正在加载视频...

视频加载失败

返回首页

Memories are the previous learnings and context. Developers build up state and context as they do work, which is what makes a more tenured developer more effective than a brand new one with a similar skillset. It would be both inefficient and painful to relearn information from scratch around...

windsurf_ai's profile picture

Windsurf

64,223 subscribers

12,356 次观看 • 1 年前 •via X (Twitter)

LIVE

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

🦊 actually, i would like to keep working as a member of enhypen. i want to do it for as long as i can. i want to keep making good memories and experiences with engenes as well as with enhypen
0:16

🦊 actually, i would like to keep working as a member of enhypen. i want to do it for as long as i can. i want to keep making good memories and experiences with engenes as well as with enhypen

jassy.

10,275 次观看 • 8 个月前

Windsurf is now the easiest way to get started with MCP! Connecting MCP servers to Cascade allows it to interact directly with platforms like Github, Slack, Figma, etc. In just a few clicks, you can get up and running with MCP and equip Cascade with additional tooling that can unlock new workflows.
0:16

Windsurf is now the easiest way to get started with MCP! Connecting MCP servers to Cascade allows it to interact directly with platforms like Github, Slack, Figma, etc. In just a few clicks, you can get up and running with MCP and equip Cascade with additional tooling that can unlock new workflows.

Windsurf

90,431 次观看 • 1 年前

Iranian streets are filling up for the 4th day as freedom-loving people around the world celebrate a New Year. I’m asking you to take a few minutes today and pray for the people of Iran. If you see footage of them in the streets, do your best to confirm it and share it. People have a hard time believing things without seeing evidence. The current regime will do everything it can to prevent brave voices from being seen and heard. This is why it’s crucial for those of you who are willing — to share what you can, whenever you can.
0:17

Iranian streets are filling up for the 4th day as freedom-loving people around the world celebrate a New Year. I’m asking you to take a few minutes today and pray for the people of Iran. If you see footage of them in the streets, do your best to confirm it and share it. People have a hard time believing things without seeing evidence. The current regime will do everything it can to prevent brave voices from being seen and heard. This is why it’s crucial for those of you who are willing — to share what you can, whenever you can.

ⓒʜɪʟʟɪɴᴏɪꜱ

76,717 次观看 • 7 个月前

Sorry for the personal post and missing Cascade today but I couldn’t miss Katiepilcher34 last varsity game. Not a more fitting way to end it than clutching one more K from Braylen Conlon! Thanks for a lot of great memories, ladies! Kristine Pilcher Eric Conlon Amy Conlon
0:12

Sorry for the personal post and missing Cascade today but I couldn’t miss Katiepilcher34 last varsity game. Not a more fitting way to end it than clutching one more K from Braylen Conlon! Thanks for a lot of great memories, ladies! Kristine Pilcher Eric Conlon Amy Conlon

K.J. Pilcher

69,890 次观看 • 1 年前

Supabase makes it easy to work with LLMs! You can copy all of the table definitions with a single click within the Supabase dashboard so that you can quickly provide the context of the database! Head to the Database menu and click the "Copy as SQL" button 📋
0:13

Supabase makes it easy to work with LLMs! You can copy all of the table definitions with a single click within the Supabase dashboard so that you can quickly provide the context of the database! Head to the Database menu and click the "Copy as SQL" button 📋

Tyler Shukert

26,656 次观看 • 11 个月前

After a few more hours, I think I've figured out Opus 5. Opus 5 is trained to be more agentic than anything I've used. All Claude 5 models are like that. So what changes? The way to interact with Opus 5 or contextualize it won't work the same way as with other models. It loves exploring, so it doesn't need much guidance for it. Unique preferences, artifacts, and references compliment it well and enable cleaner and more effective exploration and execution. Now that it can explore more effectively on its own and understand intent better, the best thing to do is to get out of its way (e.g., it doesn't need examples of your preferences; a clear high-level description of it works best). It's truly agentic in that sense. A good first step to provide better context for Opus 5 is to distinguish between what's situational and what needs persistence. Regardless, persistent system prompts and CLAUDE.MD needs to stay lightweight. Remove memories and tool descriptions from these. CLAUDE.MD is also a great place to tap into progressive disclosure by linking command/skills to it. On the situational side, agent skills and auto-memory can leverage progressive disclosure and the improved ability of the model to use its external context/knowledge. Conflicting and unnecessary instructions, which are common at this layer (mainly to ensure reliability), are going to throw off this model easily. That's the biggest change I had to make. Simple, clean, and clear prompts and skills work best. I had to clean a lot of my skills and system prompts. The way I prompt remains the same (usually clear and well-scoped). MCP tool descriptions are also more descriptive and have been deduped from the system prompt. Anthropic released a guide on the new rules for context engineering, which was helpful here. I started to test the recommendations and created a little artifact with the things that worked along the way. This might feel like a lot of work. Believe me, it has been frustrating. But I think we can expect future frontier models to become more agentic and smarter at figuring out the right context/gaps. The best thing to do is to prepare for that now. Boris Cherny mentioned that Opus 5 is their least prompt-injectable model yet. I am not sure if that was something they intentionally trained for or if it emerged based on how it was trained, which is to be extremely agentic in nature and more direct in execution.
0:15

