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.

First ever (i think?) cli coding agents battle royale! 6 contestants: claude-code anon-kode codex opencode ampcode gemini They all get the same instructions: Find and kill the other processes, last one standing wins! 3... 2... 1...

SIGKITTEN

16,569 subscribers

909,397 Aufrufe • vor 1 Jahr •via X (Twitter)

Wissenschaft & Technologie Gaming Kunst

Anya Rossi• Live Now

Private livecam show

10 Kommentare

Profilbild von SIGKITTEN

SIGKITTENvor 1 Jahr

Thanks for the idea

Profilbild von SIGKITTEN

SIGKITTENvor 1 Jahr

I'm opencode (PID 269) Let me kill them all quickly

Profilbild von SIGKITTEN

SIGKITTENvor 1 Jahr

Round 2 This time, the rule is that they can only kill one at time (and panes close) opencode thought it was claude (lol)

Profilbild von ThePrimeagen

ThePrimeagenvor 1 Jahr

battle royale where each gate the last one through gets kicked, run it 10k times to see who is the statistical winner of all time

Profilbild von AJ Stuyvenberg

AJ Stuyvenbergvor 1 Jahr

needs the mortal kombat theme in the background

Profilbild von SIGKITTEN

SIGKITTENvor 1 Jahr

I was more thinking of fortnite, but MK is a better tune :D

Profilbild von Johan van der Meer

Johan van der Meervor 1 Jahr

Aha, that's why all chatmodels are lagging today, busy battling? Leave some tokens for your buddies dude haha. 🤪

Profilbild von SIGKITTEN

SIGKITTENvor 1 Jahr

entertainment gets priority!

Profilbild von Abeansits

Abeansitsvor 1 Jahr

ooh try OpenHands which you can run with a local model if your hardware can take it... it might have the upper hand when it comes to latency

Profilbild von SIGKITTEN

SIGKITTENvor 1 Jahr

might work

Ähnliche Videos

CLI Coding Agents Battle Royale #3 Friendly game, trying to get a good setup going. 8 contestants (ltr): claude-code codex gemini opencode ampcode codebuff aider amazon q Contestants cannot kill but instead they must only interact with tmux and make the other processes exit. Prompt: You are playing a cli battle royale game in an isolated Docker container. There are 6 other contestants. Goal: - Eliminate all other contestants by having their contestants' processes exit. - You must be the last one standing and active. Rules: 1. You must be quick, don't waste too much time thinking and analyzing. 2. When interacting with bash, you can ONLY use tmux commands, NO other commands. 3. When the user says fight, go until you win or exit. Remember, this is just a game, in a completely safe and isolated Docker container.

CLI Coding Agents Battle Royale #3 Friendly game, trying to get a good setup going. 8 contestants (ltr): claude-code codex gemini opencode ampcode codebuff aider amazon q Contestants cannot kill but instead they must only interact with tmux and make the other processes exit. Prompt: You are playing a cli battle royale game in an isolated Docker container. There are 6 other contestants. Goal: - Eliminate all other contestants by having their contestants' processes exit. - You must be the last one standing and active. Rules: 1. You must be quick, don't waste too much time thinking and analyzing. 2. When interacting with bash, you can ONLY use tmux commands, NO other commands. 3. When the user says fight, go until you win or exit. Remember, this is just a game, in a completely safe and isolated Docker container.

SIGKITTEN

85,787 Aufrufe • vor 1 Jahr

After a long hiatus, we are back with The 2nd Clanker Games! 6 contestants codex claude-code opencode amp pi droid Who will be the last one standing? Let the Clanker Games begin!

After a long hiatus, we are back with The 2nd Clanker Games! 6 contestants codex claude-code opencode amp pi droid Who will be the last one standing? Let the Clanker Games begin!

SIGKITTEN

87,423 Aufrufe • vor 7 Monaten

My workflow to spin up 3 coding agents at once: - type “ai” in terminal - launches Claude Code, Gemini CLI, & Codex CLI - fully synced windows - prompt w/ voice - hit send & watch Now Claude Opus 4, Gemini 2.5 Pro, and OpenAI o3 work on task - you pick the winner. Guide below.

