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。

We launched Blueprints for Vy users earlier this week. Instead of cramming complex work into a single long prompt, you can now break it into modular steps. Test each step individually, then run them together as a complete workflow. What does this unlock?🔓 1/5

Vercept

5,191 subscribers

307,092 次观看 • 6 个月前 •via X (Twitter)

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

Most people just prompt ChatGPT for 10 tweets. Result is AI slop. Here's what Dan Koe does instead: Step 1: Find 3 posts that went viral Feed them to AI. Ask it to break down: - Structure - Psychology - Why it worked Step 2: Combine the patterns into one guide Step 3: Turn that guide into a two-phase prompt - Phase 1: AI interviews YOU for context - Phase 2: AI writes in YOUR voice He does this for tweets, landing pages, even book paragraphs. Stop prompting like a Neanderthal. Context is king.

Most people just prompt ChatGPT for 10 tweets. Result is AI slop. Here's what Dan Koe does instead: Step 1: Find 3 posts that went viral Feed them to AI. Ask it to break down: - Structure - Psychology - Why it worked Step 2: Combine the patterns into one guide Step 3: Turn that guide into a two-phase prompt - Phase 1: AI interviews YOU for context - Phase 2: AI writes in YOUR voice He does this for tweets, landing pages, even book paragraphs. Stop prompting like a Neanderthal. Context is king.

The Startup Ideas Podcast (SIP) 🧃

28,189 次观看 • 6 个月前

Turn any workflow into an agent skill. I built a YC job finder, deployed it as MCP server & connected it to Claude Desktop. It finds matching roles & sends personalized application emails to the recruiter. If you can break a process into steps, this guide will help you automate it:

Turn any workflow into an agent skill. I built a YC job finder, deployed it as MCP server & connected it to Claude Desktop. It finds matching roles & sends personalized application emails to the recruiter. If you can break a process into steps, this guide will help you automate it:

Akshay 🚀

61,867 次观看 • 4 个月前

Most people trying to build a vertical AI business start by building the agent. That's the mistake. Here's the 5-step order that actually works: Step 1) Find a boring pain point - Pick a workflow you already know from your job. - That's your unfair advantage. Step 2) Map the workflow - Literally draw it out. - Every step, every handoff. Step 3) Do the job as a service - Manually. - For real clients. - Before any code. Step 4) Document the edge cases - This is where the real IP lives. - You only find them by doing the work. Step 5) Add vertical agents to replace each step - Now you have proprietary data and a workflow you own. Skip steps 1–4 and you're just building a demo.

Most people trying to build a vertical AI business start by building the agent. That's the mistake. Here's the 5-step order that actually works: Step 1) Find a boring pain point - Pick a workflow you already know from your job. - That's your unfair advantage. Step 2) Map the workflow - Literally draw it out. - Every step, every handoff. Step 3) Do the job as a service - Manually. - For real clients. - Before any code. Step 4) Document the edge cases - This is where the real IP lives. - You only find them by doing the work. Step 5) Add vertical agents to replace each step - Now you have proprietary data and a workflow you own. Skip steps 1–4 and you're just building a demo.

The Startup Ideas Podcast (SIP) 🧃

14,202 次观看 • 3 个月前

💡 Getting a lot of mileage out of this global rule in Claude: > Break up complex plans into multi-step phases with numbered headings for each phase. We do this to avoid having to implement all features at once. This lets me work through tasks in chunks or break off new convos

💡 Getting a lot of mileage out of this global rule in Claude: > Break up complex plans into multi-step phases with numbered headings for each phase. We do this to avoid having to implement all features at once. This lets me work through tasks in chunks or break off new convos

Ben Holmes

27,446 次观看 • 6 个月前

Launch Week Day 1: Tasklist is here Eagle-eyed power users have already been putting Tasklist to work. Now, we’re showing you how to get the most out of it. With Tasklist, we’re making it way easier to take a big, vague task—and break it down step by step. So you can actually see what your Agent’s doing, monitor progress, and make changes as you go. It works the same way the most productive engineers do: - Define the ideal outcome - Break it into steps - Verify the plan makes sense That breakdown gives you confidence. Tasklist builds that into how the Agent works.

