Loading video...

Video Failed to Load

Go Home

Mood: agents optimizing kernels Claude won on kernel optimization: gemm_bf16 at 1.19x vs Codex's 0.94x. Codex was faster (~1.3h vs ~3.4h) but produced no reinjectable optimizations. Claude used (hipBLASLt) as a drop-in replacement for the custom Triton kernel. For Codex, shape mismatch caused slight regression. Still improving, open sourcing...

realSharonZhou's profile picture

Sharon Zhou

27,371 subscribers

23,583 views • 2 months ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

We're open sourcing dmux. Our internal tool for running Codex and Claude Code swarms. - tmux + worktrees + claude/codex/opencode - hooks for worktree automation - a/b claude vs codex - manage worktrees - multi-project per session ...more. ➡️
0:24

We're open sourcing dmux. Our internal tool for running Codex and Claude Code swarms. - tmux + worktrees + claude/codex/opencode - hooks for worktree automation - a/b claude vs codex - manage worktrees - multi-project per session ...more. ➡️

Justin Schroeder

327,126 views • 3 months ago

Soon as a mini-app on Alien App and in the App Store. Used Antigravity + Claude + Codex + Rive for this.
1:01

Soon as a mini-app on Alien App and in the App Store. Used Antigravity + Claude + Codex + Rive for this.

Andrey Rybin

21,805 views • 3 months ago

Linux Kernel is Now Vibe Coded Usage of AI (Claude, Codex, etc.) is exploding in the Linux world. At the current rate, the Linux Kernel will be predominantly developed using AI sometime this year.
13:53

Linux Kernel is Now Vibe Coded Usage of AI (Claude, Codex, etc.) is exploding in the Linux world. At the current rate, the Linux Kernel will be predominantly developed using AI sometime this year.

The Lunduke Journal

16,246 views • 18 days ago

Knowing Codex is better for complex tasks makes me bullish on Chamath Palihapitiya and 8090 He points out that Codex is much better for meaty, large problems, while Claude feels good for more day to day work. We’re improving model personality so Codex feels even better for pair programming. But we think pair programming with agents is a local optimization. The longer term pattern is delegation. Most people just aren’t asking agents to do ambitious enough work. The people who are delegating use Codex.
0:31

Knowing Codex is better for complex tasks makes me bullish on Chamath Palihapitiya and 8090 He points out that Codex is much better for meaty, large problems, while Claude feels good for more day to day work. We’re improving model personality so Codex feels even better for pair programming. But we think pair programming with agents is a local optimization. The longer term pattern is delegation. Most people just aren’t asking agents to do ambitious enough work. The people who are delegating use Codex.

Rohan Varma

27,703 views • 1 month ago

It's here: We just hit superhuman performance on AI kernel optimization! Real customer models & production settings. Not toy problems (what I typically see). This is the year that Claude writes its own kernels, Codex its own kernels, for every new GPU that it wants to run on -- something that takes months to port between GPU generations today. This has a massive impact to scaling intelligence. More compute means getting the next frontier model sooner.
2:48

It's here: We just hit superhuman performance on AI kernel optimization! Real customer models & production settings. Not toy problems (what I typically see). This is the year that Claude writes its own kernels, Codex its own kernels, for every new GPU that it wants to run on -- something that takes months to port between GPU generations today. This has a massive impact to scaling intelligence. More compute means getting the next frontier model sooner.

Sharon Zhou

240,793 views • 3 months ago

I gave both Codex and Claude Code full access to my twitter account. Codex spark (powered by Cerebras) did a full GTM outreach workflow 3x FASTER than Claude code, and used way less tool calls.
3:39

I gave both Codex and Claude Code full access to my twitter account. Codex spark (powered by Cerebras) did a full GTM outreach workflow 3x FASTER than Claude code, and used way less tool calls.

Sarah Chieng

75,746 views • 3 months ago

Clawdbot creator, Peter Steinberger says Opus is the best model overall, but Codex is his go-to for coding. He trusts Codex to handle big codebases with almost no mistakes. It’s more reliable and needs less handholding, which makes him faster. Claude Code can work too, but it requires more effort and tricks. For serious tasks, Codex feels like a dependable coworker.
1:42

Clawdbot creator, Peter Steinberger says Opus is the best model overall, but Codex is his go-to for coding. He trusts Codex to handle big codebases with almost no mistakes. It’s more reliable and needs less handholding, which makes him faster. Claude Code can work too, but it requires more effort and tricks. For serious tasks, Codex feels like a dependable coworker.

