Загрузка видео...

Не удалось загрузить видео

Возникла проблема при загрузке этого видео. Это может быть связано с временными проблемами сети или видео может быть недоступно.

На главную

Claude Opus 4.6 vs GPT-5.3 Codex aren't just different models. They're different engineers. Opus 4.6: → 1M token context window → Reads the whole codebase before deciding → Asks "should we do this?" → Failure mode: overanalyzes, hesitates GPT-5.3 Codex: → 200K tokens, built for speed → Decides fast,... show more

The Startup Ideas Podcast (SIP) 🧃

43,234 subscribers

59,604 просмотров • 5 месяцев назад •via X (Twitter)

Наука и технологии

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

🇵🇱 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

🇵🇱 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

46,691 просмотров • 5 месяцев назад

Here's how I use BOTH Codex + Claude Code to vibe code games For my Final Fantasy Tactics game: → 1. GPT 5.4/5.3-Codex/5.2 → 2. Opus 4.6 → 3. Nano Banana 2 → 4. Playwright → Plans + AskUserQuestion → Queue + interrupt prompts → Auto test + bug fixing FULL workflow👇 00:00 Intro 02:07 Step 1: Game Overview 03:27 Step 2: Nano Banana 2 for Portraits 05:12 Step 3: GPT 5.2 / 5.4 for Planning 09:56 Step 4: AskUserQuestion in Codex 12:02 Step 5: Saving your plans and prompts 13:43 Step 6: GPT 5.3-Codex for Implementing 16:34 Step 7: Implementing Cutscenes 20:49 Step 8: LazyGit + Yazi - Staying in the terminal 22:46 Step 9: Reviewing the changes 23:49 Step 10: Steering Codex - Queued Prompts 25:36 Steo 11: Steering Codex - Interrupt Prompts 26:45 Steo 12: Claude Code and Opus 4.6 27:16 Step 13: xHigh Reasoning for Tricky Bugs 28:50 Step 14: Playwright for automated testing + fixes 30:56 Step 15: Claude Code Plan Mode Previews 32:56 Step 16: Steering Claude Code - Add Notes to Plans 35:05 Wrap-Up

Here's how I use BOTH Codex + Claude Code to vibe code games For my Final Fantasy Tactics game: → 1. GPT 5.4/5.3-Codex/5.2 → 2. Opus 4.6 → 3. Nano Banana 2 → 4. Playwright → Plans + AskUserQuestion → Queue + interrupt prompts → Auto test + bug fixing FULL workflow👇 00:00 Intro 02:07 Step 1: Game Overview 03:27 Step 2: Nano Banana 2 for Portraits 05:12 Step 3: GPT 5.2 / 5.4 for Planning 09:56 Step 4: AskUserQuestion in Codex 12:02 Step 5: Saving your plans and prompts 13:43 Step 6: GPT 5.3-Codex for Implementing 16:34 Step 7: Implementing Cutscenes 20:49 Step 8: LazyGit + Yazi - Staying in the terminal 22:46 Step 9: Reviewing the changes 23:49 Step 10: Steering Codex - Queued Prompts 25:36 Steo 11: Steering Codex - Interrupt Prompts 26:45 Steo 12: Claude Code and Opus 4.6 27:16 Step 13: xHigh Reasoning for Tricky Bugs 28:50 Step 14: Playwright for automated testing + fixes 30:56 Step 15: Claude Code Plan Mode Previews 32:56 Step 16: Steering Claude Code - Add Notes to Plans 35:05 Wrap-Up

Chong-U

47,264 просмотров • 4 месяцев назад

Opus 4.6 FAST mode is now available in Copilot CLI. In 30 minutes, I was able to implement a new "Command Center" view for `/fleet` mode. When you launch your agent swarm, we automatically open a panel to track the status of your subagents. Should I ship this on monday?

Opus 4.6 FAST mode is now available in Copilot CLI. In 30 minutes, I was able to implement a new "Command Center" view for `/fleet` mode. When you launch your agent swarm, we automatically open a panel to track the status of your subagents. Should I ship this on monday?

