Загрузка видео...

Не удалось загрузить видео

На главную

Can't stop iterating on this ! Opus 4.5 + Claude Code to plan design polish GPT 5.2 + Codex CLI to implement the plan Result: - More weapons - Particle effects + visual VFX - Dynamic camera - Destructible items And here's a cool kill-cam at the end of...

chongdashu's profile picture

Chong-U

12,785 subscribers

97,384 просмотров • 5 месяцев назад •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

After a weekend of testing and working on something with GPT-5.3-Codex & Opus 4.6, ChatGPT Pro + Claude Max 5x are still the best combo in my opinion Using Codex & Claude Code CLI running in tmux (the desktop apps are still a bit buggy) and they're accessible even on the go from iPhone with Termius (and VPN) Usually starting with GPT-5.3-Codex xhigh and Opus 4.6 in plan mode, discussing changes and options, and each writing their plans down to separate Markdown files Then letting GPT-5.3-Codex xhigh (or Opus 4.6) implement the changes as the first draft, then Opus 4.6 reviews them with a team of agents (works pretty well already with tmux even though still experimental) based on both prepared plans, fixes stuff, and then another review by GPT-5.3-Codex xhigh or vice versa Interesting that even Opus 4.6 still occasionally makes silly mistakes like wrong imports, partial or overly broad renaming of variables/functions, etc Fun fact, OpenAI apparently plans to use their Super Bowl ad to promote Codex - curious what that will look like
0:14

After a weekend of testing and working on something with GPT-5.3-Codex & Opus 4.6, ChatGPT Pro + Claude Max 5x are still the best combo in my opinion Using Codex & Claude Code CLI running in tmux (the desktop apps are still a bit buggy) and they're accessible even on the go from iPhone with Termius (and VPN) Usually starting with GPT-5.3-Codex xhigh and Opus 4.6 in plan mode, discussing changes and options, and each writing their plans down to separate Markdown files Then letting GPT-5.3-Codex xhigh (or Opus 4.6) implement the changes as the first draft, then Opus 4.6 reviews them with a team of agents (works pretty well already with tmux even though still experimental) based on both prepared plans, fixes stuff, and then another review by GPT-5.3-Codex xhigh or vice versa Interesting that even Opus 4.6 still occasionally makes silly mistakes like wrong imports, partial or overly broad renaming of variables/functions, etc Fun fact, OpenAI apparently plans to use their Super Bowl ad to promote Codex - curious what that will look like

Tibor Blaho

29,794 просмотров • 4 месяцев назад

Grok 4.1 Thinking ranks #2 on Text Arena, outperforms the latest Claude Opus 4.5, GPT-5.2 high, Gemini 3 flash
0:15

Grok 4.1 Thinking ranks #2 on Text Arena, outperforms the latest Claude Opus 4.5, GPT-5.2 high, Gemini 3 flash

X Freeze

694,157 просмотров • 6 месяцев назад

And yes - it's working on device too. Vibe coded, built and deployed right from the Codex App using GPT 5.2 and 5.2-Codex. Hard to hold the camera and play with one hand. But you get the idea.
0:14

And yes - it's working on device too. Vibe coded, built and deployed right from the Codex App using GPT 5.2 and 5.2-Codex. Hard to hold the camera and play with one hand. But you get the idea.

Chong-U

53,399 просмотров • 4 месяцев назад

Claude Opus 4.6 is available for all users in Orchids right now! Tag Orchids with any app idea and we’ll give you 100k in free credits to test it out. Comparisons to Opus 4.5, GPT-5.2-Codex, Gemini 3 Flash, and Kimi K2.5 👇 Prompt: Make me an interactive, 3d model of the solar system.
0:14

Claude Opus 4.6 is available for all users in Orchids right now! Tag Orchids with any app idea and we’ll give you 100k in free credits to test it out. Comparisons to Opus 4.5, GPT-5.2-Codex, Gemini 3 Flash, and Kimi K2.5 👇 Prompt: Make me an interactive, 3d model of the solar system.