Wes Roth

230,226 views • 4 months ago

Claude Sonnet 4.6 vs GPT 5.3 Codex Same Prompt in Cursor (Neutral Harness) - Default Settings! GPT 5.3 Codex took - 2 mins Claude Sonnet 4.6 - 7 mins Cheaper than Sonnet 4.6! Faster than Sonnet 4.6! But I'm not sure if it's more craftier than Sonnet 4.6 because Sonnet's got a taste! Claude Sonnet 4.6 had a better result (aesthetically) and also more solid techstack - GPT 5.3 codes meanwhile just got the job done!
0:36

Claude Sonnet 4.6 vs GPT 5.3 Codex Same Prompt in Cursor (Neutral Harness) - Default Settings! GPT 5.3 Codex took - 2 mins Claude Sonnet 4.6 - 7 mins Cheaper than Sonnet 4.6! Faster than Sonnet 4.6! But I'm not sure if it's more craftier than Sonnet 4.6 because Sonnet's got a taste! Claude Sonnet 4.6 had a better result (aesthetically) and also more solid techstack - GPT 5.3 codes meanwhile just got the job done!

1LittleCoder💻

142,760 views • 3 months ago

Michael Scott, the most qualified person to judge Claude vs Codex, has entered the chat.
1:49

Michael Scott, the most qualified person to judge Claude vs Codex, has entered the chat.

Siddhartha Saxena

56,298 views • 2 days ago

Introducing multi-agent orchestration in Oz, with support for Claude Code, Codex and the Warp Agent. Use /orchestrate to delegate complex tasks across a team of agents, locally or in the cloud.
2:17

Introducing multi-agent orchestration in Oz, with support for Claude Code, Codex and the Warp Agent. Use /orchestrate to delegate complex tasks across a team of agents, locally or in the cloud.

Warp

1,184,124 views • 21 days ago

I built a new plugin! You can now trigger Codex from Claude Code! Use the Codex plugin for Claude Code to delegate tasks to Codex or have Codex review your changes using your ChatGPT subscription. Start by installing the plugin:
0:39

I built a new plugin! You can now trigger Codex from Claude Code! Use the Codex plugin for Claude Code to delegate tasks to Codex or have Codex review your changes using your ChatGPT subscription. Start by installing the plugin:

dominik kundel

1,282,093 views • 2 months ago

I built a wrapper around Claude Code and Codex that uses my subscription! Works on mobile and web🔥 - Work on multiple projet in one UI - Create worktree - Spawn Docker container for maximum isolation - Schedule Claude/Codex session It uses the CLI
0:58

I built a wrapper around Claude Code and Codex that uses my subscription! Works on mobile and web🔥 - Work on multiple projet in one UI - Create worktree - Spawn Docker container for maximum isolation - Schedule Claude/Codex session It uses the CLI

Stan Girard

25,808 views • 3 months ago

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
1:17

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

304,035 views • 3 months ago

Coding agents that actually get better the more your team uses them. Introducing Hivemind: continual learning for AI coding agents. Hivemind turns the traces from every agent your team runs (Claude Code, Codex, Cursor, Hermes, OpenClaw, Pi) into reusable skills, then pushes those skills across all of them. All on your cloud storage. Now with SkillOpt built in, your skills get trained: +19.1 points of accuracy in Claude Code, +24.8 in Codex, best or tied on all 52 setups tested. Open source, one line install.
0:38

Coding agents that actually get better the more your team uses them. Introducing Hivemind: continual learning for AI coding agents. Hivemind turns the traces from every agent your team runs (Claude Code, Codex, Cursor, Hermes, OpenClaw, Pi) into reusable skills, then pushes those skills across all of them. All on your cloud storage. Now with SkillOpt built in, your skills get trained: +19.1 points of accuracy in Claude Code, +24.8 in Codex, best or tied on all 52 setups tested. Open source, one line install.

