正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

A small codex workflow that does WONDER, at almost no cost Ask GPT 5.6 Luna (Max) to use the ImageGen skill for a 3D low-poly object. Then to use the img2threejs skill. Tada. I didn't even spend 1% of my weekly tokens for this.

Nicolas Zullo

8,062 subscribers

334,703 次观看 • 4 天前 •via X (Twitter)

科学技术游戏

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Here's a follow-up, this time with a more ambitious building (+animation, yes!) and with GPT-5.6 Sol (High), in the same thread. The prompt: "Use the ImageGen skill to generate a low-poly 3D mining rig, then use img2threejs to build it. Allow me to animate it with a button."

Here's a follow-up, this time with a more ambitious building (+animation, yes!) and with GPT-5.6 Sol (High), in the same thread. The prompt: "Use the ImageGen skill to generate a low-poly 3D mining rig, then use img2threejs to build it. Allow me to animate it with a button."

Nicolas Zullo

73,329 次观看 • 2 天前

Cristiano to the photographer… “Did you catch my pass” He then does a skill to ask if he caught that one 🥶

Cristiano to the photographer… “Did you catch my pass” He then does a skill to ask if he caught that one 🥶

Al Nassr Zone

1,645,430 次观看 • 2 年前

For skills that include a map, when you equip the skill and then go in and out of the settings tab, the cursor gets stuck and you can't use the skill. Riot Riviere Riot Nu (Marcus Reid)

For skills that include a map, when you equip the skill and then go in and out of the settings tab, the cursor gets stuck and you can't use the skill. Riot Riviere Riot Nu (Marcus Reid)

valohabercisi

442,822 次观看 • 2 个月前

OpenClaw can use Autobrowse to create and iteratively improve a Skill for any workflow. In this Craigslist extraction example we found a 68% speed up and 91% cost savings in 5 iterations. Halfway through, the agent found an exposed endpoint to speed up page navigation.

OpenClaw can use Autobrowse to create and iteratively improve a Skill for any workflow. In this Craigslist extraction example we found a 68% speed up and 91% cost savings in 5 iterations. Halfway through, the agent found an exposed endpoint to speed up page navigation.

Kyle Jeong

108,724 次观看 • 2 个月前

Pro-tip: use a token budget when using /goal in the Codex CLI This is an experimental feature we're exploring, you might have to enable the flag. Ask Codex to do it for you.

Pro-tip: use a token budget when using /goal in the Codex CLI This is an experimental feature we're exploring, you might have to enable the flag. Ask Codex to do it for you.

Kath Korevec

61,810 次观看 • 1 个月前

Today I learnt that you can: - use arrow keys to move an object - use < and > to rotate - use Page Up and Down to move an object up and down I LOVE THE PEOPLE WHO MADE THIS A THING. Kisses for you 😘😘😘 #WoWHousing

Today I learnt that you can: - use arrow keys to move an object - use < and > to rotate - use Page Up and Down to move an object up and down I LOVE THE PEOPLE WHO MADE THIS A THING. Kisses for you 😘😘😘 #WoWHousing

Rage | Tech & RPG

30,142 次观看 • 8 个月前

OpenAI’s GPT-5.6 Sol model can now run inside Claude Code. There are two ways to do it, and both take minutes to set up, here’s how: Option 1, the official plugin: /plugin marketplace add openai/codex-plugin-cc /plugin install codex@openai-codex /reload-plugins, then /codex:setup That unlocks /codex:review, /codex:adversarial-review, and /codex:rescue. Claude writes, GPT critiques, you ship. Option 2, the proxy. One alias makes Sol your main model: alias claudex=‘CLAUDE_CODE_SUBAGENT_MODEL=gpt-5.6-sol CLAUDE_CODE_ALWAYS_ENABLE_EFFORT=1 claude –model gpt-5.6-sol’ Bonus: Claude Code lets you set subagent model and effort yourself. Sol Ultra runs can burn several times the tokens of a base run, so right-sizing delegated work saves real money.

