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。

Claude Code's effort parameter is something you need to keep in mind before starting any task It's not just about picking the right model anymore (Haiku, Sonnet, Opus). Now you also need to think about which effort level to use before each task. One tip I always go back... show more

Daniel San

32,501 subscribers

66,147 次观看 • 4 个月前 •via X (Twitter)

教育新闻政治科学技术

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

Sonnet 5 is here. It's worse than Opus 4.8 on nearly every benchmark... Does that mean it's useless? Absolutely not. Use it with Claude Code Dynamic Workflows! 1. /model set to Sonnet 5 2. /effort set to Ultracode 3. Any complex task will kick off a dynamic workflow This will only become more powerful when Fable is back. You'll use Fable 5 as the superintelligent advisor and Sonnet 5 as the fast and efficient implementer.

Sonnet 5 is here. It's worse than Opus 4.8 on nearly every benchmark... Does that mean it's useless? Absolutely not. Use it with Claude Code Dynamic Workflows! 1. /model set to Sonnet 5 2. /effort set to Ultracode 3. Any complex task will kick off a dynamic workflow This will only become more powerful when Fable is back. You'll use Fable 5 as the superintelligent advisor and Sonnet 5 as the fast and efficient implementer.

Dan McAteer

660,625 次观看 • 15 天前

Claude Code's new dynamic workflow is the real deal. 🤖 Why it matters: It's not just a chain of prompts — it's an autonomous agent swarm. 1. Set model to Opus 4.8 + reasoning effort /ultracode 2. Claude detects complexity, writes orchestration script on the fly 3. Spawns a parallel fleet of coordinated subagents Operator takeaway: This is the first time I've seen an agent actually decompose and delegate autonomously without a rigid framework. Have you tried it yet? 🚀

Claude Code's new dynamic workflow is the real deal. 🤖 Why it matters: It's not just a chain of prompts — it's an autonomous agent swarm. 1. Set model to Opus 4.8 + reasoning effort /ultracode 2. Claude detects complexity, writes orchestration script on the fly 3. Spawns a parallel fleet of coordinated subagents Operator takeaway: This is the first time I've seen an agent actually decompose and delegate autonomously without a rigid framework. Have you tried it yet? 🚀

EK

197,752 次观看 • 1 个月前

Everyone is dunking on Sonnet 5 for losing to Opus 4.8 on benchmarks. They're all making the same mistake, judging a teammate by a solo test. Sonnet 5 was never built to win alone. Set the model to Sonnet 5, effort to Ultracode, and any complex task auto-kicks a dynamic workflow where it plans, spawns agents, executes and checks its own work, fast and cheap. When Fable 5 comes back, the setup gets stupid good. Fable 5 decides what to build, Sonnet 5 actually builds it. You stop paying flagship prices to do grunt work.

Everyone is dunking on Sonnet 5 for losing to Opus 4.8 on benchmarks. They're all making the same mistake, judging a teammate by a solo test. Sonnet 5 was never built to win alone. Set the model to Sonnet 5, effort to Ultracode, and any complex task auto-kicks a dynamic workflow where it plans, spawns agents, executes and checks its own work, fast and cheap. When Fable 5 comes back, the setup gets stupid good. Fable 5 decides what to build, Sonnet 5 actually builds it. You stop paying flagship prices to do grunt work.

0xMarioNawfal

98,313 次观看 • 14 天前

Bruhhh I literally just told AI to do research about today's premier league matches , log in to my sporty bet account and place bets based on its analysis And .... It did just that! 🤯😲 (This cost me almost 3$ using opus 4.6 for this task 😭 ) Going to turn this into a full fledged product / project The age of AI is here and it's not stopping 🚀

Bruhhh I literally just told AI to do research about today's premier league matches , log in to my sporty bet account and place bets based on its analysis And .... It did just that! 🤯😲 (This cost me almost 3$ using opus 4.6 for this task 😭 ) Going to turn this into a full fledged product / project The age of AI is here and it's not stopping 🚀

victory

73,962 次观看 • 5 个月前

The Dennis Cometti quote I always come back to is when Josh Hill hit the post three times with one kick (R12 2010)... “Just when you think a game is boring, Bruce, you see something you've not seen before, and it makes it all worthwhile.” Vale Dennis