Evan Boyle

47,607 просмотров • 5 месяцев назад

this was one of the biggest weeks in AI because claude opus 4.6 and gpt-5.3 codex dropped basically at the SAME time. they solve the same problem in VERY different ways. - opus spins up agent teams and disappears for a while. - codex stays with you and ships ridiculously fast. i tested them both for you in this episode of The Startup Ideas Podcast (SIP) 🧃 (on yt/spot/apple/X) with my pal Morgan we set them up live, tuned them properly, and had each one build a polymarket clone from scratch. you’ll see where each one shines, where it struggles, and which approach actually fits how you work. if you’re trying to decide what to use next, this episode will save you a lot of trial and error.

this was one of the biggest weeks in AI because claude opus 4.6 and gpt-5.3 codex dropped basically at the SAME time. they solve the same problem in VERY different ways. - opus spins up agent teams and disappears for a while. - codex stays with you and ships ridiculously fast. i tested them both for you in this episode of The Startup Ideas Podcast (SIP) 🧃 (on yt/spot/apple/X) with my pal Morgan we set them up live, tuned them properly, and had each one build a polymarket clone from scratch. you’ll see where each one shines, where it struggles, and which approach actually fits how you work. if you’re trying to decide what to use next, this episode will save you a lot of trial and error.

GREG ISENBERG

92,293 просмотров • 5 месяцев назад

FREE Claude Opus 4.8. FREE GPT 5.5. All free. 7,200 credits. I tested it myself - works. The platform is Gumloop(.)com. Chat interface plus connections into different services. Company raised $50M Here's the exact setup: → Register via Google OAuth or Microsoft OAuth → During onboarding, answer the questions and select every option you can → When asked to connect services, pick Apify, Semrush, and Reducto - no login needed for any of them → Skip the Slack connection → Done correctly, you land 7,200 credits minimum Models inside: Opus 4.6 through 4.8, GPT 5.3 Codex, GPT 5.4, GPT 5.5, Gemini 3 Flash, Gemini 3.1 Pro, Gemini 3.5 Flash, DeepSeek V4 Flash and Pro, Kimi K2.6. No card needed anywhere in this flow. I ran through it myself - fully working. Bookmark this before it gets patched.

FREE Claude Opus 4.8. FREE GPT 5.5. All free. 7,200 credits. I tested it myself - works. The platform is Gumloop(.)com. Chat interface plus connections into different services. Company raised $50M Here's the exact setup: → Register via Google OAuth or Microsoft OAuth → During onboarding, answer the questions and select every option you can → When asked to connect services, pick Apify, Semrush, and Reducto - no login needed for any of them → Skip the Slack connection → Done correctly, you land 7,200 credits minimum Models inside: Opus 4.6 through 4.8, GPT 5.3 Codex, GPT 5.4, GPT 5.5, Gemini 3 Flash, Gemini 3.1 Pro, Gemini 3.5 Flash, DeepSeek V4 Flash and Pro, Kimi K2.6. No card needed anywhere in this flow. I ran through it myself - fully working. Bookmark this before it gets patched.

Atenov int.

22,779 просмотров • 1 месяц назад

Spent the last few days vibe coding on my NVIDIA DGX Spark. Here's what I learned. Qwen 3.5 122B took one minute and nine seconds to respond "Hi how are you doing". Unusable for vibe coding. Gemma 4 was fast but built a dot instead of a first person shooter game. GPT-OSS 120B was the sweet spot. Fast, capable, and actually produced working HTML. Open source models running locally are not replacing Claude Opus 4.6 or Codex with GPT 5.4. Not even close. But they're getting better every month. The new DGX Spark Bench is live on Real-world benchmarks for local models on local hardware. This is just the start. Full video below.

Spent the last few days vibe coding on my NVIDIA DGX Spark. Here's what I learned. Qwen 3.5 122B took one minute and nine seconds to respond "Hi how are you doing". Unusable for vibe coding. Gemma 4 was fast but built a dot instead of a first person shooter game. GPT-OSS 120B was the sweet spot. Fast, capable, and actually produced working HTML. Open source models running locally are not replacing Claude Opus 4.6 or Codex with GPT 5.4. Not even close. But they're getting better every month. The new DGX Spark Bench is live on Real-world benchmarks for local models on local hardware. This is just the start. Full video below.

BridgeMind

57,304 просмотров • 3 месяцев назад

Opus 4.6 vs GPT-5.4 (High) (6/9) Testing out how well these models to with cloth physics simulation, and honestly both where pretty close here but my god I am shocked how good GPT 5.4 is with optimizing this scene whilst opus 4.6 felt quite janky and lower fps. GPT 5.4 also got the cutting working properly whilst Opus was just floating about. I do want to heavily stress the fact that making this prompt, Opus 4.6 cost the whole 100% of the session ($20 pro plan) + $3 in credits whilst GPT 5.4 only cost 10% of the usage. prompt: Build a premium Vite + React interactive cloth simulation of a cozy room curtain using real particle/constraint physics, with structural + shear springs, damping, collisions, and stable real-time deformation. Users should be able to drag the curtain, add wind, and cut constraints, while the experience stays polished, visually elegant, and numerically stable.