OpenAI’s GPT-5.6 Sol model can now run inside Claude Code. There are two ways to do it, and both take minutes to set up, here’s how: Option 1, the official plugin: /plugin marketplace add openai/codex-plugin-cc /plugin install codex@openai-codex /reload-plugins, then /codex:setup That unlocks /codex:review, /codex:adversarial-review, and /codex:rescue. Claude writes, GPT critiques, you ship. Option 2, the proxy. One alias makes Sol your main model: alias claudex=‘CLAUDE_CODE_SUBAGENT_MODEL=gpt-5.6-sol CLAUDE_CODE_ALWAYS_ENABLE_EFFORT=1 claude –model gpt-5.6-sol’ Bonus: Claude Code lets you set subagent model and effort yourself. Sol Ultra runs can burn several times the tokens of a base run, so right-sizing delegated work saves real money.

Alvaro Cintas

89,994 次观看 • 25 天前

I built this landing page inside Lovable in UNDER 15 minutes. Here’s the workflow: • Dribbble for design inspiration • Use SnapPrompt GPT for the prompt • 21st dev for UI components If you want the FULL video on my EXACT workflow, comment “LOVABLE” and I’ll send it to you

I built this landing page inside Lovable in UNDER 15 minutes. Here’s the workflow: • Dribbble for design inspiration • Use SnapPrompt GPT for the prompt • 21st dev for UI components If you want the FULL video on my EXACT workflow, comment “LOVABLE” and I’ll send it to you

Prajwal Tomar

45,804 次观看 • 5 个月前

Working on a “Hand-Off to Mac” way to load the chats from the Codex Remote Control for iOS app to the Codex App Codex app-server doesn’t quite support a live update So I decided to find a workaround A button that forces the closing of the Codex App and reopening it in the chat created from iPhone Would you use this button?

Working on a “Hand-Off to Mac” way to load the chats from the Codex Remote Control for iOS app to the Codex App Codex app-server doesn’t quite support a live update So I decided to find a workaround A button that forces the closing of the Codex App and reopening it in the chat created from iPhone Would you use this button?

Emanuele Di Pietro

24,351 次观看 • 4 个月前

You can do professional animation with a low budget! I use recicled paper, 8$ USD for 500 sheets, and my animation pegbar, 1$ USD, the puncher is cheap too. This are the materials i use to do traditional animation.

You can do professional animation with a low budget! I use recicled paper, 8$ USD for 500 sheets, and my animation pegbar, 1$ USD, the puncher is cheap too. This are the materials i use to do traditional animation.

Tlauz - Open Sketch Comms

785,712 次观看 • 2 年前

To help cleave in adds phase, you can use a macro like this which will use your skill on your previous target. This is very useful for line cleaves like WWT, Geirskogul Shadowbringers, etc. I use it mostly to cleave the cat while it jumps around so I don't have to target it.

To help cleave in adds phase, you can use a macro like this which will use your skill on your previous target. This is very useful for line cleaves like WWT, Geirskogul Shadowbringers, etc. I use it mostly to cleave the cat while it jumps around so I don't have to target it.

iTrolledU

54,173 次观看 • 1 年前

Sharing my new skill! It keeps track of high-signal X accounts for top AI news, papers, projects, etc. Total gamechanger for me. Built with X MCP tools. Give your agent the skill and tell it to generate the artifact with top stories. Works for Codex, Claude, Hermes, OpenClaw, or whatever you use. 3 steps: 1. Set up X MCP - X API: 2. Install skill here: 3. Run prompt: "Use the x-agent-intelligence skill to build a self-contained local feed from my X MCP connection; ask for my source handles if needed, save feed.html, and validate it." It should generate a nice, beautiful HTML artifact like the one shown in the clip. You can tune it however you want. You can then set a schedule/automation to do this daily or whatever cadence you prefer. I have it every 4 hours. You will need to curate the X accounts yourself, but I have shared a few good ones under the assets. You can ask your agent to tune it to however you like. I have also shared my personal feed with our community here: I understand if it gets tricky to set up. Please reach out to me in the community forum. I plan to do a little tutorial or live session soon to help others reproduce the process. You can also store the feed as a wiki, as I have in my own implementation, but that's optional. If you encounter any issues or have ideas on how to improve it, please open a PR.