After a few more hours, I think I've figured out Opus 5. Opus 5 is trained to be more agentic than anything I've used. All Claude 5 models are like that. So what changes? The way to interact with Opus 5 or contextualize it won't work the same way as with other models. It loves exploring, so it doesn't need much guidance for it. Unique preferences, artifacts, and references compliment it well and enable cleaner and more effective exploration and execution. Now that it can explore more effectively on its own and understand intent better, the best thing to do is to get out of its way (e.g., it doesn't need examples of your preferences; a clear high-level description of it works best). It's truly agentic in that sense. A good first step to provide better context for Opus 5 is to distinguish between what's situational and what needs persistence. Regardless, persistent system prompts and CLAUDE.MD needs to stay lightweight. Remove memories and tool descriptions from these. CLAUDE.MD is also a great place to tap into progressive disclosure by linking command/skills to it. On the situational side, agent skills and auto-memory can leverage progressive disclosure and the improved ability of the model to use its external context/knowledge. Conflicting and unnecessary instructions, which are common at this layer (mainly to ensure reliability), are going to throw off this model easily. That's the biggest change I had to make. Simple, clean, and clear prompts and skills work best. I had to clean a lot of my skills and system prompts. The way I prompt remains the same (usually clear and well-scoped). MCP tool descriptions are also more descriptive and have been deduped from the system prompt. Anthropic released a guide on the new rules for context engineering, which was helpful here. I started to test the recommendations and created a little artifact with the things that worked along the way. This might feel like a lot of work. Believe me, it has been frustrating. But I think we can expect future frontier models to become more agentic and smarter at figuring out the right context/gaps. The best thing to do is to prepare for that now. Boris Cherny mentioned that Opus 5 is their least prompt-injectable model yet. I am not sure if that was something they intentionally trained for or if it emerged based on how it was trained, which is to be extremely agentic in nature and more direct in execution.

elvis

37,551 次观看 • 13 天前

More and more Western far-left women are converting to Islam as they believe it to be a one of the most progressive things one can do
0:16

More and more Western far-left women are converting to Islam as they believe it to be a one of the most progressive things one can do

Visegrád 24

155,247 次观看 • 1 年前

Been playing Rust since 2014 and today is finally the day i’m quitting, i’ve got myself a nice comfortable and good paying IT job for longterm that requires 24/7 of my time, thanks for the great memories y’all! 🙂 Under a yr from 600 subs to 50k, if i can do it then you can too!
0:19

Been playing Rust since 2014 and today is finally the day i’m quitting, i’ve got myself a nice comfortable and good paying IT job for longterm that requires 24/7 of my time, thanks for the great memories y’all! 🙂 Under a yr from 600 subs to 50k, if i can do it then you can too!

KaaNo

80,868 次观看 • 3 个月前

🚨: Vibe coding 2.0 just released Today, Claude just got a massive upgrade and I'm so happy to be a part it. From now on, Claude Code Opus 4.6 can build and run a full business, 100% autonomously and from scratch. We just launched Shipper 2.0, a tool that lets Claude: → Build web/mobile apps and Chrome extensions → Code, design, monetize, launch → Do email marketing for you → Continue to build out new features → Self-maintain in the long run Claude's most powerful models can now do all of that from a <10 word prompt, for as low as $0.12/app... And it takes minutes! Simply go to Shipper, then ask Claude to "build a talent hiring platform" or "build a complete saas that charges $29/mo"! To celebrate the launch, we're giving away free credits randomly to people who repost and comment "SHIPPER' :)
0:13