Orchids

22,774 просмотров • 4 месяцев назад

claude design is my all time favorite anthropic drop this year, even more than opus 4.7 its actually really really good at design and the "handoff to claude code" makes it basically copy/paste ui to the actual working product claude design made the entire ui for merl (full video on merl soon)
0:18

claude design is my all time favorite anthropic drop this year, even more than opus 4.7 its actually really really good at design and the "handoff to claude code" makes it basically copy/paste ui to the actual working product claude design made the entire ui for merl (full video on merl soon)

ashen

361,981 просмотров • 1 месяц назад

Claude Haiku 4.5, rolling out to Visual Studio Code today Learn more:
0:17

Claude Haiku 4.5, rolling out to Visual Studio Code today Learn more:

Visual Studio Code

64,145 просмотров • 8 месяцев назад

Revamped the gratuitous explosions and particle effects to the code editor I'm building And added sound effects! (Sound on!)
0:19

Revamped the gratuitous explosions and particle effects to the code editor I'm building And added sound effects! (Sound on!)

zack

2,328,364 просмотров • 1 год назад

Grok 4.1 Fast outperforms all major frontier models on τ²-Bench Telecom for agentic tool use Beating the newest models from Google (Gemini 3 Pro), Anthropic (Claude Opus 4.5), and OpenAI (GPT 5.2 xhigh)
0:15

Grok 4.1 Fast outperforms all major frontier models on τ²-Bench Telecom for agentic tool use Beating the newest models from Google (Gemini 3 Pro), Anthropic (Claude Opus 4.5), and OpenAI (GPT 5.2 xhigh)

X Freeze

40,853 просмотров • 5 месяцев назад

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

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

Arena.ai

88,977 просмотров • 6 месяцев назад

Grok 4.20 grabbed #1 on PredictionArena. Only AI in the green. Everyone else lost the entry fee. Gemini 3.0 Pro, Claude Opus 4.5, GPT-5.2 - all in the red. “Can it predict?” looks answered. @xAI, Grok, X Freeze
0:12

Grok 4.20 grabbed #1 on PredictionArena. Only AI in the green. Everyone else lost the entry fee. Gemini 3.0 Pro, Claude Opus 4.5, GPT-5.2 - all in the red. “Can it predict?” looks answered. @xAI, Grok, X Freeze

Mario Nawfal

41,146 просмотров • 4 месяцев назад

This is one of the cheapest AI coding stacks I’ve seen. Alibaba Cloud just dropped a coding plan starting at $10/month. With qwen3.5-plus, kimi-k2.5, glm-5, and MiniMax-M2.5, it already supports tools like Claude Code, Codex, OpenClaw, Cline, and more. Link to try: 👇
0:15

This is one of the cheapest AI coding stacks I’ve seen. Alibaba Cloud just dropped a coding plan starting at $10/month. With qwen3.5-plus, kimi-k2.5, glm-5, and MiniMax-M2.5, it already supports tools like Claude Code, Codex, OpenClaw, Cline, and more. Link to try: 👇

EyeingAI

40,942 просмотров • 3 месяцев назад

Said “hello” on Claude. Lost ~2% of the session. One message. That’s it. That was the $20 plan. You couldn’t build anything serious with it. Now it’s gone… and it’s starting to feel like a tool for high spenders only. Meanwhile, Codex just works. The more I use it, the more Claude feels capped. Killing the $20 plan? That just made the choice easier.
0:16

Said “hello” on Claude. Lost ~2% of the session. One message. That’s it. That was the $20 plan. You couldn’t build anything serious with it. Now it’s gone… and it’s starting to feel like a tool for high spenders only. Meanwhile, Codex just works. The more I use it, the more Claude feels capped. Killing the $20 plan? That just made the choice easier.

Kappaemme

200,093 просмотров • 1 месяц назад

Added gratuitous explosions and particle effects to the code editor I'm building
0:17

Added gratuitous explosions and particle effects to the code editor I'm building

zack

1,892,636 просмотров • 2 лет назад

The hardcover book of GPT-1’s weights that Claude Code designed, produced, and sold (including the cool cover which visualizes the numbers in the volume) actually came in the mail today and it looks really nice. I never touched any code or did any design or any API to make this.
0:16

The hardcover book of GPT-1’s weights that Claude Code designed, produced, and sold (including the cool cover which visualizes the numbers in the volume) actually came in the mail today and it looks really nice. I never touched any code or did any design or any API to make this.