Sharing my new skill! It keeps track of high-signal X accounts for top AI news, papers, projects, etc. Total gamechanger for me. Built with X MCP tools. Give your agent the skill and tell it to generate the artifact with top stories. Works for Codex, Claude, Hermes, OpenClaw, or whatever you use. 3 steps: 1. Set up X MCP - X API: 2. Install skill here: 3. Run prompt: "Use the x-agent-intelligence skill to build a self-contained local feed from my X MCP connection; ask for my source handles if needed, save feed.html, and validate it." It should generate a nice, beautiful HTML artifact like the one shown in the clip. You can tune it however you want. You can then set a schedule/automation to do this daily or whatever cadence you prefer. I have it every 4 hours. You will need to curate the X accounts yourself, but I have shared a few good ones under the assets. You can ask your agent to tune it to however you like. I have also shared my personal feed with our community here: I understand if it gets tricky to set up. Please reach out to me in the community forum. I plan to do a little tutorial or live session soon to help others reproduce the process. You can also store the feed as a wiki, as I have in my own implementation, but that's optional. If you encounter any issues or have ideas on how to improve it, please open a PR.

elvis

71,341 次观看 • 19 天前

❤️‍🔥 GPT 5.6 Sol is genuinely absurd for 3D scrolling websites now. An AI that can one shot designs this good means that the web design industry as a whole is in serious trouble If you’re a designer and your workflow hasn’t fundamentally changed in the past year, it's time to pivot

❤️‍🔥 GPT 5.6 Sol is genuinely absurd for 3D scrolling websites now. An AI that can one shot designs this good means that the web design industry as a whole is in serious trouble If you’re a designer and your workflow hasn’t fundamentally changed in the past year, it's time to pivot

Viktor Oddy

42,574 次观看 • 17 天前

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

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 次观看 • 5 个月前

Can Fable write good TypeGPU code? I’d say so, but make sure to use the TypeGPU skill, written by yours truly: It made a pretty nice generic horde game from scratch, no engine involved. Assets by the amazing Kay Lousberg: I paid for one of the packs and I encourage you to do the same. No better time to support 3D artists :D

Can Fable write good TypeGPU code? I’d say so, but make sure to use the TypeGPU skill, written by yours truly: It made a pretty nice generic horde game from scratch, no engine involved. Assets by the amazing Kay Lousberg: I paid for one of the packs and I encourage you to do the same. No better time to support 3D artists :D

Konrad Reczko

22,291 次观看 • 1 个月前

I am getting super excited to share my workflow for sending the After Effects 3D Motion Tracked Camera to Unreal Engine and then bringing the 3D renders back to AE for compositing. It will be a free tutorial NEXT WEEK from School of Motion.

I am getting super excited to share my workflow for sending the After Effects 3D Motion Tracked Camera to Unreal Engine and then bringing the 3D renders back to AE for compositing. It will be a free tutorial NEXT WEEK from School of Motion.

Aharon Rabinowitz

13,028 次观看 • 1 年前

🚨 GPT-5.6 features flag can be enabled in the codex > So we can see ui but can't use the model directly > Only trusted users are given access for now Personal life update: my adhd get worse with vacation as it fuck up my routine that's why I was not active lately, suggest something to solve this 🫂

🚨 GPT-5.6 features flag can be enabled in the codex > So we can see ui but can't use the model directly > Only trusted users are given access for now Personal life update: my adhd get worse with vacation as it fuck up my routine that's why I was not active lately, suggest something to solve this 🫂

Chetaslua

354,860 次观看 • 1 个月前

❒ Once you've trained the bot with your information field, ask for the part of the code that will serve as the bot's workspace. ❒ The bot will search for tokens on @pumpdotfun and @RaydiumProtocol, analyze them and then snipe them instantly. ❒ Use this specific query to approach #DeepSeek

❒ Once you've trained the bot with your information field, ask for the part of the code that will serve as the bot's workspace. ❒ The bot will search for tokens on @pumpdotfun and @RaydiumProtocol, analyze them and then snipe them instantly. ❒ Use this specific query to approach #DeepSeek

NoName

43,845 次观看 • 1 年前