The Dennis Cometti quote I always come back to is when Josh Hill hit the post three times with one kick (R12 2010)... “Just when you think a game is boring, Bruce, you see something you've not seen before, and it makes it all worthwhile.” Vale Dennis

Oliver Gigacz

44,648 次观看 • 4 个月前

Elon Musk: If you don't understand things at a detailed level, you cannot make a decision. “At SpaceX, almost all my time is spent on engineering and design. It's probably 80% or 90%. I think in order to make the right decisions, you have to understand something. If you don't understand something at a detailed level, you cannot make a decision.” From: Interview at SXSW 2018, March 11, 2018

Elon Musk: If you don't understand things at a detailed level, you cannot make a decision. “At SpaceX, almost all my time is spent on engineering and design. It's probably 80% or 90%. I think in order to make the right decisions, you have to understand something. If you don't understand something at a detailed level, you cannot make a decision.” From: Interview at SXSW 2018, March 11, 2018

ELON CLIPS

54,371 次观看 • 5 个月前

The best hitters I’ve worked with know how to reset before each pitch. Comment “3” for my ‘3 Step Checklist to Master The Time Between Pitches’ 📈 Not before each at bat, or game. Each pitch. Not just mechanically, mentally, too. You can’t hit with a crowded head. Let the last pitch or at-bat go. One pitch at a time. One slow breath at a time. One simple thought at time. ——— Now, go win. ——— Save this for when you need it. Send this to someone who lets the game speed them up. ——— Comment “3” for my ‘3 Step Checklist to Master The Time Between Pitches’ 📈

The best hitters I’ve worked with know how to reset before each pitch. Comment “3” for my ‘3 Step Checklist to Master The Time Between Pitches’ 📈 Not before each at bat, or game. Each pitch. Not just mechanically, mentally, too. You can’t hit with a crowded head. Let the last pitch or at-bat go. One pitch at a time. One slow breath at a time. One simple thought at time. ——— Now, go win. ——— Save this for when you need it. Send this to someone who lets the game speed them up. ——— Comment “3” for my ‘3 Step Checklist to Master The Time Between Pitches’ 📈

Trey Hannam

23,366 次观看 • 3 个月前

Sometimes a connection enters your field and it's unexplainable, you just remember them. There's no forcing this remembrance. You just know. Both can sit in silence and recognize each other like you've done this a thousand lifetimes before. It's the unspoken energy that forms between two souls that gets woven into the Akashic field, and when you meet again, there's no logic that can define what this is. It's just felt. It's also not about forcing or trying to make sense of it. It's about allowing what's real to move through you effortlessly. Because when the connection is real, you don't need proof. The proof is trusting what you feel. ~ Elizabethcopolla ✨🙌🏽💫

Sometimes a connection enters your field and it's unexplainable, you just remember them. There's no forcing this remembrance. You just know. Both can sit in silence and recognize each other like you've done this a thousand lifetimes before. It's the unspoken energy that forms between two souls that gets woven into the Akashic field, and when you meet again, there's no logic that can define what this is. It's just felt. It's also not about forcing or trying to make sense of it. It's about allowing what's real to move through you effortlessly. Because when the connection is real, you don't need proof. The proof is trusting what you feel. ~ Elizabethcopolla ✨🙌🏽💫

🧬Maxpein🧬

17,851 次观看 • 6 个月前

I find it pretty hilarious when people try to preach about how homosexuality is wrong because it's "in The Bible"... 🏳️‍🌈🏳️‍⚧️ "Marge, just about everything is a sin. You ever sat down and read this thing? "Technically, we're not allowed to go to the bathroom...'

Sensitive content

I find it pretty hilarious when people try to preach about how homosexuality is wrong because it's "in The Bible"... 🏳️‍🌈🏳️‍⚧️ "Marge, just about everything is a sin. You ever sat down and read this thing? "Technically, we're not allowed to go to the bathroom...'