Launch Week Day 1: Tasklist is here Eagle-eyed power users have already been putting Tasklist to work. Now, we’re showing you how to get the most out of it. With Tasklist, we’re making it way easier to take a big, vague task—and break it down step by step. So you can actually see what your Agent’s doing, monitor progress, and make changes as you go. It works the same way the most productive engineers do: - Define the ideal outcome - Break it into steps - Verify the plan makes sense That breakdown gives you confidence. Tasklist builds that into how the Agent works.

Augment Code

584,421 次观看 • 1 年前

Running top-tier models like Claude Fable 5, Kimi K3, and Grok 4.5 inside Codex is now completely possible using a straightforward open-source repository. Here is how you can set it up right now: - Locate and open the opencodex repository - Copy the prompt instructions directly into your chat window - Follow the detailed guide linked below to configure your setup and start running queries This workflow bypasses complex installations and lets you leverage multiple frontier models within a single interface. Bookmark this post so you do not lose the step-by-step walkthrough.

Running top-tier models like Claude Fable 5, Kimi K3, and Grok 4.5 inside Codex is now completely possible using a straightforward open-source repository. Here is how you can set it up right now: - Locate and open the opencodex repository - Copy the prompt instructions directly into your chat window - Follow the detailed guide linked below to configure your setup and start running queries This workflow bypasses complex installations and lets you leverage multiple frontier models within a single interface. Bookmark this post so you do not lose the step-by-step walkthrough.

0xMarioNawfal

66,209 次观看 • 5 天前

BILL MAHER: “I’m supportive of the idea of going into Iran. I thought that was a good attempt. What I hope [Trump] does now is realize it didn't work … Let’s not make a bad situation worse. Let’s get out of this as cleanly as we can.”

BILL MAHER: “I’m supportive of the idea of going into Iran. I thought that was a good attempt. What I hope [Trump] does now is realize it didn't work … Let’s not make a bad situation worse. Let’s get out of this as cleanly as we can.”

Chief Nerd

76,665 次观看 • 2 个月前

Introducing Wide Research Tackle complex research in a single step. With Wide Research, Manus breaks massive, large-scale tasks into multiple sub-tasks — and runs them all at once — without missing a beat. - Research a long list of sales leads - Profile hundreds of companies across multiple metrics - Batch-generate images, web pages, slides, and more You define the goal. Manus handles the rest — simultaneously. Prompt once. Run wide. This is research at scale. Launching today for Pro users, with a gradual rollout planned for Plus and Basic tiers.

Manus

1,248,982 次观看 • 1 年前

Most teams are sitting on piles of low-hanging automation fruit. If you’re trying to justify the ROI, you’re probably overthinking it. I talked about this on Applied, the tenex podcast with Alex Lieberman (Alex Lieberman) and Arman Hezarkhani. We built an agent that takes new Typeform leads, researches them online, and drops them into a Zapier Table. Small build, big ripple for any team learning to work with AI. Here’s how to find your own automation silver bullet: 1. Pick one process close to revenue or your biggest cost 2. Break it into 3 to 5 steps 3. Automate the boring parts with a workflow 4. Insert an agent only where judgment is needed 5. Keep a human in the loop. Remove as confidence grows You can run this exercise in 15 mins. You don’t need to code, but you DO need to think like an engineer. What win will you ship this week?