Opus 4.6 vs GPT-5.4 (High) (6/9) Testing out how well these models to with cloth physics simulation, and honestly both where pretty close here but my god I am shocked how good GPT 5.4 is with optimizing this scene whilst opus 4.6 felt quite janky and lower fps. GPT 5.4 also got the cutting working properly whilst Opus was just floating about. I do want to heavily stress the fact that making this prompt, Opus 4.6 cost the whole 100% of the session ($20 pro plan) + $3 in credits whilst GPT 5.4 only cost 10% of the usage. prompt: Build a premium Vite + React interactive cloth simulation of a cozy room curtain using real particle/constraint physics, with structural + shear springs, damping, collisions, and stable real-time deformation. Users should be able to drag the curtain, add wind, and cut constraints, while the experience stays polished, visually elegant, and numerically stable.

Dev Ed

414,134 просмотров • 4 месяцев назад

THE 64 MINUTE OPENAI CODEX MASTERCLASS IS HERE if you've been meaning to learn Codex, this is the episode for you, we cover: 1/ Claude vs Codex (what's better?) 2/How to run Claude Code inside Codex (really cool) 3/Why GPT 5.5 changed everything for browser agents 4/How to create skills (reusable agents you build once and call by name forever) 5/How to connect Notion with surgical permissions (one database, not the whole workspace) 6/How to use Remotion inside Codex to create videos 7/ How to one-shot full mobile apps in Swift 8/The 4 projects to run on day one to get up to speed fast shoutout to Riley Brown for coming onto The Startup Ideas Podcast (SIP) 🧃 for the 5th time. every episode he delivers. this one is the Codex masterclass. if you've been meaning to learn Codex, this is the episode. 100% free i just want to see you build your ideas. watch

THE 64 MINUTE OPENAI CODEX MASTERCLASS IS HERE if you've been meaning to learn Codex, this is the episode for you, we cover: 1/ Claude vs Codex (what's better?) 2/How to run Claude Code inside Codex (really cool) 3/Why GPT 5.5 changed everything for browser agents 4/How to create skills (reusable agents you build once and call by name forever) 5/How to connect Notion with surgical permissions (one database, not the whole workspace) 6/How to use Remotion inside Codex to create videos 7/ How to one-shot full mobile apps in Swift 8/The 4 projects to run on day one to get up to speed fast shoutout to Riley Brown for coming onto The Startup Ideas Podcast (SIP) 🧃 for the 5th time. every episode he delivers. this one is the Codex masterclass. if you've been meaning to learn Codex, this is the episode. 100% free i just want to see you build your ideas. watch

GREG ISENBERG

199,205 просмотров • 3 месяцев назад

I just built an entire app in 7 minutes using Codex Spark. EveryMCP: a universal MCP server installer that configures 15+ coding agents from a single CLI command. 12 Codex Spark subagents. All running in parallel. At the same time. The project itself isn't complicated, but just imagine what this looks like when you scale the complexity. My setup: • Codex 5.3 High to plan • Codex 5.3 Medium to orchestrate • 12 Codex Spark agents (xhigh) to implement in one shot Spark isn't competing with the big models. It's a different tool entirely. You orchestrate it. You run it in swarms. And it moves at a speed that wasn't possible before, even for the top 1% of AI coders. More complex workflows coming soon. Comment below if you want me to tell you how I did it.

I just built an entire app in 7 minutes using Codex Spark. EveryMCP: a universal MCP server installer that configures 15+ coding agents from a single CLI command. 12 Codex Spark subagents. All running in parallel. At the same time. The project itself isn't complicated, but just imagine what this looks like when you scale the complexity. My setup: • Codex 5.3 High to plan • Codex 5.3 Medium to orchestrate • 12 Codex Spark agents (xhigh) to implement in one shot Spark isn't competing with the big models. It's a different tool entirely. You orchestrate it. You run it in swarms. And it moves at a speed that wasn't possible before, even for the top 1% of AI coders. More complex workflows coming soon. Comment below if you want me to tell you how I did it.

am.will

16,916 просмотров • 5 месяцев назад

This is so cool. In the next Codex update, multi agents will get a massive flexibility upgrade. "Hey Codex, when you implement this plan, I want you to delegate all the lower complexity tasks to GPT 5.3 Spark subagents" Instead of needing to create 100 different custom agent roles for different situations, you can just prompt your agent to spawn whatever model or reasoning level you want. With only natural language. No config files. No pre-defined roles. Just tell the orchestrator what to use and it listens.

