Loading video...

Video Failed to Load

Go Home

watch opencode absolutely destroy claude code using the exact same model

thdxr's profile picture

dax

147,030 subscribers

256,269 views • 7 months ago •via X (Twitter)

ComedyScience & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

cross-platform e2e mobile testing is solved. watch claude code run the same test on ipad, iphone, and android, at the exact same time ->
0:13

cross-platform e2e mobile testing is solved. watch claude code run the same test on ipad, iphone, and android, at the exact same time ->

hayden

16,309 views • 2 months ago

Side by side example Same model (claude-opus-4-6). Same task. Two different agent harnesses LangChain Deep Agents CLI: 9s Claude Code: 16s The harness IS the performance. 1.7× difference, zero model changes
0:19

Side by side example Same model (claude-opus-4-6). Same task. Two different agent harnesses LangChain Deep Agents CLI: 9s Claude Code: 16s The harness IS the performance. 1.7× difference, zero model changes

Git Maxd

114,022 views • 5 months ago

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

72,501 views • 4 months ago

Claude Code ships with a built-in skill for working with the Claude Platform. Useful for model migrations, using API features (e.g., prompt caching), or onboarding to newer APIs like Claude Managed Agents.
0:14

Claude Code ships with a built-in skill for working with the Claude Platform. Useful for model migrations, using API features (e.g., prompt caching), or onboarding to newer APIs like Claude Managed Agents.

ClaudeDevs

313,187 views • 2 months ago

how using claude code feels
0:14

how using claude code feels

tweet davidson

76,209 views • 4 months ago

Absolutely loving this setup: Claude Code + Ghostty + Lazygit + Worktree I’m writing 3 threads on X showing how you can use it: 1- Ghostty setup and SAND keybindings 2- Monitoring Claude Code changes with Lazygit 3- Parallel agents with Git worktrees + Claude Code I’ll publish one per week, using exactly the same setup and workflow I use. If you’re interested, feel free to follow along so you catch them
0:14

Absolutely loving this setup: Claude Code + Ghostty + Lazygit + Worktree I’m writing 3 threads on X showing how you can use it: 1- Ghostty setup and SAND keybindings 2- Monitoring Claude Code changes with Lazygit 3- Parallel agents with Git worktrees + Claude Code I’ll publish one per week, using exactly the same setup and workflow I use. If you’re interested, feel free to follow along so you catch them

Daniel San

161,884 views • 5 months ago

a project i've been excited about: make Claude Code better at using the Claude API. just ask Claude Code about Claude API features (e.g., prompt caching, adaptive thinking + effort, tools, etc).
0:11

a project i've been excited about: make Claude Code better at using the Claude API. just ask Claude Code about Claude API features (e.g., prompt caching, adaptive thinking + effort, tools, etc).

Lance Martin

31,964 views • 4 months ago

THE GIRLS People said they use the same exact model
0:15

THE GIRLS People said they use the same exact model

Betrigan

45,870 views • 3 months ago

Claude made this insane PDF flipbook entirely through code using the algorithmic art skill in claude dot ai
0:11

Claude made this insane PDF flipbook entirely through code using the algorithmic art skill in claude dot ai

Alex Albert

211,579 views • 9 months ago

I built an app that runs Claude Code, Codex, Cursor, Grok, Antigravity, OpenCode, and Pi side by side in my Mac notch. Agent finishes → notch pops. Needs approval → notch pops. One click back to that exact session. no more switching between apps.
0:19

I built an app that runs Claude Code, Codex, Cursor, Grok, Antigravity, OpenCode, and Pi side by side in my Mac notch. Agent finishes → notch pops. Needs approval → notch pops. One click back to that exact session. no more switching between apps.

Edward Luo

869,683 views • 3 days ago

Same exact prompts, but made using Seedance 2.0
0:15

Same exact prompts, but made using Seedance 2.0

CHRIS FIRST

33,568 views • 4 months ago

You can now review the code written by Claude Code, Codex, OpenCode, and more directly in Warp, and send inline comments straight to the agent. It's like a PR review without having to leave your terminal. Try it out!
0:19

You can now review the code written by Claude Code, Codex, OpenCode, and more directly in Warp, and send inline comments straight to the agent. It's like a PR review without having to leave your terminal. Try it out!

Warp

222,928 views • 3 months ago

Trying to choose the right AI model? Here’s what happens when Claude, ChatGPT, and Grok try to build the same thing. Watch the side-by-side 👇
0:15

Trying to choose the right AI model? Here’s what happens when Claude, ChatGPT, and Grok try to build the same thing. Watch the side-by-side 👇

Verse 8 | Why Code, Just Verse 8

11,232 views • 5 months ago

Advent of Claude Day 31 - Claude Agent SDK I saved the best for last. The same agent loop, tools, and context management that power Claude Code is available as an SDK. Build agents that work like Claude Code in as little as 10 lines of code. This is just the beginning. 🎇🥂
0:18

Advent of Claude Day 31 - Claude Agent SDK I saved the best for last. The same agent loop, tools, and context management that power Claude Code is available as an SDK. Build agents that work like Claude Code in as little as 10 lines of code. This is just the beginning. 🎇🥂

Ado

100,117 views • 6 months ago

microsoft has banned employees from using claude code. we're so back, baby!
0:14

microsoft has banned employees from using claude code. we're so back, baby!

void.

6,464,669 views • 1 month ago

Why devs love OpenCode: > fully open source harness + privacy-first > butter-smooth terminal TUI > bring your own model: Claude, GPT, Kimi, etc. > LSP-smart, multi-session agents, git-native What’s your favorite feature of OpenCode?
0:11

Why devs love OpenCode: > fully open source harness + privacy-first > butter-smooth terminal TUI > bring your own model: Claude, GPT, Kimi, etc. > LSP-smart, multi-session agents, git-native What’s your favorite feature of OpenCode?

Warp

101,944 views • 3 months ago

Michael Arnaldi suggested cloning the effect repo as a git subtree, giving it to Claude, then using that as docs It sounds absurd, but it's actually kind amazing lol Setup a custom OpenCode agent that has all the context on where the files are then it kinda just works I feel like this could definitely be refined but idk if I even care enough. Stuff like cursor/opencode/claude code is already so good at searching codebases that I don't really care to do anything more
0:12

Michael Arnaldi suggested cloning the effect repo as a git subtree, giving it to Claude, then using that as docs It sounds absurd, but it's actually kind amazing lol Setup a custom OpenCode agent that has all the context on where the files are then it kinda just works I feel like this could definitely be refined but idk if I even care enough. Stuff like cursor/opencode/claude code is already so good at searching codebases that I don't really care to do anything more

Ben Davis

112,524 views • 8 months ago

You can now vibe code a 3D website using this open source model. - Totally free - Runs even locally - Works with any image This workflow is compatible with all tools (Replit, Lovable, Claude Code, etc.) Quick steps below:
0:18

You can now vibe code a 3D website using this open source model. - Totally free - Runs even locally - Works with any image This workflow is compatible with all tools (Replit, Lovable, Claude Code, etc.) Quick steps below:

Paul Couvert

140,388 views • 1 year ago

Created animations for a Discord server using Claude code in 8 prompts🤞| Rive
0:17

Created animations for a Discord server using Claude code in 8 prompts🤞| Rive

Dani Bayanov

136,162 views • 3 months ago