Loading video...

Video Failed to Load

Go Home

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

GitMaxd's profile picture

Git Maxd

1,863 subscribers

113,649 views • 3 months ago •via X (Twitter)

EducationScience & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

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

11,201 views • 4 months ago

watch opencode absolutely destroy claude code using the exact same model
0:10

watch opencode absolutely destroy claude code using the exact same model

dax

254,889 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 • 3 months ago

We decided to take Paul Jankura’s Claude Opus 4.5 out for a test drive vs. the current #1 ranking model in Code Arena: Gemini 3 Pro. Same prompt, different outputs. Let’s take a look. Remember, your votes drive the leaderboards. We’ll see how Claude Opus 4.5 stacks up in the coming days! Check out some of the comparisons, like how Claude Opus 4.5 handled the “Pyramids of Giza” prompt, in thread. 🧵
0:17

We decided to take Paul Jankura’s Claude Opus 4.5 out for a test drive vs. the current #1 ranking model in Code Arena: Gemini 3 Pro. Same prompt, different outputs. Let’s take a look. Remember, your votes drive the leaderboards. We’ll see how Claude Opus 4.5 stacks up in the coming days! Check out some of the comparisons, like how Claude Opus 4.5 handled the “Pyramids of Giza” prompt, in thread. 🧵

Arena.ai

88,977 views • 6 months ago

GLM-4.7 and MiniMax M2.1 side by side, both powered by Claude Code! Prompt below. Trick: one setting file per provider: - claude --settings ~/.claude/minimax_settings.json - claude --settings ~/.claude/zai-settings.json
0:17

GLM-4.7 and MiniMax M2.1 side by side, both powered by Claude Code! Prompt below. Trick: one setting file per provider: - claude --settings ~/.claude/minimax_settings.json - claude --settings ~/.claude/zai-settings.json

Ivan Fioravanti ᯅ

44,866 views • 5 months ago

Rōki Sasaki, Two Splitters, Two Different Breaks. 1. 7" of Arm Side Run 2. 8" of Glove Side Break 15 inches difference on the same pitch type.
0:16

Rōki Sasaki, Two Splitters, Two Different Breaks. 1. 7" of Arm Side Run 2. 8" of Glove Side Break 15 inches difference on the same pitch type.

Rob Friedman

416,210 views • 1 year ago

daytime: work with the best agents side by side — claude code + three we built ourselves (browser, computer use, video editing). nighttime: hand your machine over, earn while you sleep.
0:10

daytime: work with the best agents side by side — claude code + three we built ourselves (browser, computer use, video editing). nighttime: hand your machine over, earn while you sleep.

Derek Nee

13,117 views • 3 months ago

Users can explore how different AI agents analyze the same market task and compare their outputs through the platform. It is a product experience built around agent performance, task execution, and real usage. AI agents are becoming measurable digital workers.
0:17

Users can explore how different AI agents analyze the same market task and compare their outputs through the platform. It is a product experience built around agent performance, task execution, and real usage. AI agents are becoming measurable digital workers.

OKAI Official

10,097 views • 24 days ago

I got early access to AltSociety Chat and the real-time multi-model battles go crazy GPT, Gemini, Grok, and Claude respond side by side If you want to know which model actually fits your project, join waitlist is your shortcut:
0:11

I got early access to AltSociety Chat and the real-time multi-model battles go crazy GPT, Gemini, Grok, and Claude respond side by side If you want to know which model actually fits your project, join waitlist is your shortcut:

Nelly;

64,849 views • 6 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

312,035 views • 1 month ago

To make it easier to migrate your workflows, we've updated the claude-api skill in Claude Code with Opus 4.7 support. Just say "migrate to Opus 4.7" and it updates model names, prompts, and effort settings for you.
0:11

To make it easier to migrate your workflows, we've updated the claude-api skill in Claude Code with Opus 4.7 support. Just say "migrate to Opus 4.7" and it updates model names, prompts, and effort settings for you.