This is so cool. In the next Codex update, multi agents will get a massive flexibility upgrade. "Hey Codex, when you implement this plan, I want you to delegate all the lower complexity tasks to GPT 5.3 Spark subagents" Instead of needing to create 100 different custom agent roles for different situations, you can just prompt your agent to spawn whatever model or reasoning level you want. With only natural language. No config files. No pre-defined roles. Just tell the orchestrator what to use and it listens.

am.will

128,125 просмотров • 4 месяцев назад

With all the buzz around the Codex App, OpenAI Developers quietly snuck out a new CLI update (0.94.0) as well. And boy is it an important update! Codex Plan mode is now officially released to the general audience! I am very excited about this one as it has a really strong prompt that is unlike any other plan mode I've personally used. Codex Plan mode doesn't necessarily just ask you 3 questions up front. It goes, collects context, asks questions, collects more context, asks more questions (sometimes), and then writes an incredibly high quality plan. It is my favorite implementation of plan mode thus far. It also comes with Codex's own version of "AskUserQuestion!" Although, it only works in Plan mode for now. They really need to allow people to use it in Code mode as well, but one win at a time. npm i -g @openai/codex Below is a demo of how it works. Let me know what you think!

With all the buzz around the Codex App, OpenAI Developers quietly snuck out a new CLI update (0.94.0) as well. And boy is it an important update! Codex Plan mode is now officially released to the general audience! I am very excited about this one as it has a really strong prompt that is unlike any other plan mode I've personally used. Codex Plan mode doesn't necessarily just ask you 3 questions up front. It goes, collects context, asks questions, collects more context, asks more questions (sometimes), and then writes an incredibly high quality plan. It is my favorite implementation of plan mode thus far. It also comes with Codex's own version of "AskUserQuestion!" Although, it only works in Plan mode for now. They really need to allow people to use it in Code mode as well, but one win at a time. npm i -g @openai/codex Below is a demo of how it works. Let me know what you think!

am.will

57,121 просмотров • 5 месяцев назад

CLAUDE OPUS 4.7 TRANSFORMED MY TRADING. i didn't write a single line of code here's exactly what happened: → day 1: opus 4.7 dropped. i killed all my 4.6 bots. → day 2: asked claude to rebuild them. v2 shipped in 18 min. → day 3: went live with on perps. the 3 things that changed in 4.7: → reads chart + orderflow + news in ONE call it's much faster & more capable. and the models will only get better from here. the bot is not the edge. the speed of iteration is the edge. 4.6 shipped a strategy in 4 days. 4.7 ships in 18 minutes. because we know, traders who ignore AI will be left behind. bookmark this, start building with OPUS 4.7 asap. You only need Claude + laptop + 1 hour/day. Giving This Free for 24 hours. To get it: 1. Comment the word 'Claude' 2. Like and Retweet this post 3. Follow me Marry Evan (so i can DM you)

CLAUDE OPUS 4.7 TRANSFORMED MY TRADING. i didn't write a single line of code here's exactly what happened: → day 1: opus 4.7 dropped. i killed all my 4.6 bots. → day 2: asked claude to rebuild them. v2 shipped in 18 min. → day 3: went live with on perps. the 3 things that changed in 4.7: → reads chart + orderflow + news in ONE call it's much faster & more capable. and the models will only get better from here. the bot is not the edge. the speed of iteration is the edge. 4.6 shipped a strategy in 4 days. 4.7 ships in 18 minutes. because we know, traders who ignore AI will be left behind. bookmark this, start building with OPUS 4.7 asap. You only need Claude + laptop + 1 hour/day. Giving This Free for 24 hours. To get it: 1. Comment the word 'Claude' 2. Like and Retweet this post 3. Follow me Marry Evan (so i can DM you)

Marry Evan

20,101 просмотров • 3 месяцев назад

FREE Fable 5, Opus 4.8, Sonnet 5, and GPT-5.6 in one IDE. Alibaba built it, 520 credits at signup - one Sonnet 5 message eats 4. It's called Accio. Web or Windows desktop, both free. Registration takes 30 seconds via Google or email. Inside: → Fable 5 for creative and long-context work. → Opus 4.6 through 4.8 - the full Anthropic frontier lineup. → Sonnet 5 for speed and reasoning at pennies per message. → GPT-5.5 for OpenAI native tasks. → Gemini 3.1 Pro and 3.5 Flash for multimodal. Real math: 520 credits divided by 4 = 130 Sonnet 5 messages in your first week. Cheaper models drop that even further. Anthropic charges $20/month for the same access with weekly limits. Custom MCP support built in. Profile > Settings > MCP. Every agent workflow you've built for Claude Desktop ports over instantly. Setup: → Go to accio(.)com → Sign up with Google → 520 credits land automatically → Pick your model and start firing prompts Bookmark this before Alibaba puts it behind a paywall.

Atenov int.