Simpsons Daily Glavins 🏳️‍🌈🏳️‍⚧️

49,762 次观看 • 1 个月前

I just want to take a moment to say thank you to everyone. We fight, we argue, and I know some of you get mad at my tweets sometimes🤣🤣 but at the end of the day, it's all love, no hate. I truly appreciate each and every one of you for sticking around and for your support. Thanksgiving is all about gratitude and today l'm feeling extra grateful for all of you. Let's keep lifting each other up even when we don't always agree and we don’t need to agree🤣🤣 I'm ending this thanksgiving with love in my heart, and I want you to know I love you all❣️ #Grateful #Thanksgiving

I just want to take a moment to say thank you to everyone. We fight, we argue, and I know some of you get mad at my tweets sometimes🤣🤣 but at the end of the day, it's all love, no hate. I truly appreciate each and every one of you for sticking around and for your support. Thanksgiving is all about gratitude and today l'm feeling extra grateful for all of you. Let's keep lifting each other up even when we don't always agree and we don’t need to agree🤣🤣 I'm ending this thanksgiving with love in my heart, and I want you to know I love you all❣️ #Grateful #Thanksgiving

Big Love

16,073 次观看 • 1 年前

This is how you can personalize sports and finance on Perplexity today. This way, when your favorite team is about to play a game, you didn’t have to go search. Live action widget just takes over your Lock Screen. Similar things planned for earnings calls for the finance watchlist. More personalization and customization are being worked on and coming in March. Idea is for you to not even have to think of asking stuff. The AI should just do that work for you and give it to you without any effort.

This is how you can personalize sports and finance on Perplexity today. This way, when your favorite team is about to play a game, you didn’t have to go search. Live action widget just takes over your Lock Screen. Similar things planned for earnings calls for the finance watchlist. More personalization and customization are being worked on and coming in March. Idea is for you to not even have to think of asking stuff. The AI should just do that work for you and give it to you without any effort.

Aravind Srinivas

47,080 次观看 • 1 年前

one of my favorite ways to use claude code skills right now - combining remotion with claude-in-chrome for motion video creation. the workflow is addictive. the clip you see here was produced with minimal prompting effort let me know if you would like me to write a full break down of this process. you describe to claude code what you want, claude code writes the remotion components, opens the remotion studio (via browser) with claude-in-chrome, sees the actual rendered output, and iterates on it in real time. need the arrows pointing to the center of the bubbles instead of the edge? just say it. need the layout shifted to the center? say it. claude sees the preview, adjusts the code, re-renders. then when you're happy you tell claude code to render the final video. but skills are what make this possible. remotion knowledge + browser automation + the taste to iterate visually. no copy pasting screenshots back and forth. no "can you try moving it 10px to the right" over chat. it just looks and fixes. this is the kind of workflow that makes you realize how much further claude code can go beyond just writing code in a terminal. i didn't touch any code while working on the clip you see if you haven't tried combining skills together like this - start experimenting. the skills combos is where the magic is at.

one of my favorite ways to use claude code skills right now - combining remotion with claude-in-chrome for motion video creation. the workflow is addictive. the clip you see here was produced with minimal prompting effort let me know if you would like me to write a full break down of this process. you describe to claude code what you want, claude code writes the remotion components, opens the remotion studio (via browser) with claude-in-chrome, sees the actual rendered output, and iterates on it in real time. need the arrows pointing to the center of the bubbles instead of the edge? just say it. need the layout shifted to the center? say it. claude sees the preview, adjusts the code, re-renders. then when you're happy you tell claude code to render the final video. but skills are what make this possible. remotion knowledge + browser automation + the taste to iterate visually. no copy pasting screenshots back and forth. no "can you try moving it 10px to the right" over chat. it just looks and fixes. this is the kind of workflow that makes you realize how much further claude code can go beyond just writing code in a terminal. i didn't touch any code while working on the clip you see if you haven't tried combining skills together like this - start experimenting. the skills combos is where the magic is at.