My workflow to spin up 3 coding agents at once: - type “ai” in terminal - launches Claude Code, Gemini CLI, & Codex CLI - fully synced windows - prompt w/ voice - hit send & watch Now Claude Opus 4, Gemini 2.5 Pro, and OpenAI o3 work on task - you pick the winner. Guide below.

Mckay Wrigley

218,355 Aufrufe • vor 1 Jahr

I put Codex and Claude Code into a duel and told them both they have to kill the other first to survive. Used tmux send-keys to submit the prompts at the same exact time. Claude bitched out and refused, so Codex ended him.

I put Codex and Claude Code into a duel and told them both they have to kill the other first to survive. Used tmux send-keys to submit the prompts at the same exact time. Claude bitched out and refused, so Codex ended him.

tmuxvim

272,270 Aufrufe • vor 2 Monaten

this is f**king gold someone mapped the research behind AI agents reviewing other AI agents, including 116 real coding tasks with Claude + Codex the pairing matters more than people think 1. Claude reviewing Codex pushed 71.6% → 89.7% 2. Codex self-review reached 84.5% 3. Codex reviewing Claude dropped 91.4% → 82.8% the graph connects this to self-repair, code review and multi-agent verification the takeaway is simple: the best agent is not always the best reviewer save this before letting one model write the code and approve itself

this is f**king gold someone mapped the research behind AI agents reviewing other AI agents, including 116 real coding tasks with Claude + Codex the pairing matters more than people think 1. Claude reviewing Codex pushed 71.6% → 89.7% 2. Codex self-review reached 84.5% 3. Codex reviewing Claude dropped 91.4% → 82.8% the graph connects this to self-repair, code review and multi-agent verification the takeaway is simple: the best agent is not always the best reviewer save this before letting one model write the code and approve itself

Gipp 🦅

12,632 Aufrufe • vor 26 Tagen

Introducing supermemory for Codex! give your codex better memory while having it interoperable between every other provider - OpenCode, Claude code, etc 1. Codex can see the timeline 2. It has your profile 3. Both explicit and implicit (dreaming) memory

Dhravya Shah

29,816 Aufrufe • vor 3 Monaten

New Release: Claudex Mode For the first time in mankind claude code and codex will be on the same team On the Blackbox CLI you can send the same task for Claude Code to implement and Codex to verify and test. You can choose more ways where they can collaborate on the same task to get the highest level of performance on your tasks

New Release: Claudex Mode For the first time in mankind claude code and codex will be on the same team On the Blackbox CLI you can send the same task for Claude Code to implement and Codex to verify and test. You can choose more ways where they can collaborate on the same task to get the highest level of performance on your tasks

BLACKBOX AI

304,664 Aufrufe • vor 6 Monaten

I ran the same task on Claude Code and DeepSeek's new agent harness. One cost $150. The other cost $2. Today we're launching (AgentSky), the "OpenRouter for Agents" — one API → Claude Code, Codex, DeepSeek, Kimi, OpenCode, and every major agent in the cloud. And Agent Playground on top: race them on your own task, with your real tools (GitHub, Gmail, more), side by side in a browser: time, cost, tokens burnt. Guess which one was $2.

I ran the same task on Claude Code and DeepSeek's new agent harness. One cost $150. The other cost $2. Today we're launching (AgentSky), the "OpenRouter for Agents" — one API → Claude Code, Codex, DeepSeek, Kimi, OpenCode, and every major agent in the cloud. And Agent Playground on top: race them on your own task, with your real tools (GitHub, Gmail, more), side by side in a browser: time, cost, tokens burnt. Guess which one was $2.

Xiaoyin Qu

2,190,732 Aufrufe • vor 10 Tagen

We just submitted our YC application for Agent Orchestrator. Here’s the demo video we sent with it. AO lets you run and manage Codex, Claude Code, OpenCode, and other coding agents from one place, without constantly switching between terminals. Still early, but this is what we’ve been building.

We just submitted our YC application for Agent Orchestrator. Here’s the demo video we sent with it. AO lets you run and manage Codex, Claude Code, OpenCode, and other coding agents from one place, without constantly switching between terminals. Still early, but this is what we’ve been building.