31,157 просмотров • 12 дней назад

Free Opus 4.8, GPT 5.5, and Gemini 3.1 Pro. 50 credits, no card. The platform behind it is valued at $4 billion. Most people are burning API credits testing prompts across three different subscriptions. Opus for one thing, GPT for another, Gemini when the other two fail. > ClickUp just made that unnecessary. Sign up with Google or a corporate email. 50 credits land immediately. 1 message costs 1 credit - that's 50 real conversations with Opus 4.8 before you spend a dollar. Models available: Opus 4.8, GPT 5.5, Gemini 3.1 Pro, Gemini 3.5 Flash. Custom MCP support if you want your own tools wired in. This isn't a startup burning VC money on a growth hack. ClickUp was valued at $4 billion in 2021, raised $535M, and runs ~100,000 paying clients - McDonald's, Booking, Netflix, Papa Johns. The AI pivot landed in November 2025. Same infrastructure, same userbase, new models bolted on top. → Go to app(.)clickup(.)com → Sign up with Google → 50 credits land automatically → Pick your model and start Bookmark this before the free tier gets capped.

Free Opus 4.8, GPT 5.5, and Gemini 3.1 Pro. 50 credits, no card. The platform behind it is valued at $4 billion. Most people are burning API credits testing prompts across three different subscriptions. Opus for one thing, GPT for another, Gemini when the other two fail. > ClickUp just made that unnecessary. Sign up with Google or a corporate email. 50 credits land immediately. 1 message costs 1 credit - that's 50 real conversations with Opus 4.8 before you spend a dollar. Models available: Opus 4.8, GPT 5.5, Gemini 3.1 Pro, Gemini 3.5 Flash. Custom MCP support if you want your own tools wired in. This isn't a startup burning VC money on a growth hack. ClickUp was valued at $4 billion in 2021, raised $535M, and runs ~100,000 paying clients - McDonald's, Booking, Netflix, Papa Johns. The AI pivot landed in November 2025. Same infrastructure, same userbase, new models bolted on top. → Go to app(.)clickup(.)com → Sign up with Google → 50 credits land automatically → Pick your model and start Bookmark this before the free tier gets capped.

Atenov int.

10,846 просмотров • 25 дней назад

🚨 JUST IN: Claude got a huge update today and I'm flattered to be a part of it. As of now, Claude Opus 4.6 can build mobile apps and prepare shipping them on the Apple + Google app stores. We just launched Shipper a new package that empowers Claude to: → Build complete mobile apps → Recreate existing apps → Assure iOS & Android compatibility → Autofill listings for both app stores (app icon, images, descriptions, keywords, privacy policy etc) Claude Opus 4.6 can do all of the above in one prompt for ~$0.17/app... Publishable from the first prompt & built in 5 mins, not months. You can try it on Shipper by asking Claude to "create an AI chatbot like Perplexity" or "eBay style marketplace app for local goods". To celebrate this huge step forward, if you comment "SHIP" you will get free credits.

🚨 JUST IN: Claude got a huge update today and I'm flattered to be a part of it. As of now, Claude Opus 4.6 can build mobile apps and prepare shipping them on the Apple + Google app stores. We just launched Shipper a new package that empowers Claude to: → Build complete mobile apps → Recreate existing apps → Assure iOS & Android compatibility → Autofill listings for both app stores (app icon, images, descriptions, keywords, privacy policy etc) Claude Opus 4.6 can do all of the above in one prompt for ~$0.17/app... Publishable from the first prompt & built in 5 mins, not months. You can try it on Shipper by asking Claude to "create an AI chatbot like Perplexity" or "eBay style marketplace app for local goods". To celebrate this huge step forward, if you comment "SHIP" you will get free credits.

David Ch

448,710 просмотров • 5 месяцев назад

introducing OpenBench v1, an open framework for measuring AI performance and efficiency for your codebase and use case. Companies are realizing that you can't simply tokenmaxx, and are frantically looking for better ways to use and measure AI use and efficiency. One approach is evidenced by the rise in model routers: OpenRouter, Cloudflare, Databricks, Vercel, and now Ramp to name a few. But they'll also need the ability to evaluate how agents are performing in their actual use cases and codebase. A good example is DoorDash's recent evals on their codebase and prs. This will become even more important as companies explore different model + harness combinations. OpenBench will be built to this direction, focusing on the cross between correctness vs efficiency in both token use and latency. Starting off, OpenBench makes it easy for anyone to add to the task set, and run a variety of harness + models. The framework also makes it easy to add any custom harness variant, for example I've been testing codex variants with ablations against the stock codex harness. OpenBench will also have tooling to help with discovering/adding reliable tasks from your repo. Today I have integrated harnesses: codex, claude, cursor, devin, grok build, pi, and eval'ed them for different models like gpt 5.6-sol, GLM 5.2, Kimi K3, Grok 4.5, etc. measuring correctness %, token use (in/out/cache), and latency.

