Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

Did some spring cleaning over the weekend; finished a 'garage project' I had -- in near future we won't use docs for how things work, agents will do all of it for us So I did this for Base -- it's called BaseHub, built exclusively for Agents; updates automatically everyday

wbnns ⚡️

7,768 subscribers

16,047 Aufrufe • vor 3 Monaten •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

I spent the last 2 weeks diving deep into trading agents I built so many of them that it made sense to build this... A scaffolding tool for building trading agents It's very experimental but it comes with wallets, tools and x402 integrations Built on LangChain & Base 🦜 🟦

I spent the last 2 weeks diving deep into trading agents I built so many of them that it made sense to build this... A scaffolding tool for building trading agents It's very experimental but it comes with wallets, tools and x402 integrations Built on LangChain & Base 🦜 🟦

Youssef

27,114 Aufrufe • vor 5 Monaten

🦊 the members were all cleaning? i did mine in advance before i left~ i had a big cleaning day before i left because we decided on cleaning!! 🦊 i thought i wouldn’t get the time to do it so i did it in advance

🦊 the members were all cleaning? i did mine in advance before i left~ i had a big cleaning day before i left because we decided on cleaning!! 🦊 i thought i wouldn’t get the time to do it so i did it in advance

💬

159,808 Aufrufe • vor 5 Monaten

This ◉ ʜᴜᴍᴀɴ ○ ᴍᴀᴄʜɪɴᴇ toggle by Parallel Web Systems is brilliant. It's a beautiful illustration of what the web will "look like" to agents. It will look like a whole lotta markdown 😄 Incidentally, we just made it such that links automatically render as markdown when agents consume it (we do the same for /𝚍𝚘𝚌𝚜). Page went from 500kb to 2kb. The web for agents will be very efficient! Try: curl -H 'accept: text/markdown'

This ◉ ʜᴜᴍᴀɴ ○ ᴍᴀᴄʜɪɴᴇ toggle by Parallel Web Systems is brilliant. It's a beautiful illustration of what the web will "look like" to agents. It will look like a whole lotta markdown 😄 Incidentally, we just made it such that links automatically render as markdown when agents consume it (we do the same for /𝚍𝚘𝚌𝚜). Page went from 500kb to 2kb. The web for agents will be very efficient! Try: curl -H 'accept: text/markdown'

Guillermo Rauch

187,349 Aufrufe • vor 7 Monaten

I just built my own wiki generator plugin for my agents. My agents can now generate wikis for anything I ask. One of my favorite wikis is called PaperWiki. This is a great example of what Andrej Karpathy describes. It uses obsidian vaults to organize papers, retrieve LLM-generated summaries, diagrams, and other advanced views for paper exploration. When Obsidian UI is not enough, I use my own artifact generator inside my agent orchestrator (see clip for example). This allows my agents to build any kind of view or exploration feature that I need. The papers are all curated with automations and several rules/patterns I have manually built over the years. On the surface, this looks basic. But behind the scenes, there are advanced search capabilities, connections, metadata, derived data, and other interesting bits of information that are extremely useful for my research agents. This is mostly built for agents. The artifact preview is just a high-level way to validate and quickly assess the quality of the wiki, suggest improvements, and it's also great for research. I use tobi lutke's qmd for all search capabilities. Everything is markdown. The summaries and even the diagrams. The wiki updates on its own based on several automations I have optimized over the past couple of weeks. The wiki grows and self-improves based on several requirements important for my research use cases. This is as personalized as it gets. There is nothing like it out there. And I use my research expertise to continue improving it over time. This is a vanilla wiki. There are so many things I want to build on top of this. Different aggregations, views, artifacts, etc. All to help automate more of my research work and accelerate productivity. I think the biggest leverage here is how powerful this could be for discovery and experimentation. One of my goals is to use it to find deeper connections and insights that would otherwise elude the top human researchers and use those to generate interesting new hypotheses and research experiments. That way, my agents can use autoresearch to explore research ideas at the frontier. Stay tuned for more.

I just built my own wiki generator plugin for my agents. My agents can now generate wikis for anything I ask. One of my favorite wikis is called PaperWiki. This is a great example of what Andrej Karpathy describes. It uses obsidian vaults to organize papers, retrieve LLM-generated summaries, diagrams, and other advanced views for paper exploration. When Obsidian UI is not enough, I use my own artifact generator inside my agent orchestrator (see clip for example). This allows my agents to build any kind of view or exploration feature that I need. The papers are all curated with automations and several rules/patterns I have manually built over the years. On the surface, this looks basic. But behind the scenes, there are advanced search capabilities, connections, metadata, derived data, and other interesting bits of information that are extremely useful for my research agents. This is mostly built for agents. The artifact preview is just a high-level way to validate and quickly assess the quality of the wiki, suggest improvements, and it's also great for research. I use tobi lutke's qmd for all search capabilities. Everything is markdown. The summaries and even the diagrams. The wiki updates on its own based on several automations I have optimized over the past couple of weeks. The wiki grows and self-improves based on several requirements important for my research use cases. This is as personalized as it gets. There is nothing like it out there. And I use my research expertise to continue improving it over time. This is a vanilla wiki. There are so many things I want to build on top of this. Different aggregations, views, artifacts, etc. All to help automate more of my research work and accelerate productivity. I think the biggest leverage here is how powerful this could be for discovery and experimentation. One of my goals is to use it to find deeper connections and insights that would otherwise elude the top human researchers and use those to generate interesting new hypotheses and research experiments. That way, my agents can use autoresearch to explore research ideas at the frontier. Stay tuned for more.

elvis

67,257 Aufrufe • vor 4 Monaten

For episode 6, I was mainly focused on lighting. BUT I did do some animation! But for future episodes, I'll be doing more anim! But here's the little things I've done so far!