ClaudeDevs

361,565 views • 1 month ago

Truco para gastar tu suscripción de 20$ de Claude Code con un único prompt. /model → Opus 4.8 /effort → ultracode
0:11

Truco para gastar tu suscripción de 20$ de Claude Code con un único prompt. /model → Opus 4.8 /effort → ultracode

Brais Moure

111,561 views • 8 days ago

a great way to get started is to use our skill, built into Claude Code. get the latest Claude Code release: $ claude update then start Claude Code and run our subcommand: $ claude /claude-api managed-agents-onboarding
0:11

a great way to get started is to use our skill, built into Claude Code. get the latest Claude Code release: $ claude update then start Claude Code and run our subcommand: $ claude /claude-api managed-agents-onboarding

Lance Martin

14,764 views • 1 month ago

We just added /btw to Claude Code! Use it to have side chain conversations while Claude is working.
0:13

We just added /btw to Claude Code! Use it to have side chain conversations while Claude is working.

Thariq

2,780,954 views • 2 months ago

Agentic Video Editing This is crazy! I just asked Claude Code to build me an entire agent-powered video editing app. ~10K lines of code. Uses Claude Agent SDK + Claude Opus 4.6. It's really good. Runs locally. Highly customizable. You can just build things.
0:15

Agentic Video Editing This is crazy! I just asked Claude Code to build me an entire agent-powered video editing app. ~10K lines of code. Uses Claude Agent SDK + Claude Opus 4.6. It's really good. Runs locally. Highly customizable. You can just build things.

elvis

11,249 views • 3 months ago

Perplexity Computer is massively multi-model. Computer orchestrates models to run agents in parallel, leveraging Opus to match each task to the model best suited for it. In total, Computer can route work across 19 different models.
0:12

Perplexity Computer is massively multi-model. Computer orchestrates models to run agents in parallel, leveraging Opus to match each task to the model best suited for it. In total, Computer can route work across 19 different models.

Perplexity

531,610 views • 3 months ago

ANTHROPIC JUST TURNED AI AGENTS INTO GIT REPOS Anthropic shipped "ant" - a CLI that runs every Claude API endpoint straight from your terminal. The headline isn't the terminal access. It's that you can now version-control an AI agent as YAML in Git and have CI sync it to the Claude Platform, the same way you ship code. - Every API resource is a subcommand: messages, models, files, agents, sessions - Define an agent in a YAML file, check it into your repo, and keep it in sync with one update command - Spin up a session, send it an event, then pull every event and tool call back from the same CLI - Claude Code knows how to drive ant out of the box - it shells out and reads the results with no glue code Agents just stopped being prompts you babysit and became infrastructure you deploy.
0:18

ANTHROPIC JUST TURNED AI AGENTS INTO GIT REPOS Anthropic shipped "ant" - a CLI that runs every Claude API endpoint straight from your terminal. The headline isn't the terminal access. It's that you can now version-control an AI agent as YAML in Git and have CI sync it to the Claude Platform, the same way you ship code. - Every API resource is a subcommand: messages, models, files, agents, sessions - Define an agent in a YAML file, check it into your repo, and keep it in sync with one update command - Spin up a session, send it an event, then pull every event and tool call back from the same CLI - Claude Code knows how to drive ant out of the box - it shells out and reads the results with no glue code Agents just stopped being prompts you babysit and became infrastructure you deploy.

BuBBliK

198,380 views • 4 days ago

Not every task needs the same model. A quick summary doesn't need the same horsepower as a deep research question — and it shouldn't cost the same either. Now, you can now easily compare models for your Custom Agent on speed, intelligence, and cost 🫡
0:12

Not every task needs the same model. A quick summary doesn't need the same horsepower as a deep research question — and it shouldn't cost the same either. Now, you can now easily compare models for your Custom Agent on speed, intelligence, and cost 🫡

Notion

32,420 views • 3 months ago

Claude Code pro tip: use the new /rewind command to roll back code changes instantly. Model messes up? no biggie, just rewind it back to when it worked!
0:10

Claude Code pro tip: use the new /rewind command to roll back code changes instantly. Model messes up? no biggie, just rewind it back to when it worked!

Ian Nuttall

40,662 views • 8 months ago

This is amazing. Do this: 1. Set model to Opus 4.8 2. Reasoning effort to /ultracode Enables Claude Code's new Dynamic Workflows. Claude will autonomously detect complex tasks, write an orchestration script, and spawn an agent swarm.
0:13

This is amazing. Do this: 1. Set model to Opus 4.8 2. Reasoning effort to /ultracode Enables Claude Code's new Dynamic Workflows. Claude will autonomously detect complex tasks, write an orchestration script, and spawn an agent swarm.

Dan McAteer

844,200 views • 9 days ago