Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

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

1,878 subscribers

114,022 Aufrufe • vor 5 Monaten •via X (Twitter)

Bildung Wissenschaft & Technologie

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche 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 👇

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 Aufrufe • vor 5 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.

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 Aufrufe • vor 4 Monaten

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. 🧵

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 Aufrufe • vor 7 Monaten

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.

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 Aufrufe • vor 2 Monaten

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:

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 Aufrufe • vor 7 Monaten

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.

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

200,080 Aufrufe • vor 1 Monat

We gave Grok 4.5 and GPT-5.6 Sol the exact same prompt and compared the outputs side by side. The task: generate a fully interactive HTML5 glass bridge simulation with realistic physics, structural failure, cinematic visuals, polished UI, and smooth animations. The difference is actually visible.

We gave Grok 4.5 and GPT-5.6 Sol the exact same prompt and compared the outputs side by side. The task: generate a fully interactive HTML5 glass bridge simulation with realistic physics, structural failure, cinematic visuals, polished UI, and smooth animations. The difference is actually visible.

Entelligence AI

71,177 Aufrufe • vor 11 Tagen

Claude Fable 5 orchestrating Grok 4.5 is now my favorite real workflow. all you need is this free Claude Code plugin that makes Grok the default implementer. Fable writes the specs and reviews every diff, Grok 4.5 does the typing through the Grok CLI. - Grok handles the volume, Fable handles the judgment - Every diff gets cross-vendor review for free - Specs run as parallel agents when they're independent I've been testing it for a few days and the part that sold me is watching Fable refuse to write code. It sends specs down, judges what comes back, and that's it. setup: 1. claude plugin marketplace add DannyMac180/fable-advisor && claude plugin install fable-advisor 2. Install the Grok CLI from then grok login 3. /model fable It's open source, so you can read the agent files and tweak the routing however you want.

Claude Fable 5 orchestrating Grok 4.5 is now my favorite real workflow. all you need is this free Claude Code plugin that makes Grok the default implementer. Fable writes the specs and reviews every diff, Grok 4.5 does the typing through the Grok CLI. - Grok handles the volume, Fable handles the judgment - Every diff gets cross-vendor review for free - Specs run as parallel agents when they're independent I've been testing it for a few days and the part that sold me is watching Fable refuse to write code. It sends specs down, judges what comes back, and that's it. setup: 1. claude plugin marketplace add DannyMac180/fable-advisor && claude plugin install fable-advisor 2. Install the Grok CLI from then grok login 3. /model fable It's open source, so you can read the agent files and tweak the routing however you want.

Alvaro Cintas

98,800 Aufrufe • vor 10 Tagen

Claude Code Desktop now opens a new window for each session This makes it much easier to visualize multiple Claude Code agents running in parallel My current stack depends on the task: - Ghostty: when starting a project. Bash commands, git, env variables, provider connections. All manual through the terminal with a Claude panel running alongside. - Claude Code Desktop: once everything is configured. GitHub connected, CLAUDE.md, Skills, subagents and Hooks ready. Claude Code runs on its own, no more terminal setup, just panels running and outputs to review. - VSCode: when I need to review code by hand. I use it less and less, but there are moments where I have to confirm Claude got it right. I usually open the Claude extension inside VSCode, but it lacks most of the CLI features so it's limited Solid update. Worth trying once your workflows are already set up 👇

Claude Code Desktop now opens a new window for each session This makes it much easier to visualize multiple Claude Code agents running in parallel My current stack depends on the task: - Ghostty: when starting a project. Bash commands, git, env variables, provider connections. All manual through the terminal with a Claude panel running alongside. - Claude Code Desktop: once everything is configured. GitHub connected, CLAUDE.md, Skills, subagents and Hooks ready. Claude Code runs on its own, no more terminal setup, just panels running and outputs to review. - VSCode: when I need to review code by hand. I use it less and less, but there are moments where I have to confirm Claude got it right. I usually open the Claude extension inside VSCode, but it lacks most of the CLI features so it's limited Solid update. Worth trying once your workflows are already set up 👇

Daniel San

38,718 Aufrufe • vor 1 Monat

New feature in Claude Code 2.1.14 just dropped! You can now search and install plugins from the marketplaces installed in your current Claude Code session. This is huge if you’re building plugins on top of Claude Code’s marketplace layer (Skills, Agents, Hooks, etc). How it works: - Run /plugin - The official Claude marketplace is installed by default - Use the search bar to find the plugin you want - Select one or multiple plugins with space, then press i to install - Go to the Installed tab to browse and enable them With the exponential growth of Skills and Agent-based components running in the CLI, improving plugin discoverability is a big win. Pretty sure more marketplace-related features are coming