introducing OpenBench v1, an open framework for measuring AI performance and efficiency for your codebase and use case. Companies are realizing that you can't simply tokenmaxx, and are frantically looking for better ways to use and measure AI use and efficiency. One approach is evidenced by the rise in model routers: OpenRouter, Cloudflare, Databricks, Vercel, and now Ramp to name a few. But they'll also need the ability to evaluate how agents are performing in their actual use cases and codebase. A good example is DoorDash's recent evals on their codebase and prs. This will become even more important as companies explore different model + harness combinations. OpenBench will be built to this direction, focusing on the cross between correctness vs efficiency in both token use and latency. Starting off, OpenBench makes it easy for anyone to add to the task set, and run a variety of harness + models. The framework also makes it easy to add any custom harness variant, for example I've been testing codex variants with ablations against the stock codex harness. OpenBench will also have tooling to help with discovering/adding reliable tasks from your repo. Today I have integrated harnesses: codex, claude, cursor, devin, grok build, pi, and eval'ed them for different models like gpt 5.6-sol, GLM 5.2, Kimi K3, Grok 4.5, etc. measuring correctness %, token use (in/out/cache), and latency.

Matthew Lam

116,971 просмотров • 7 дней назад

$I just compared Claude Code vs Codex vs Cursor CLI The task was to build a Next.js app with Tailwind 4 and shadcn components to collect customer feedback and showcase it with a widget. I gave all three the same prompt and let them go for 30 minutes to see what they came up with. Claude Code with Opus 4.1 Even though I told it to set up the app in the existing project folder, it tried to create a directory for it. After I interrupted and told it not to do that, it built a demo form and landing page with no errors. I had to ask it to make the demo interactive so users could submit a testimonial and preview it. The landing page looked like AI and was pretty basic, but it worked and it was done in a fraction of the time of the others. Total tokens used: 33k Codex with GPT-5 At the end of the 30 minutes I just could not get Codex to produce a working app. It got stuck in a loop of not being able to set up Tailwind 4 and despite many, MANY, attempts, I ended up with a "failed to compile" error. Total tokens used: 102k Cursor Agent with GPT-5 This was the slowest agent by far and a couple of times I actually thought it got stuck in a loop and was close to Ctrl+C'ing to cancel it. The TUI is really nice though, especially how it shows diffs and it did eventually build a working app (after one or two slight errors that needed fixing) The demo was interactive and it had a very minimal design that looked bare but also a lot less like an "AI generated" app than the Opus 4.1 design. It also wasn't too chatty and just did what it needed to do! Code quality was on a par with Opus 4.1, but it did use 5.5x as many tokens to get there. Still cheaper than Opus on a direct comparison but not when you factor in a Claude Code Max subscription. Total tokens: 188k I'll be able to do a proper comparison and record some videos when I'm back from holiday but for now, Opus is still the more capable model out of the box and Claude Code is the more complete CLI product. It will be interesting to see how Cursor evolve their CLI though with commands and subagents because I think with GPT-5 they have a real shot at providing competition for Claude Code if they can optimise output to get similar quality with less tokens. Jump to 0:40 in the video to see the two apps. Which do you think is which? ;)$

I just compared Claude Code vs Codex vs Cursor CLI The task was to build a Next.js app with Tailwind 4 and shadcn components to collect customer feedback and showcase it with a widget. I gave all three the same prompt and let them go for 30 minutes to see what they came up with. Claude Code with Opus 4.1 Even though I told it to set up the app in the existing project folder, it tried to create a directory for it. After I interrupted and told it not to do that, it built a demo form and landing page with no errors. I had to ask it to make the demo interactive so users could submit a testimonial and preview it. The landing page looked like AI and was pretty basic, but it worked and it was done in a fraction of the time of the others. Total tokens used: 33k Codex with GPT-5 At the end of the 30 minutes I just could not get Codex to produce a working app. It got stuck in a loop of not being able to set up Tailwind 4 and despite many, MANY, attempts, I ended up with a "failed to compile" error. Total tokens used: 102k Cursor Agent with GPT-5 This was the slowest agent by far and a couple of times I actually thought it got stuck in a loop and was close to Ctrl+C'ing to cancel it. The TUI is really nice though, especially how it shows diffs and it did eventually build a working app (after one or two slight errors that needed fixing) The demo was interactive and it had a very minimal design that looked bare but also a lot less like an "AI generated" app than the Opus 4.1 design. It also wasn't too chatty and just did what it needed to do! Code quality was on a par with Opus 4.1, but it did use 5.5x as many tokens to get there. Still cheaper than Opus on a direct comparison but not when you factor in a Claude Code Max subscription. Total tokens: 188k I'll be able to do a proper comparison and record some videos when I'm back from holiday but for now, Opus is still the more capable model out of the box and Claude Code is the more complete CLI product. It will be interesting to see how Cursor evolve their CLI though with commands and subagents because I think with GPT-5 they have a real shot at providing competition for Claude Code if they can optimise output to get similar quality with less tokens. Jump to 0:40 in the video to see the two apps. Which do you think is which? ;)