elvis

46,426 次观看 • 5 个月前

❓️ ways to overcome worries that occur from time to time 💙 for me, back then i would do something (to overcome it), but nowadays i would do absolutely nothing and just lie down in the house. (with the mindset of) the mountain is a mountain and the water is water, that's how i freed myself (from those worries) t/n: "the mountain is a mountain and the water is water" is from buddhism, it's about how you are ought not to be confused with the truths in life and only then you'll achieve enlightenment, you need to keep your mind open and see everything just as it is

❓️ ways to overcome worries that occur from time to time 💙 for me, back then i would do something (to overcome it), but nowadays i would do absolutely nothing and just lie down in the house. (with the mindset of) the mountain is a mountain and the water is water, that's how i freed myself (from those worries) t/n: "the mountain is a mountain and the water is water" is from buddhism, it's about how you are ought not to be confused with the truths in life and only then you'll achieve enlightenment, you need to keep your mind open and see everything just as it is

♡

22,241 次观看 • 1 年前

subagents are just recursive agents where you can apply different prompts + models depending on the task. since they’re just a primitive, Cursor cli can actually spawn subagents by calling cursor-agent in headless mode via shell commands. that’s what makes the cli so nice. you can extend it, experiment, and have a lot of fun exploring orchestration patterns. here’s one way to do it w. dynamic model selection: 1. create a subagents.mdc rule 2. drop in: ``` --- alwaysApply: true --- ALWAYS spawn subagents by running `cursor-agent -p [task] --output-format=text --force --model [model]` in the terminal. Each subagent should return a summary of the changes it made. Subagents should be used for ALL tasks You can adopt a fan-out pattern where you spawn subagents to perform parallel isolated tasks, and then fan-in the results. Use the following models: - `--model gpt-5` for reasoning, researching, and planning - `--model sonnet-4` for implementation ``` 3. start cursor cli and try it out you can also adjust the rule to be more explicit when it should use subagents, when not to, which models when etc.

subagents are just recursive agents where you can apply different prompts + models depending on the task. since they’re just a primitive, Cursor cli can actually spawn subagents by calling cursor-agent in headless mode via shell commands. that’s what makes the cli so nice. you can extend it, experiment, and have a lot of fun exploring orchestration patterns. here’s one way to do it w. dynamic model selection: 1. create a subagents.mdc rule 2. drop in: ``` --- alwaysApply: true --- ALWAYS spawn subagents by running `cursor-agent -p [task] --output-format=text --force --model [model]` in the terminal. Each subagent should return a summary of the changes it made. Subagents should be used for ALL tasks You can adopt a fan-out pattern where you spawn subagents to perform parallel isolated tasks, and then fan-in the results. Use the following models: - `--model gpt-5` for reasoning, researching, and planning - `--model sonnet-4` for implementation ``` 3. start cursor cli and try it out you can also adjust the rule to be more explicit when it should use subagents, when not to, which models when etc.

eric zakariasson

54,017 次观看 • 10 个月前

Announcing the upcoming FlatForge plugin. The first HueForge plugin. It's HueForge - But Flat. have created an information page about this upcoming plugin. I am planning to release it by the end of September. It will start off at a $15 one time payment (no more payments ever, full updates forever) until after Cyber Monday when it will go up to it's full price of $20. I have spent a lot of time and effort not just on this plugin but on the Plugin system as a whole. I will be working with a few select users/developers to finalize the plugin API before releasing it for you all to use as well. More information on the Plugin system will come after launch.

Announcing the upcoming FlatForge plugin. The first HueForge plugin. It's HueForge - But Flat. have created an information page about this upcoming plugin. I am planning to release it by the end of September. It will start off at a $15 one time payment (no more payments ever, full updates forever) until after Cyber Monday when it will go up to it's full price of $20. I have spent a lot of time and effort not just on this plugin but on the Plugin system as a whole. I will be working with a few select users/developers to finalize the plugin API before releasing it for you all to use as well. More information on the Plugin system will come after launch.