New feature in Claude Code 2.1.14 just dropped! You can now search and install plugins from the marketplaces installed in your current Claude Code session. This is huge if you’re building plugins on top of Claude Code’s marketplace layer (Skills, Agents, Hooks, etc). How it works: - Run /plugin - The official Claude marketplace is installed by default - Use the search bar to find the plugin you want - Select one or multiple plugins with space, then press i to install - Go to the Installed tab to browse and enable them With the exponential growth of Skills and Agent-based components running in the CLI, improving plugin discoverability is a big win. Pretty sure more marketplace-related features are coming

Daniel San

40,994 Aufrufe • vor 6 Monaten

SOMEONE MAPPED CHAOS INTO A NAVIGABLE SPACE AND YOUR HERMES AGENT NEEDS THE SAME THING thousands of chaotic data points, each given a position, navigation becomes instant because the structure does the work your vault is the same chaos, hermes lands in it and opens files at random because nothing tells it where to start one index file per major folder with a clear starting point changes everything 2 minutes per task drops to 10 seconds, same agent, same model full breakdown in the article below ↓

SOMEONE MAPPED CHAOS INTO A NAVIGABLE SPACE AND YOUR HERMES AGENT NEEDS THE SAME THING thousands of chaotic data points, each given a position, navigation becomes instant because the structure does the work your vault is the same chaos, hermes lands in it and opens files at random because nothing tells it where to start one index file per major folder with a clear starting point changes everything 2 minutes per task drops to 10 seconds, same agent, same model full breakdown in the article below ↓

leopardracer

23,618 Aufrufe • vor 19 Tagen

Excited to announce AI Research Skills - an open-source library of 82 specialized skills for AI coding tools. One command gives your agent expert knowledge in: → Model training & fine-tuning (TRL, Unsloth ...) → Distributed systems (DeepSpeed, FSDP ...) → Inference optimization (vLLM, TensorRT ...) → Agent building ? (Langchain, AutoGPT ...) Works with Claude Code, Cursor, Gemini CLI, Windsurf, and Codex with one click interactive installation @ npx orchestra-research/ai-research-skills If you found the ML paper writing skill useful, check out the comprehensive collection

Excited to announce AI Research Skills - an open-source library of 82 specialized skills for AI coding tools. One command gives your agent expert knowledge in: → Model training & fine-tuning (TRL, Unsloth ...) → Distributed systems (DeepSpeed, FSDP ...) → Inference optimization (vLLM, TensorRT ...) → Agent building ? (Langchain, AutoGPT ...) Works with Claude Code, Cursor, Gemini CLI, Windsurf, and Codex with one click interactive installation @ npx orchestra-research/ai-research-skills If you found the ML paper writing skill useful, check out the comprehensive collection

Zechen Zhang

75,466 Aufrufe • vor 5 Monaten

> open Claude Cowork > write an email > close it > do the same thing next week > wonder why people say it's life-changing meanwhile: > /schedule — inbox triaged before I wake up. every morning. > /agents — sub-agent reviews every PR in my team's code style > custom skills folder — every output sounds like me, not Claude > .claude/ folder — hiring managers check this before your LinkedIn now 60 commands. most people use 6. I documented all of them. save this.

> open Claude Cowork > write an email > close it > do the same thing next week > wonder why people say it's life-changing meanwhile: > /schedule — inbox triaged before I wake up. every morning. > /agents — sub-agent reviews every PR in my team's code style > custom skills folder — every output sounds like me, not Claude > .claude/ folder — hiring managers check this before your LinkedIn now 60 commands. most people use 6. I documented all of them. save this.