Ian Nuttall

194,949 просмотров • 11 месяцев назад

Introducing 🌸 Kanna – a web ui for Claude Code + Codex running right in your browser (and my first open source project!) It's sort of like if Claude Code & Codex had a baby with a much better ui/ux 💅 Here's what makes Kanna special: 🔀 One-click switch between Claude Code / Codex 🌐 Runs in your browser on localhost - no app switching 🧩 Embedded split terminals, persisted between chats with a beautiful horizontal scrolling UX 📁 Full project file browser built in, embedded editor coming soon too. Coming soon: 🔒 End-to-end encryption + remote access via reverse proxy 🌿 Git integration, diffs, PRs 🧱 Plugins I wanted to replace switching between cursor, the github app, browser & (most recently) the codex app. The browser is hardest to recreate yet also the most flexible so it makes sense to build in the browser itself. Install in 5 seconds: bun install -g kanna-code then just type: kanna Kanna is purely a ui/ux layer. It uses your existing CLIs, is 100% compliant & no data ever leaves your machine. If running claude or codex in your terminal works, kanna works too. Kanna natively supports every tool call, model, reasoning effort, fast mode, plan mode, compaction, user questions, web searching, skills, agents, mcps, everything. There are a few libraries that do this but none that I found as comprehensive. All feedback welcome!

Introducing 🌸 Kanna – a web ui for Claude Code + Codex running right in your browser (and my first open source project!) It's sort of like if Claude Code & Codex had a baby with a much better ui/ux 💅 Here's what makes Kanna special: 🔀 One-click switch between Claude Code / Codex 🌐 Runs in your browser on localhost - no app switching 🧩 Embedded split terminals, persisted between chats with a beautiful horizontal scrolling UX 📁 Full project file browser built in, embedded editor coming soon too. Coming soon: 🔒 End-to-end encryption + remote access via reverse proxy 🌿 Git integration, diffs, PRs 🧱 Plugins I wanted to replace switching between cursor, the github app, browser & (most recently) the codex app. The browser is hardest to recreate yet also the most flexible so it makes sense to build in the browser itself. Install in 5 seconds: bun install -g kanna-code then just type: kanna Kanna is purely a ui/ux layer. It uses your existing CLIs, is 100% compliant & no data ever leaves your machine. If running claude or codex in your terminal works, kanna works too. Kanna natively supports every tool call, model, reasoning effort, fast mode, plan mode, compaction, user questions, web searching, skills, agents, mcps, everything. There are a few libraries that do this but none that I found as comprehensive. All feedback welcome!

Superdaddy

43,285 просмотров • 4 месяцев назад

We added a device tool bar to the Codex in-app browser, so it's easier to build and test responsive apps! Now, you can have Codex test your app in different dimensions, so it can fix bugs & improve UI for every device. Just click the 3 dots on the right of the URL bar to use it! As part of this change, we also: - improved the speed of browser use (~30% in my vibe testing) - tightened the animation of the cursor - added a way to hide the composer in full screen mode - fixed a few bugs for browser use in Windows Oliver Tepman and John Nastos cooked on this one! Try it out and let us know what you think!

We added a device tool bar to the Codex in-app browser, so it's easier to build and test responsive apps! Now, you can have Codex test your app in different dimensions, so it can fix bugs & improve UI for every device. Just click the 3 dots on the right of the URL bar to use it! As part of this change, we also: - improved the speed of browser use (~30% in my vibe testing) - tightened the animation of the cursor - added a way to hide the composer in full screen mode - fixed a few bugs for browser use in Windows Oliver Tepman and John Nastos cooked on this one! Try it out and let us know what you think!