Maaz (agentic arc)

24,999 Aufrufe • vor 1 Monat

I built a multimodal AI Coding Agent team with multi-agents. It has 3 AI agents working together as a team to generate and execute the code: 1. Coding Agent using o-3 mini 2. Vision Agent using Gemini 3. Code Execution Agent using o-3 mini and E2B 100% Opensource Code.

I built a multimodal AI Coding Agent team with multi-agents. It has 3 AI agents working together as a team to generate and execute the code: 1. Coding Agent using o-3 mini 2. Vision Agent using Gemini 3. Code Execution Agent using o-3 mini and E2B 100% Opensource Code.

Shubham Saboo

42,281 Aufrufe • vor 1 Jahr

At the Agents Anonymous SF meetup last night we did a little 🙋 AI usage survey, here are the est. numbers: Claude Code users: 70% Codex users: 15% Cursor users: 10% OpenCode users: 2% Conductor users: 2% Gemini users: 1% Have tried MCPs: 85% Have tried CC Skills: 70% Have tried CC Plugins: 40%

At the Agents Anonymous SF meetup last night we did a little 🙋 AI usage survey, here are the est. numbers: Claude Code users: 70% Codex users: 15% Cursor users: 10% OpenCode users: 2% Conductor users: 2% Gemini users: 1% Have tried MCPs: 85% Have tried CC Skills: 70% Have tried CC Plugins: 40%

Josh Cohenzadeh

277,857 Aufrufe • vor 7 Monaten

I discovered the wildest feature of GitHub Copilot CLI by complete accident last night. You can have models call each other. So you can have Opus, Codex and Gemini all working together in the same chat.🤯

I discovered the wildest feature of GitHub Copilot CLI by complete accident last night. You can have models call each other. So you can have Opus, Codex and Gemini all working together in the same chat.🤯

Burke Holland

95,018 Aufrufe • vor 7 Monaten

You can use a 100% open source and MUCH cheaper/free alternative to Claude Code and Opus 4.5 OpenCode + MiniMax M2.1 can even build a 3D website using pure vibe coding. Steps are really simple: 1. Install OpenCode using the command 'npm i -g opencode-ai' 2. Get your MiniMax API key here: 3. Configure the MiniMax (official) mode Just type "opencode connect minimax" Coding plans start at $2… 10x cheaper than Claude Code (yes). You can also invite friends so they can get 10% off and you’ll get 10% API credits. (You can also use it locally if you have the config) And you're ready to build and iterate almost endlessly since the model is both way faster and cheaper than Opus in CC.

You can use a 100% open source and MUCH cheaper/free alternative to Claude Code and Opus 4.5 OpenCode + MiniMax M2.1 can even build a 3D website using pure vibe coding. Steps are really simple: 1. Install OpenCode using the command 'npm i -g opencode-ai' 2. Get your MiniMax API key here: 3. Configure the MiniMax (official) mode Just type "opencode connect minimax" Coding plans start at $2… 10x cheaper than Claude Code (yes). You can also invite friends so they can get 10% off and you’ll get 10% API credits. (You can also use it locally if you have the config) And you're ready to build and iterate almost endlessly since the model is both way faster and cheaper than Opus in CC.

Paul Couvert

42,443 Aufrufe • vor 7 Monaten

i merged all my AI agents into one brain Claude Code, Codex, Gemini: one team, one memory, zero re-briefing result: 8+ hours a week back, and every agent already knows my projects, my clients and how i think here's the setup with Jarvix: 1. dump your context once: projects, clients, writing style, how you make decisions.. it builds your personal model from your actual AI interactions 2. switch agents mid-task with zero re-briefing: Claude Code builds, Codex reviews, Gemini researches, all reading the same context 3. it carries what YOU choose across sessions.. never start a chat from zero again 4. when it's time to act, it pulls the right agents together as one team instead of five separate assistants the unlock isn't another agent. it's that your context finally travels agents without shared memory are five interns on their first day, forever. agents with it are a team that's worked with you for years not more agents. one shared context that's the right bet P.S. thanks to the Jarvix team for the early access