Most teams are sitting on piles of low-hanging automation fruit. If you’re trying to justify the ROI, you’re probably overthinking it. I talked about this on Applied, the tenex podcast with Alex Lieberman (Alex Lieberman) and Arman Hezarkhani. We built an agent that takes new Typeform leads, researches them online, and drops them into a Zapier Table. Small build, big ripple for any team learning to work with AI. Here’s how to find your own automation silver bullet: 1. Pick one process close to revenue or your biggest cost 2. Break it into 3 to 5 steps 3. Automate the boring parts with a workflow 4. Insert an agent only where judgment is needed 5. Keep a human in the loop. Remove as confidence grows You can run this exercise in 15 mins. You don’t need to code, but you DO need to think like an engineer. What win will you ship this week?

Wade Foster

112,490 次观看 • 9 个月前

As an anniversary of your Day 21 of 21, We hear greater songs of joy bursting out around you… Connect and Receive as you officially step into a new week for What our God Cannot Do Does Not Exist🔥🔥🔥

As an anniversary of your Day 21 of 21, We hear greater songs of joy bursting out around you… Connect and Receive as you officially step into a new week for What our God Cannot Do Does Not Exist🔥🔥🔥

streamsofjoyinternational

10,355 次观看 • 1 年前

👤 how does it feel practicing with GOT7 again after so long? 🐍 do you know this?when a group of guys get together, their iq drops a little 🐍 we've all matured & learned so much while doing our solo stuff. As soon as we get together, we turn into total idiots. No one can focus

👤 how does it feel practicing with GOT7 again after so long? 🐍 do you know this?when a group of guys get together, their iq drops a little 🐍 we've all matured & learned so much while doing our solo stuff. As soon as we get together, we turn into total idiots. No one can focus

𝐣𝐨𝐲𝐜𝐞

110,082 次观看 • 1 年前

This week we're launching new skills for HyperFrames, each built around a workflow Today is pr-to-video Nobody reads pull requests. Now agents can turn them into a short explainer video npx skills add heygen-com/hyperframes New skill launching every day. Follow for more

This week we're launching new skills for HyperFrames, each built around a workflow Today is pr-to-video Nobody reads pull requests. Now agents can turn them into a short explainer video npx skills add heygen-com/hyperframes New skill launching every day. Follow for more

HeyGen

39,040 次观看 • 1 个月前

Guys I just saw this message now and the message is so disturbing ..can we look into this please .... This is bad if it is real then we are in for a long journey !! Share massively please Can we get responses please

Guys I just saw this message now and the message is so disturbing ..can we look into this please .... This is bad if it is real then we are in for a long journey !! Share massively please Can we get responses please

AFRICAMUSTBEFREE!!!!!!!

16,278 次观看 • 8 个月前

What started as building a personal taste.md skill for myself, turned into building a pipeline to create any taste as a skill. The most important piece is references. This is where you should spend time. If the references suck, so does the skill. I find that references cropped tightly on details in high resolution work the best. Each image gets analyzed by both Opus 4.7 and GPT 5.5. The analysis is based on why the reference is successful as a piece of design - not what it does functionally. Using two models helps rule out biases and gaps from each. The models focus on layout, spacing, typography, rhythm, composition, hierarchy, etc. At the end, each image has: reference-01/ - opus-4-7-analysis.md - gpt-5-5-analysis.md Then we fuse them together using GPT 5.5 - but the md files are anonymized so 5.5 doesn't prefer itself. reference-01/ - fused-analysis.md reference-02/ - fused-analysis.md etc. After fusion, we have one synthesized analysis per reference. Now the goal is to combine all of those into a single rule set. This is where chunking matters. If you ask one model to combine 100 image analyses at once, the result becomes too broad. It summarizes instead of preserving the granular design rules we want. Instead we chunk the fused analyses into smaller groups. Each group gets merged into a chunk-level synthesis, usually from around 6 to 8 image notes at a time. Then one final model pass fuses those chunks into a single md rule set. Finally, using the rule set, we write a skill of concrete instructions. It enforces constraints, uses imperative wording, and avoids vague taste words.