Nav Toor

402,030 Aufrufe • vor 2 Monaten

subagents are just recursive agents where you can apply different prompts + models depending on the task. since they’re just a primitive, Cursor cli can actually spawn subagents by calling cursor-agent in headless mode via shell commands. that’s what makes the cli so nice. you can extend it, experiment, and have a lot of fun exploring orchestration patterns. here’s one way to do it w. dynamic model selection: 1. create a subagents.mdc rule 2. drop in: ``` --- alwaysApply: true --- ALWAYS spawn subagents by running `cursor-agent -p [task] --output-format=text --force --model [model]` in the terminal. Each subagent should return a summary of the changes it made. Subagents should be used for ALL tasks You can adopt a fan-out pattern where you spawn subagents to perform parallel isolated tasks, and then fan-in the results. Use the following models: - `--model gpt-5` for reasoning, researching, and planning - `--model sonnet-4` for implementation ``` 3. start cursor cli and try it out you can also adjust the rule to be more explicit when it should use subagents, when not to, which models when etc.

subagents are just recursive agents where you can apply different prompts + models depending on the task. since they’re just a primitive, Cursor cli can actually spawn subagents by calling cursor-agent in headless mode via shell commands. that’s what makes the cli so nice. you can extend it, experiment, and have a lot of fun exploring orchestration patterns. here’s one way to do it w. dynamic model selection: 1. create a subagents.mdc rule 2. drop in: ``` --- alwaysApply: true --- ALWAYS spawn subagents by running `cursor-agent -p [task] --output-format=text --force --model [model]` in the terminal. Each subagent should return a summary of the changes it made. Subagents should be used for ALL tasks You can adopt a fan-out pattern where you spawn subagents to perform parallel isolated tasks, and then fan-in the results. Use the following models: - `--model gpt-5` for reasoning, researching, and planning - `--model sonnet-4` for implementation ``` 3. start cursor cli and try it out you can also adjust the rule to be more explicit when it should use subagents, when not to, which models when etc.

eric zakariasson

57,554 Aufrufe • vor 11 Monaten

This Japanese trader fed Claude 400M Polymarket trades and made $51,648 in 2 months His account is mocamoca He gave Claude one task: find an edge in prediction markets Claude analyzed 36GB of trades collected over 6 years and found one thing: "dead" contracts priced under 1¢ don't stay dead 6% of the time and 2.66% at 99x covers everything mocamoca's twist: enters at 3-15¢, exits at 87-93¢ same asymmetry, tighter execution from Feb 5 to today: - biggest win: $395 -> $2,906 - 1,658 trades account is public, check it yourself: I found 7 more wallets doing the same thing -> $550K combined reverse-engineered the strategy, built the bot full code inside the article

This Japanese trader fed Claude 400M Polymarket trades and made $51,648 in 2 months His account is mocamoca He gave Claude one task: find an edge in prediction markets Claude analyzed 36GB of trades collected over 6 years and found one thing: "dead" contracts priced under 1¢ don't stay dead 6% of the time and 2.66% at 99x covers everything mocamoca's twist: enters at 3-15¢, exits at 87-93¢ same asymmetry, tighter execution from Feb 5 to today: - biggest win: $395 -> $2,906 - 1,658 trades account is public, check it yourself: I found 7 more wallets doing the same thing -> $550K combined reverse-engineered the strategy, built the bot full code inside the article

Paone

16,153 Aufrufe • vor 3 Monaten

I ran Codex, Claude, and Gemini on the same PR review. They disagreed on 4 out of 7 issues. That’s when I realized the best workflow isn’t choosing one model - it’s making them compare notes. So I built Council: an open source CLI that runs all three in parallel, surfaces disagreements, and gives you one synthesized recommendation. npx @armstrng/council review this PR

I ran Codex, Claude, and Gemini on the same PR review. They disagreed on 4 out of 7 issues. That’s when I realized the best workflow isn’t choosing one model - it’s making them compare notes. So I built Council: an open source CLI that runs all three in parallel, surfaces disagreements, and gives you one synthesized recommendation. npx @armstrng/council review this PR

Colin Armstrong

11,666 Aufrufe • vor 2 Monaten

I MADE MY AI AGENT 10X FASTER WITHOUT CHANGING THE MODEL not a smarter model, not a bigger context window, not another clever prompt the same kind of AI that designs vaccines for viruses we have not even met yet was spending two minutes opening the wrong files just to hand me a brief from three months ago the problem was never capability, it was the scaffolding that piled up around my agent by accident, folder by folder an agent does not think in your categories, it searches from scratch every single time, and your tidy human folders are a maze to it the fix was almost stupidly small, one index file at the root of each big folder and a few numbers in front of the folder names slowest task dropped from 2 minutes to 26 seconds, fastest ones hit 10, zero model changes capability is cheap when the scaffolding around it is broken the article breaks down the whole system in 15 minutes ↓