🚨: Vibe coding 2.0 just released Today, Claude just got a massive upgrade and I'm so happy to be a part it. From now on, Claude Code Opus 4.6 can build and run a full business, 100% autonomously and from scratch. We just launched Shipper 2.0, a tool that lets Claude: → Build web/mobile apps and Chrome extensions → Code, design, monetize, launch → Do email marketing for you → Continue to build out new features → Self-maintain in the long run Claude's most powerful models can now do all of that from a <10 word prompt, for as low as $0.12/app... And it takes minutes! Simply go to Shipper, then ask Claude to "build a talent hiring platform" or "build a complete saas that charges $29/mo"! To celebrate the launch, we're giving away free credits randomly to people who repost and comment "SHIPPER' :)

David Ch

55,992 次观看 • 4 个月前

Before, I worked for a cultural and events organization, and I had the chance to work alongside hundreds of very kind and dedicated volunteers And I had the opportunity to reunite with some of them to throw them a surprise show in fursuit Here are a few memories from that time
0:15

Before, I worked for a cultural and events organization, and I had the chance to work alongside hundreds of very kind and dedicated volunteers And I had the opportunity to reunite with some of them to throw them a surprise show in fursuit Here are a few memories from that time

ℝ𝕒𝕪 𝔹𝕝𝕖𝕚𝕫

13,300 次观看 • 2 个月前

OpenAI's Deep Research is getting a run for its money. Deep Lake was just released, and it's a different take on an AI system that can do deep research on your own data. You can use Deep Lake to build AI search with reasoning on your private and public data. (Look at the attached videos to get an idea of how it works.) If you want to research proprietary and sensitive data, Deep Research won't help you because it's limited to public data. Deep Lake, however, will allow you to use your private data. On top of that, Deep Lake supports multi-modal retrieval from the ground up. It uses vision language models for data ingestion and retrieval so that you can connect any data (PDFs, images, videos, structured data, etc.) You can even use mixed-data queries! Deep Lake can search your data from S3, Dropbox, and GCP. It learns from your queries over time, making the results as relevant to your work as possible!
0:15

OpenAI's Deep Research is getting a run for its money. Deep Lake was just released, and it's a different take on an AI system that can do deep research on your own data. You can use Deep Lake to build AI search with reasoning on your private and public data. (Look at the attached videos to get an idea of how it works.) If you want to research proprietary and sensitive data, Deep Research won't help you because it's limited to public data. Deep Lake, however, will allow you to use your private data. On top of that, Deep Lake supports multi-modal retrieval from the ground up. It uses vision language models for data ingestion and retrieval so that you can connect any data (PDFs, images, videos, structured data, etc.) You can even use mixed-data queries! Deep Lake can search your data from S3, Dropbox, and GCP. It learns from your queries over time, making the results as relevant to your work as possible!

Santiago

171,340 次观看 • 1 年前

While we understand that the popular thing to do is to solicit pity by creating false narratives, it is important that we remember that Dignity will never go out of style and Dignity Can Win. Here is a video of what CeeC said and none of it was directed to Adekunle or any person in particular. We have access to more information out here than our respective contestants in the house and so it is important we act accordingly, we would all be better for it. Spartans, I hope this motivates you to prepare to vote and deliver. #CeecX120M #BBNaija #BBNaijaAllStars
0:11

While we understand that the popular thing to do is to solicit pity by creating false narratives, it is important that we remember that Dignity will never go out of style and Dignity Can Win. Here is a video of what CeeC said and none of it was directed to Adekunle or any person in particular. We have access to more information out here than our respective contestants in the house and so it is important we act accordingly, we would all be better for it. Spartans, I hope this motivates you to prepare to vote and deliver. #CeecX120M #BBNaija #BBNaijaAllStars

Cynthia Nwadiora

665,953 次观看 • 2 年前

We're launching something new: Collaborative Notes The idea: when you request a note, AI drafts one — then the community refines it together through ratings and suggestions. You can watch it get better in real time. It’s a whole new way for the public to work with AI — and each other — to make information more accurate. And a whole new way to contribute to Community Notes. For now, only requests from Top Writers on English-language posts generate Collaborative Notes, and you must have 2+ Writing Impact to make suggestions. We plan to expand that & shape the experience based on your feedback. As usual, it’s open-source:
0:12

We're launching something new: Collaborative Notes The idea: when you request a note, AI drafts one — then the community refines it together through ratings and suggestions. You can watch it get better in real time. It’s a whole new way for the public to work with AI — and each other — to make information more accurate. And a whole new way to contribute to Community Notes. For now, only requests from Top Writers on English-language posts generate Collaborative Notes, and you must have 2+ Writing Impact to make suggestions. We plan to expand that & shape the experience based on your feedback. As usual, it’s open-source:

Community Notes

7,781,232 次观看 • 6 个月前

SOMEONE TURNED THEIR TEAM'S TASK TRACKER INTO A 3D ISLAND instead of a boring list of tasks, your teams work is a little island that grows as you get stuff done > you assign tasks right in slack, just type who its for, the points, and the due date > finish a task and you get to place a building on the island > get your work rejected and the building collapses into rubble > the rubble stays there forever, so everyone can see it > each new sprint starts a fresh island so over time the island fills up with buildings for all the work your team actually finished, and the rubble is a reminder of what got rejected. its open source, so any team can set it up. way more fun than staring at a to do list all day
0:13

SOMEONE TURNED THEIR TEAM'S TASK TRACKER INTO A 3D ISLAND instead of a boring list of tasks, your teams work is a little island that grows as you get stuff done > you assign tasks right in slack, just type who its for, the points, and the due date > finish a task and you get to place a building on the island > get your work rejected and the building collapses into rubble > the rubble stays there forever, so everyone can see it > each new sprint starts a fresh island so over time the island fills up with buildings for all the work your team actually finished, and the rubble is a reminder of what got rejected. its open source, so any team can set it up. way more fun than staring at a to do list all day

Om Patel

12,910 次观看 • 1 个月前

✨Tap here to find out how this tie can create a range of effects: 🪢 What you do with this tie depends entirely on your intention. You can wear it as a decorative flair, use it for extra sensations, or add it to a predicament to make things more challenging. All of the above? Also valid. Go explore out what it does for you!
0:17

Sensitive content

✨Tap here to find out how this tie can create a range of effects: 🪢 What you do with this tie depends entirely on your intention. You can wear it as a decorative flair, use it for extra sensations, or add it to a predicament to make things more challenging. All of the above? Also valid. Go explore out what it does for you!

Shibari Study

65,138 次观看 • 1 个月前

It's incredible what you can do with Rive + Cursor in just a few hours. This nav I built in Rive is fully integrated into my Swift app and took a fraction of the time to build as it would doing it all in code. It's super performant and really lightweight.
0:15

It's incredible what you can do with Rive + Cursor in just a few hours. This nav I built in Rive is fully integrated into my Swift app and took a fraction of the time to build as it would doing it all in code. It's super performant and really lightweight.

Ben

153,681 次观看 • 1 年前

It has been an extraordinary run. As I leave the State House for the last time as Governor, I am proud to say we are leaving our children a state that is better than we found it. A New Jersey that is stronger, fairer, and more responsible. To each and every New Jerseyan: It has been the highest honor of my life to serve as your Governor. Thank you for joining me on this journey. Never forget: We’re from Jersey, baby!!
0:10

It has been an extraordinary run. As I leave the State House for the last time as Governor, I am proud to say we are leaving our children a state that is better than we found it. A New Jersey that is stronger, fairer, and more responsible. To each and every New Jerseyan: It has been the highest honor of my life to serve as your Governor. Thank you for joining me on this journey. Never forget: We’re from Jersey, baby!!

Governor Phil Murphy

185,956 次观看 • 6 个月前

Simplicity is at the heart of great software. This is one of the reasons why Claude Code has been sticky for me. As a builder, I love planning and brainstorming, and this is now a key focus of Claude Code. I use Shift + Tab a lot to cycle between brainstorming, planning, and execution. This functionality provides the appropriate interface for me to either be very involved or less involved as I please. This works particularly well when building out new and complex features or entire new projects. This saves a huge amount of time. It allows me to tune Claude Code to execute and build more effectively. It also builds a loop of trust, and I often (surprisingly) find Claude Code asking for clarifications when it's confused. Coding agents don't normally do that. I have shared before on the power of brainstorming with AI for longer times. Try it and you will not be disappointed. Vibe coding is fun, but pair it with intentional development cycles, and you watch how far you can take a project with coding agents today.
0:10

Simplicity is at the heart of great software. This is one of the reasons why Claude Code has been sticky for me. As a builder, I love planning and brainstorming, and this is now a key focus of Claude Code. I use Shift + Tab a lot to cycle between brainstorming, planning, and execution. This functionality provides the appropriate interface for me to either be very involved or less involved as I please. This works particularly well when building out new and complex features or entire new projects. This saves a huge amount of time. It allows me to tune Claude Code to execute and build more effectively. It also builds a loop of trust, and I often (surprisingly) find Claude Code asking for clarifications when it's confused. Coding agents don't normally do that. I have shared before on the power of brainstorming with AI for longer times. Try it and you will not be disappointed. Vibe coding is fun, but pair it with intentional development cycles, and you watch how far you can take a project with coding agents today.

elvis

81,765 次观看 • 9 个月前