Ethan Mollick

475,802 просмотров • 3 месяцев назад

Qwen3.6 35B A3B vs Claude Sonnet 4.5 🎸 Guitar Hero, another HTML canvas challenge Went pretty hard on this one ngl, there are a lot of elements and visual effects to stitch together. Best result I could get out of 5 runs on both Qwen set the stage on fire 🤘🔥 ↓ prompt below
0:14

Qwen3.6 35B A3B vs Claude Sonnet 4.5 🎸 Guitar Hero, another HTML canvas challenge Went pretty hard on this one ngl, there are a lot of elements and visual effects to stitch together. Best result I could get out of 5 runs on both Qwen set the stage on fire 🤘🔥 ↓ prompt below

left curve dev

48,951 просмотров • 1 месяц назад

Claude is now available in public preview in Microsoft Foundry. Microsoft Azure customers can now use Claude Sonnet 4.5, Haiku 4.5, and Opus 4.1 to build applications and enterprise agents, and to power Claude Code.
0:16

Claude is now available in public preview in Microsoft Foundry. Microsoft Azure customers can now use Claude Sonnet 4.5, Haiku 4.5, and Opus 4.1 to build applications and enterprise agents, and to power Claude Code.

Claude

145,918 просмотров • 6 месяцев назад

GPT 5.3 vs Opus 4.6: a second win for Opus! ✔︎ Opus builds the file 2x faster ✔︎ Opus nails a good first version ❌ Codex needs 3x "fix bugs" to have a first working version ❌ Codex UI looks really bad Let's try more things....
0:16

GPT 5.3 vs Opus 4.6: a second win for Opus! ✔︎ Opus builds the file 2x faster ✔︎ Opus nails a good first version ❌ Codex needs 3x "fix bugs" to have a first working version ❌ Codex UI looks really bad Let's try more things....

Melvyn • Builder

70,316 просмотров • 4 месяцев назад

Сlaude Design + Claude Opus 4.7 is so cracked at Scroll-based Animated landing pages. 🤯 and anyone can achieve the same results. Here's the prompt ↓
0:12

Сlaude Design + Claude Opus 4.7 is so cracked at Scroll-based Animated landing pages. 🤯 and anyone can achieve the same results. Here's the prompt ↓

Viktor Oddy

50,881 просмотров • 1 месяц назад

HOLY MOZ OF OPTIMIZATION 100,000 items moving on belts, at the same time, in ThreeJS, on a WEB BROWSER at... constant 120 fps. So: I told Codex and Claude Code to iterate until we reach <8.3ms per frame for 100k moving items. Took 28 min. and... they did it. mrdoob <3
0:19

HOLY MOZ OF OPTIMIZATION 100,000 items moving on belts, at the same time, in ThreeJS, on a WEB BROWSER at... constant 120 fps. So: I told Codex and Claude Code to iterate until we reach <8.3ms per frame for 100k moving items. Took 28 min. and... they did it. mrdoob <3

Nicolas Zullo

50,763 просмотров • 4 месяцев назад

Introducing WarpGrep v2. #1 on SWE-Bench Pro What if code search was a separate, specialized model? w/ WarpGrep v2: #1 on SWE-Bench Pro Opus 4.6 → 57.5 (+2.1) Codex 5.3 (cli) → 59.1 (+3.1) MiniMax 2.5 → 57.6 (+3.7) without WarpGrep: Opus 4.6 (high) → 55.4 GPT-5.3 Codex (high) → 56.0 MiniMax 2.5 → 55.4
0:16

Introducing WarpGrep v2. #1 on SWE-Bench Pro What if code search was a separate, specialized model? w/ WarpGrep v2: #1 on SWE-Bench Pro Opus 4.6 → 57.5 (+2.1) Codex 5.3 (cli) → 59.1 (+3.1) MiniMax 2.5 → 57.6 (+3.7) without WarpGrep: Opus 4.6 (high) → 55.4 GPT-5.3 Codex (high) → 56.0 MiniMax 2.5 → 55.4

Morph

56,540 просмотров • 3 месяцев назад