I MADE MY AI AGENT 10X FASTER WITHOUT CHANGING THE MODEL not a smarter model, not a bigger context window, not another clever prompt the same kind of AI that designs vaccines for viruses we have not even met yet was spending two minutes opening the wrong files just to hand me a brief from three months ago the problem was never capability, it was the scaffolding that piled up around my agent by accident, folder by folder an agent does not think in your categories, it searches from scratch every single time, and your tidy human folders are a maze to it the fix was almost stupidly small, one index file at the root of each big folder and a few numbers in front of the folder names slowest task dropped from 2 minutes to 26 seconds, fastest ones hit 10, zero model changes capability is cheap when the scaffolding around it is broken the article breaks down the whole system in 15 minutes ↓

shmidt

36,439 Aufrufe • vor 20 Tagen

MiniMax M2.5 is benchmaxed. I gave 4 models the same prompt: Create a neon "OPEN" sign in HTML. GLM 5: Clean, classic neon. Nailed it. Claude Opus 4.6: Stylized with glow. Solid. Gemini 3 Pro: Cursive with bloom lighting. Creative. MiniMax M2.5: Spelled it "O b∈ N" with broken spacing. This model ranks #2 on BridgeBench with a 59.7 score and 100% completion rate. But it can't spell a 4-letter word. Benchmarks don't tell the whole story. A model can ace structured tasks and fail basic creative prompts. High score ≠ production ready.

MiniMax M2.5 is benchmaxed. I gave 4 models the same prompt: Create a neon "OPEN" sign in HTML. GLM 5: Clean, classic neon. Nailed it. Claude Opus 4.6: Stylized with glow. Solid. Gemini 3 Pro: Cursive with bloom lighting. Creative. MiniMax M2.5: Spelled it "O b∈ N" with broken spacing. This model ranks #2 on BridgeBench with a 59.7 score and 100% completion rate. But it can't spell a 4-letter word. Benchmarks don't tell the whole story. A model can ace structured tasks and fail basic creative prompts. High score ≠ production ready.

BridgeMind

54,212 Aufrufe • vor 5 Monaten

Claude Code Agent Teams are f*cking ridiculous 🤯 One prompt → a team lead breaks your project into pieces, spins up multiple AI agents, and they all work on different parts simultaneously. Research, builds, reviews, and debugging: all happening at the same time. All inside Claude Code. If you're running complex projects where every step waits on the last one... Agent teams eliminate the entire bottleneck: → Tell Claude what you need and describe the team structure in plain English → A lead agent breaks the work into a shared task list → It spawns 3-5 teammates — each with their own context and workspace → Teammates research, build, test, and review in parallel → They message each other, share findings, and challenge each other's work → The lead synthesizes everything into a finished deliverable No managing agents yourself. No waiting for step 1 to finish before step 2 starts. No single-lens reviews that miss half the issues. What you get: → Competitive research across 5 brands done in minutes instead of hours → Multi-component builds where frontend, backend, and data layers happen simultaneously → Creative reviews from 3 different angles at once — brand voice, conversion, differentiation → Funnel debugging where 4 agents investigate 4 theories and debate until they find the real answer Built 100% in Claude Code with one settings change. I put together a full DTC playbook: 5 workflows with copy-paste prompts, the exact setup process, token management tips, and honest guidance on when agent teams are worth it vs. when a simpler approach is the better move. Want it for free? > Like this post > Comment "AGENTS" And I'll send it over (must be following so I can DM)

Mike Futia

46,392 Aufrufe • vor 4 Monaten

Claude Code's effort parameter is something you need to keep in mind before starting any task It's not just about picking the right model anymore (Haiku, Sonnet, Opus). Now you also need to think about which effort level to use before each task. One tip I always go back to: when Opus can't solve a problem, just adding ultrathink makes things click, it's almost magic. We wrote a post at Hedgineer benchmarking each effort level by cost and time Read it here:

Claude Code's effort parameter is something you need to keep in mind before starting any task It's not just about picking the right model anymore (Haiku, Sonnet, Opus). Now you also need to think about which effort level to use before each task. One tip I always go back to: when Opus can't solve a problem, just adding ultrathink makes things click, it's almost magic. We wrote a post at Hedgineer benchmarking each effort level by cost and time Read it here:

Daniel San

66,147 Aufrufe • vor 4 Monaten