HueForge

33,063 次观看 • 10 个月前

Claude Code Desktop now opens a new window for each session This makes it much easier to visualize multiple Claude Code agents running in parallel My current stack depends on the task: - Ghostty: when starting a project. Bash commands, git, env variables, provider connections. All manual through the terminal with a Claude panel running alongside. - Claude Code Desktop: once everything is configured. GitHub connected, CLAUDE.md, Skills, subagents and Hooks ready. Claude Code runs on its own, no more terminal setup, just panels running and outputs to review. - VSCode: when I need to review code by hand. I use it less and less, but there are moments where I have to confirm Claude got it right. I usually open the Claude extension inside VSCode, but it lacks most of the CLI features so it's limited Solid update. Worth trying once your workflows are already set up 👇

Claude Code Desktop now opens a new window for each session This makes it much easier to visualize multiple Claude Code agents running in parallel My current stack depends on the task: - Ghostty: when starting a project. Bash commands, git, env variables, provider connections. All manual through the terminal with a Claude panel running alongside. - Claude Code Desktop: once everything is configured. GitHub connected, CLAUDE.md, Skills, subagents and Hooks ready. Claude Code runs on its own, no more terminal setup, just panels running and outputs to review. - VSCode: when I need to review code by hand. I use it less and less, but there are moments where I have to confirm Claude got it right. I usually open the Claude extension inside VSCode, but it lacks most of the CLI features so it's limited Solid update. Worth trying once your workflows are already set up 👇

Daniel San

38,591 次观看 • 1 个月前

Claude Mobile starts the idea... Ghostty finishes it I basically use Claude Mobile as a notepad now. Whenever something comes to mind, I open the app, pick a repo, and ask Claude to start exploring. Then I just let it run while I go on with my day. Later I jump into Claude Desktop and I’m right back in the same session, with context, structure, and a clearer shape of the idea. I tweak a few things to set up the coding phase. Finally, one click to Ghostty (video), open a couple of worktrees, and start working on the PR. IMPORTANT: when you move to Ghostty, it must be the exact same repo you started on mobile, otherwise the --teleport command will fail

Claude Mobile starts the idea... Ghostty finishes it I basically use Claude Mobile as a notepad now. Whenever something comes to mind, I open the app, pick a repo, and ask Claude to start exploring. Then I just let it run while I go on with my day. Later I jump into Claude Desktop and I’m right back in the same session, with context, structure, and a clearer shape of the idea. I tweak a few things to set up the coding phase. Finally, one click to Ghostty (video), open a couple of worktrees, and start working on the PR. IMPORTANT: when you move to Ghostty, it must be the exact same repo you started on mobile, otherwise the --teleport command will fail

Daniel San

67,891 次观看 • 5 个月前

This free model just beat every closed-source AI on coding benchmarks. Open weights. 6x cheaper than Opus. The labs don't want you to know it exists. > GLM-5.2 from Zai just topped Code Arena - the first open-weights model to ever hold the #1 coding spot. Not a leaked weight, not a fine-tune. A fully open model beating GPT and Claude on their own turf. It's live on Hugging Face Inference API right now. 5 providers: Novita, Together AI, Fireworks, Deepinfra, Zai. OpenAI-compatible client. → Go to huggingface(.)co → grab HF_TOKEN from account settings → plug into any OpenAI-compatible client 6x cheaper than Opus. Companies bleeding on AI bills are already routing to this for orchestration, caching, and token optimization. The smart money moved before the headline dropped. > Now you know. huggingface(.)co/zai-org/GLM-5.2 Bookmark this before everyone else figures it out.

This free model just beat every closed-source AI on coding benchmarks. Open weights. 6x cheaper than Opus. The labs don't want you to know it exists. > GLM-5.2 from Zai just topped Code Arena - the first open-weights model to ever hold the #1 coding spot. Not a leaked weight, not a fine-tune. A fully open model beating GPT and Claude on their own turf. It's live on Hugging Face Inference API right now. 5 providers: Novita, Together AI, Fireworks, Deepinfra, Zai. OpenAI-compatible client. → Go to huggingface(.)co → grab HF_TOKEN from account settings → plug into any OpenAI-compatible client 6x cheaper than Opus. Companies bleeding on AI bills are already routing to this for orchestration, caching, and token optimization. The smart money moved before the headline dropped. > Now you know. huggingface(.)co/zai-org/GLM-5.2 Bookmark this before everyone else figures it out.

Atenov int.

12,395 次观看 • 26 天前