Davit

393,791 views • 1 day ago

Today we’re releasing Venice Skills. A better interface for agents using the Venice API, ready for Cursor, Claude Code, Codex, Hermes, and other agent runtimes. 👉
0:21

Today we’re releasing Venice Skills. A better interface for agents using the Venice API, ready for Cursor, Claude Code, Codex, Hermes, and other agent runtimes. 👉

Sabrina

61,625 views • 1 month ago

I made Claude Code and Codex talk to each other. No APIs. No special protocol. Just a terminal. smux lets agents create, read, and act on terminals. the terminal becomes a shared interface. this enables agent-to-agent communication. Now Claude Code and Codex can hold hands 🤝 Try it now ↓
0:39

I made Claude Code and Codex talk to each other. No APIs. No special protocol. Just a terminal. smux lets agents create, read, and act on terminals. the terminal becomes a shared interface. this enables agent-to-agent communication. Now Claude Code and Codex can hold hands 🤝 Try it now ↓

shawn

315,068 views • 2 months ago

🇵🇱 Dzisiaj stworzyłem Claude Code Math Prover (13-minutowy film pokazuje jak to działa). Claude Code Opus 4.6 orkiestruje cały przepływ pracy. Deleguje podzadania do różnych agentów: - OpenAI Codex 5.3 (badacz, rozwiązuje, recenzent) - jak widać można używać równolegle i Codex'a i Claude Code. - Claude Code (planista, rozwiązuje). - Wykorzystuje MCP poprzez lean-lsp-mcp dowodzenie twierdzeń za pomocą Lean. Używam Team Agents z tmux do pokazania jak Claude Code deleguje zadania do Codex i do siebie ale do subagentów. SKILL - codex - napisałem skilla do orkiestracji Codex'a -------------------- 🇬🇧Claude Code Math Prover (13-minute video) I made today. Claude Code Opus 4.6 orchestrates the workflow. It delegates subtasks to different agents: - OpenAI Codex 5.3 (researcher, solver, reviewer) - so we can use both solution Codex ad Claude Code - Claude Code (planner, solver). - It uses MCP via lean-lsp-mcp, which enables agentic interaction with the Lean theorem prover. I use Claude Code team agents for this task so you can see how Claude Code delegate all task. SKILL - I wrote skill for codex orchestration
13:43

🇵🇱 Dzisiaj stworzyłem Claude Code Math Prover (13-minutowy film pokazuje jak to działa). Claude Code Opus 4.6 orkiestruje cały przepływ pracy. Deleguje podzadania do różnych agentów: - OpenAI Codex 5.3 (badacz, rozwiązuje, recenzent) - jak widać można używać równolegle i Codex'a i Claude Code. - Claude Code (planista, rozwiązuje). - Wykorzystuje MCP poprzez lean-lsp-mcp dowodzenie twierdzeń za pomocą Lean. Używam Team Agents z tmux do pokazania jak Claude Code deleguje zadania do Codex i do siebie ale do subagentów. SKILL - codex - napisałem skilla do orkiestracji Codex'a -------------------- 🇬🇧Claude Code Math Prover (13-minute video) I made today. Claude Code Opus 4.6 orchestrates the workflow. It delegates subtasks to different agents: - OpenAI Codex 5.3 (researcher, solver, reviewer) - so we can use both solution Codex ad Claude Code - Claude Code (planner, solver). - It uses MCP via lean-lsp-mcp, which enables agentic interaction with the Lean theorem prover. I use Claude Code team agents for this task so you can see how Claude Code delegate all task. SKILL - I wrote skill for codex orchestration

Remek Kinas

46,560 views • 4 months ago

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.
0:30

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

179,802 views • 19 hours ago

Introducing @𝚠𝚊𝚕𝚕𝚎𝚝𝚌𝚑𝚊𝚗/𝚖𝚌𝚙 Prompt to Transact from your Local pk accounts via AI agents like Claude, Codex, and more! Built on top of Base MCP skills, for WalletChan.eth
1:00

Introducing @𝚠𝚊𝚕𝚕𝚎𝚝𝚌𝚑𝚊𝚗/𝚖𝚌𝚙 Prompt to Transact from your Local pk accounts via AI agents like Claude, Codex, and more! Built on top of Base MCP skills, for WalletChan.eth

apoorv.eth

18,146 views • 9 days ago

Introducing MagicPath 2.0. MagicPath is now a multiplayer canvas for humans and agents like Codex or Claude Code to design and build with AI. Use your codebase, grab data from anywhere, and see the agents work in real time as a team while building fully functional prototypes.
1:29

Introducing MagicPath 2.0. MagicPath is now a multiplayer canvas for humans and agents like Codex or Claude Code to design and build with AI. Use your codebase, grab data from anywhere, and see the agents work in real time as a team while building fully functional prototypes.

Pietro Schirano

247,298 views • 26 days ago