James Sun

148,198 просмотров • 2 месяцев назад

OpenAI’s hottest app isn’t ChatGPT—it’s Codex. In the last few weeks alone, the Codex team shipped a desktop app, GPT-5.3 Codex (a new flagship model), and Spark, the fastest coding model I’ve ever used. Usage has grown fivefold since January and over a million people now use Codex weekly. Codex was also the app that OpenAI chose to run an ad for in the Super Bowl. I talked to Thibault (Tibo), head of Codex, and Andrew (Andrew Ambrosino), a member of technical staff who built the Codex app, for Every 📧’s AI & I about what OpenAI is building and how they’re using it internally. We get into: - Why they built a GUI instead of a terminal. Terminals work for quick tasks, they say, but feel limiting when you’re running multiple agents in parallel. The IDE, meanwhile, overwhelms users—and the Codex team wants the AI to dynamically decide which tools to show you for a given task. - How they’re teaching the model to read between the lines. Codex is great at following instructions, but optimize too hard in that direction, and it starts taking you literally—like copying a typo directly into the code. The team obsesses over this tradeoff, and is also introducing “personalities,” modes users can toggle between that control how blunt or supportive the model feels. - How OpenAI uses its own coding agent. Codex lets you schedule prompts to run on a recurring basis, and the team has dozens of automations running at all times. For example, one scans for merge conflicts every couple of hours so code is always ready to ship, and another picks a random file from the codebase multiple times a day and hunts for bugs no one would've gone looking for. - Why speed is a dimension of intelligence. OpenAI’s newest model (Spark) is so fast that they actually slow it down so you can read the output. They see the speed enabling three things: staying super in the flow, replacing brittle developer tools with intelligent ones that can adapt on the fly, and redirecting the model mid-task— especially with voice—so coding starts to feel more and more like a conversation. - Code review is the next bottleneck. Models can generate code faster than ever, but someone still has to verify that it works. The team is exploring a future where the model proves its own fix works—retracing the click path a user would take, screenshotting the results, and attaching the evidence to a pull request. This is a must-watch for anyone who uses AI coding agents—and is curious about the future of programming. Watch below! Timestamps: Introduction: 00:01:27 OpenAI’s evolving bet on its coding agent: 00:05:27 The choice to invest in a GUI (over a terminal): 00:09:42 The AI workflows that the Codex team relies on to ship: 00:20:38 Teaching Codex how to read between the lines: 00:26:45 Building affordances for a lightening fast model: 00:28:45 Why speed is a dimension of intelligence: 00:33:15 Code review is the next bottleneck for coding agents: 00:36:30 How the Codex team positions against the competition: 00:41:24

OpenAI’s hottest app isn’t ChatGPT—it’s Codex. In the last few weeks alone, the Codex team shipped a desktop app, GPT-5.3 Codex (a new flagship model), and Spark, the fastest coding model I’ve ever used. Usage has grown fivefold since January and over a million people now use Codex weekly. Codex was also the app that OpenAI chose to run an ad for in the Super Bowl. I talked to Thibault (Tibo), head of Codex, and Andrew (Andrew Ambrosino), a member of technical staff who built the Codex app, for Every 📧’s AI & I about what OpenAI is building and how they’re using it internally. We get into: - Why they built a GUI instead of a terminal. Terminals work for quick tasks, they say, but feel limiting when you’re running multiple agents in parallel. The IDE, meanwhile, overwhelms users—and the Codex team wants the AI to dynamically decide which tools to show you for a given task. - How they’re teaching the model to read between the lines. Codex is great at following instructions, but optimize too hard in that direction, and it starts taking you literally—like copying a typo directly into the code. The team obsesses over this tradeoff, and is also introducing “personalities,” modes users can toggle between that control how blunt or supportive the model feels. - How OpenAI uses its own coding agent. Codex lets you schedule prompts to run on a recurring basis, and the team has dozens of automations running at all times. For example, one scans for merge conflicts every couple of hours so code is always ready to ship, and another picks a random file from the codebase multiple times a day and hunts for bugs no one would've gone looking for. - Why speed is a dimension of intelligence. OpenAI’s newest model (Spark) is so fast that they actually slow it down so you can read the output. They see the speed enabling three things: staying super in the flow, replacing brittle developer tools with intelligent ones that can adapt on the fly, and redirecting the model mid-task— especially with voice—so coding starts to feel more and more like a conversation. - Code review is the next bottleneck. Models can generate code faster than ever, but someone still has to verify that it works. The team is exploring a future where the model proves its own fix works—retracing the click path a user would take, screenshotting the results, and attaching the evidence to a pull request. This is a must-watch for anyone who uses AI coding agents—and is curious about the future of programming. Watch below! Timestamps: Introduction: 00:01:27 OpenAI’s evolving bet on its coding agent: 00:05:27 The choice to invest in a GUI (over a terminal): 00:09:42 The AI workflows that the Codex team relies on to ship: 00:20:38 Teaching Codex how to read between the lines: 00:26:45 Building affordances for a lightening fast model: 00:28:45 Why speed is a dimension of intelligence: 00:33:15 Code review is the next bottleneck for coding agents: 00:36:30 How the Codex team positions against the competition: 00:41:24

Dan Shipper 📧

15,588 просмотров • 5 месяцев назад