireconnect claude model select Docs to do the same for Pi, Opencode, and Codex:

Sinan Ozdemir

149,913 Aufrufe • vor 3 Monaten

The founder of Claude Code (@ bcherny) made a thread last week going over 10 ways he and his team use Claude Code (Opus 4.5) to its maximum potential This 10 minute video is all the information you need to max out your Claude Code skills straight from the team who made it.
10:25

The founder of Claude Code (@ bcherny) made a thread last week going over 10 ways he and his team use Claude Code (Opus 4.5) to its maximum potential This 10 minute video is all the information you need to max out your Claude Code skills straight from the team who made it.

ashen

62,522 Aufrufe • vor 7 Monaten

Introducing Deep Graph MCP for Claude Code 🤩 Claude Code by Anthropic is excellent and arguably one of the best tools for working with code today but... It has one major limitation, its native code search capabilities don't scale well to large repositories. By adding Deep Graph MCP, Claude's ability to explore large codebases improves dramatically. In this thread 🧵 I’ll show you how easy it is to connect this MCP to Claude Code.
1:12

Introducing Deep Graph MCP for Claude Code 🤩 Claude Code by Anthropic is excellent and arguably one of the best tools for working with code today but... It has one major limitation, its native code search capabilities don't scale well to large repositories. By adding Deep Graph MCP, Claude's ability to explore large codebases improves dramatically. In this thread 🧵 I’ll show you how easy it is to connect this MCP to Claude Code.

Daniel San

31,974 Aufrufe • vor 1 Jahr

Introducing 𝙨𝙚𝙨𝙨𝙞𝙤𝙣-𝙢𝙞𝙜𝙧𝙖𝙩𝙚, a tool for migrating coding agent sessions across Claude Code, Codex, Pi, OpenCode, and more. If you started in Claude but ran of usage, you can now convert your session to another harness in one command:
0:43

Introducing 𝙨𝙚𝙨𝙨𝙞𝙤𝙣-𝙢𝙞𝙜𝙧𝙖𝙩𝙚, a tool for migrating coding agent sessions across Claude Code, Codex, Pi, OpenCode, and more. If you started in Claude but ran of usage, you can now convert your session to another harness in one command:

Xing Han Lu

29,930 Aufrufe • vor 1 Monat

Why I support Anthropic ... and think you should too. Yes, Claude Code (Claude) has the best coding model in the best harness. Yes, Cowork is phenomenal. But those are trees. We need to look at the forest, because it's currently dry -- and we're giving everyone matches.
6:44

Why I support Anthropic ... and think you should too. Yes, Claude Code (Claude) has the best coding model in the best harness. Yes, Cowork is phenomenal. But those are trees. We need to look at the forest, because it's currently dry -- and we're giving everyone matches.

Eric Buess

24,813 Aufrufe • vor 8 Monaten

OpenAI engineer: "Nobody on my team has touched code in 9 months. Agents write all the code, the way you do it is harness engineering." In 45 minutes he breaks down exactly how to build the setup so agents do the full job without you in the loop. This beats any paid course on building agents I've seen. Watch it, then read the full guide on harness engineering below.
45:40

OpenAI engineer: "Nobody on my team has touched code in 9 months. Agents write all the code, the way you do it is harness engineering." In 45 minutes he breaks down exactly how to build the setup so agents do the full job without you in the loop. This beats any paid course on building agents I've seen. Watch it, then read the full guide on harness engineering below.

Anatoli Kopadze

25,222 Aufrufe • vor 1 Monat