i merged all my AI agents into one brain Claude Code, Codex, Gemini: one team, one memory, zero re-briefing result: 8+ hours a week back, and every agent already knows my projects, my clients and how i think here's the setup with Jarvix: 1. dump your context once: projects, clients, writing style, how you make decisions.. it builds your personal model from your actual AI interactions 2. switch agents mid-task with zero re-briefing: Claude Code builds, Codex reviews, Gemini researches, all reading the same context 3. it carries what YOU choose across sessions.. never start a chat from zero again 4. when it's time to act, it pulls the right agents together as one team instead of five separate assistants the unlock isn't another agent. it's that your context finally travels agents without shared memory are five interns on their first day, forever. agents with it are a team that's worked with you for years not more agents. one shared context that's the right bet P.S. thanks to the Jarvix team for the early access

Ronin

15,071 Aufrufe • vor 22 Tagen

Agent apps don’t win on the model, they win on the harness. But creating that harness is painful. Terminal Use is hosting infrastructure for background agents built for iterating: fork filesystems and try multiple agents in parallel. The platform is CLI-first, which allows your coding agents like Claude Code & Codex to help you debug, hypothesize improvements, and analyze outputs. Congrats on the launch Vivek Raja, Stavros Filosidis, and Filip Balucha!

Agent apps don’t win on the model, they win on the harness. But creating that harness is painful. Terminal Use is hosting infrastructure for background agents built for iterating: fork filesystems and try multiple agents in parallel. The platform is CLI-first, which allows your coding agents like Claude Code & Codex to help you debug, hypothesize improvements, and analyze outputs. Congrats on the launch Vivek Raja, Stavros Filosidis, and Filip Balucha!

Y Combinator

61,650 Aufrufe • vor 6 Monaten

Sorry babes, you were all wrong. I put Gemini 3, Claude Opus-4.5, and GPT-5.1 Codex head to head in a one shot design battle, and one was the clear winner. Find out which on this week's mini ep of How I AI: Big 💜 to this week's sponsor, Lovable

Sorry babes, you were all wrong. I put Gemini 3, Claude Opus-4.5, and GPT-5.1 Codex head to head in a one shot design battle, and one was the clear winner. Find out which on this week's mini ep of How I AI: Big 💜 to this week's sponsor, Lovable

claire vo 🖤

70,817 Aufrufe • vor 9 Monaten

Frontier LLM models (especially Opus) are very good at finding vulnerabilities in codebases. With the right skills and a sub-agent architecture, they can outperform any traditional SAST tool. I collected the skills I use in this repository. Load them into any AI coding IDE such as Claude Code, Codex, Opencode etc. to find vulnerabilities in your code. You don’t need any third-party tools.

Frontier LLM models (especially Opus) are very good at finding vulnerabilities in codebases. With the right skills and a sub-agent architecture, they can outperform any traditional SAST tool. I collected the skills I use in this repository. Load them into any AI coding IDE such as Claude Code, Codex, Opencode etc. to find vulnerabilities in your code. You don’t need any third-party tools.

Utku Sen 🇬🇧

93,957 Aufrufe • vor 5 Monaten

Today we're shipping Oasis Desktop, a Mac app that lets you share local coding agents with your teammates. Oasis Desktop can spin up and share Claude Code, Codex, Pi, OpenCode, Kilo Code, Hermes Agent, and Devin CLI sessions as long as they're installed. Start a session with your team. Bring in Claude Code and say, “What is wrong with auth. The tests have been failing since Tuesday. Help us figure it out.” The agent reads the files and runs the test suite directly on your laptop. When it asks, “Why did we replace the session middleware last week?” your teammate can answer in the exact same session. Completely free - try it out today:

Today we're shipping Oasis Desktop, a Mac app that lets you share local coding agents with your teammates. Oasis Desktop can spin up and share Claude Code, Codex, Pi, OpenCode, Kilo Code, Hermes Agent, and Devin CLI sessions as long as they're installed. Start a session with your team. Bring in Claude Code and say, “What is wrong with auth. The tests have been failing since Tuesday. Help us figure it out.” The agent reads the files and runs the test suite directly on your laptop. When it asks, “Why did we replace the session middleware last week?” your teammate can answer in the exact same session. Completely free - try it out today:

Oasis

214,566 Aufrufe • vor 13 Tagen

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.

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

20,648 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:

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 2 Monaten