What started as building a personal taste.md skill for myself, turned into building a pipeline to create any taste as a skill. The most important piece is references. This is where you should spend time. If the references suck, so does the skill. I find that references cropped tightly on details in high resolution work the best. Each image gets analyzed by both Opus 4.7 and GPT 5.5. The analysis is based on why the reference is successful as a piece of design - not what it does functionally. Using two models helps rule out biases and gaps from each. The models focus on layout, spacing, typography, rhythm, composition, hierarchy, etc. At the end, each image has: reference-01/ - opus-4-7-analysis.md - gpt-5-5-analysis.md Then we fuse them together using GPT 5.5 - but the md files are anonymized so 5.5 doesn't prefer itself. reference-01/ - fused-analysis.md reference-02/ - fused-analysis.md etc. After fusion, we have one synthesized analysis per reference. Now the goal is to combine all of those into a single rule set. This is where chunking matters. If you ask one model to combine 100 image analyses at once, the result becomes too broad. It summarizes instead of preserving the granular design rules we want. Instead we chunk the fused analyses into smaller groups. Each group gets merged into a chunk-level synthesis, usually from around 6 to 8 image notes at a time. Then one final model pass fuses those chunks into a single md rule set. Finally, using the rule set, we write a skill of concrete instructions. It enforces constraints, uses imperative wording, and avoids vague taste words.

Jaytel

59,705 次观看 • 2 个月前

Sam Altman: "The Turing test sort of went whooshing by, which seemed long impossible ( it as this most important test of AI for a long time)", and after a week, everyone took it for granted. The next step: The next big step: AI that conducts science independently, and we are already seeing the first discoveries! Sam Altman's AGI moment, so to speak.

Sam Altman: "The Turing test sort of went whooshing by, which seemed long impossible ( it as this most important test of AI for a long time)", and after a week, everyone took it for granted. The next step: The next big step: AI that conducts science independently, and we are already seeing the first discoveries! Sam Altman's AGI moment, so to speak.

Chubby♨️

47,818 次观看 • 9 个月前

This week Symbiotic launched the first integration of Omni's SolverNet on incentivized testnet. For the first time, users can deposit into vaults on L1 from rollups without bridging. Here’s a quick tutorial on how you can participate in our incentivized testnet today:

This week Symbiotic launched the first integration of Omni's SolverNet on incentivized testnet. For the first time, users can deposit into vaults on L1 from rollups without bridging. Here’s a quick tutorial on how you can participate in our incentivized testnet today:

Austin King

38,183 次观看 • 1 年前

What you see in the video is just the surface. 🖋️ On Patreon, we delve deeper into each concept and explore the aesthetics of tension without restrictions. For just $5 a month, you support independent art and unlock the BDMANCARTOON HQ: 🔓 Complete and uncensored galleries 🔓 Behind-the-scenes animation and concept art 🔓 Early access to upcoming projects (including Memoirs of a Bondage Artist) Join the experience and support the creation of the legend. See you there: 🔗

Sensitive content

What you see in the video is just the surface. 🖋️ On Patreon, we delve deeper into each concept and explore the aesthetics of tension without restrictions. For just $5 a month, you support independent art and unlock the BDMANCARTOON HQ: 🔓 Complete and uncensored galleries 🔓 Behind-the-scenes animation and concept art 🔓 Early access to upcoming projects (including Memoirs of a Bondage Artist) Join the experience and support the creation of the legend. See you there: 🔗

BDManCartoon - OPEN FOR COMMISSIONS

38,052 次观看 • 1 个月前

As another year of pride ends, we will let Rob Schneider 🇺🇸 close it out for us! Each year less and less people support pride because of what it has turned into. We hope next year we can celebrate a whole month for our veterans instead…one can dream.

As another year of pride ends, we will let Rob Schneider 🇺🇸 close it out for us! Each year less and less people support pride because of what it has turned into. We hope next year we can celebrate a whole month for our veterans instead…one can dream.

Gays Against Groomers

60,100 次观看 • 25 天前