For episode 6, I was mainly focused on lighting. BUT I did do some animation! But for future episodes, I'll be doing more anim! But here's the little things I've done so far!

Trixel

116,619 Aufrufe • vor 1 Jahr

I had some spare ST3215 motors (and time), so I built these amazing actuators designed by Lethic and they work so well! Once I have a use for them in a project, I'll probably get the gears printed from a professional 3D printing service...

I had some spare ST3215 motors (and time), so I built these amazing actuators designed by Lethic and they work so well! Once I have a use for them in a project, I'll probably get the gears printed from a professional 3D printing service...

Aditya Kamath

11,140 Aufrufe • vor 2 Jahren

In a couple months, Do Anything will be almost completely run by Do Anything agents. This week, I decided to let it start running it's own support. In 5 minutes, I set up a regular Do Anything account that has been managing all Do Anything support. Here's how I did it:

In a couple months, Do Anything will be almost completely run by Do Anything agents. This week, I decided to let it start running it's own support. In 5 minutes, I set up a regular Do Anything account that has been managing all Do Anything support. Here's how I did it:

Garrett Scott 🕳

47,719 Aufrufe • vor 7 Monaten

[Fart/Animation] I did not realize its a week about sharks, so have this rough animation of Mako I promised to show for 1k followers. I tried to color it but idk how to work Toonsquid much. I’ll probably do more animations like this in the future.

[Fart/Animation] I did not realize its a week about sharks, so have this rough animation of Mako I promised to show for 1k followers. I tried to color it but idk how to work Toonsquid much. I’ll probably do more animations like this in the future.

Filthy Hobo (INDEFINITE HIATUS)

27,749 Aufrufe • vor 1 Jahr

Panic in the streets of Abu Dhabi, and some parts of the country is burning. This is why I will never support US military base in Nigeria, because we automatically become a target for a war we know nothing about. Ghana should be worried..

Panic in the streets of Abu Dhabi, and some parts of the country is burning. This is why I will never support US military base in Nigeria, because we automatically become a target for a war we know nothing about. Ghana should be worried..

Ainà Dipo 🇳🇬

224,078 Aufrufe • vor 6 Monaten

🇮🇱 Netanyahu: "The Nazis did not politely ask the Jews to leave. 'Did they say please step out so we can move in?' Of course not." "I can name all the genocidal leaders in history and no one did this. So why is it a problem for us?"

🇮🇱 Netanyahu: "The Nazis did not politely ask the Jews to leave. 'Did they say please step out so we can move in?' Of course not." "I can name all the genocidal leaders in history and no one did this. So why is it a problem for us?"

Coinvo

7,074,676 Aufrufe • vor 2 Monaten

HTML Artifacts are a big part of how I work with agents now. Artifacts can be more than just static files. When combined with agents, they can take action or help you take action. This unlocks all kinds of interesting ways to work with agents. This is clearly the future. Check out this writing and scheduler artifact I built in a few minutes. It uses a bit of HTML and JS. All the data is in markdown (Obsidian vaults), so the agent can access and modify it at any time. No DB needed. No sophisticated functionalities. The agent decides all that for me based on the skills, context, and memory it has access to. The best part about this simple stack is that all the important information stays with me. This has allowed me to build a recursive self-improving system and automations that can better tap into coding agents like Codex or Claude Code. I could have paid or built an entire app for scheduling posts, and there are so many of them out there. But I don't need to. I've realized a simple artifact does the job. And the simplicity of it is actually an advantage. Very little maintenance for very high returns on personalization, time, and efficiency. The other benefit of this is that I can add features as I please. That level of personalization feels magical, and we should all be pursuing more of it. All of this just keeps compounding. Of course, this example is just about writing. But I have similar artifacts for research, design, experimentation, evaluation, and so much more. And no, I didn't actually publish the post example I shared in the clip. It was just for demonstration purposes. I actually spend more time than this when writing together with agents. Lastly, having built my own agent orchestrator tool has made me realize that simplifying the tool stack is a superpower. If you are curious about how all this works, I will do a live session next week:

HTML Artifacts are a big part of how I work with agents now. Artifacts can be more than just static files. When combined with agents, they can take action or help you take action. This unlocks all kinds of interesting ways to work with agents. This is clearly the future. Check out this writing and scheduler artifact I built in a few minutes. It uses a bit of HTML and JS. All the data is in markdown (Obsidian vaults), so the agent can access and modify it at any time. No DB needed. No sophisticated functionalities. The agent decides all that for me based on the skills, context, and memory it has access to. The best part about this simple stack is that all the important information stays with me. This has allowed me to build a recursive self-improving system and automations that can better tap into coding agents like Codex or Claude Code. I could have paid or built an entire app for scheduling posts, and there are so many of them out there. But I don't need to. I've realized a simple artifact does the job. And the simplicity of it is actually an advantage. Very little maintenance for very high returns on personalization, time, and efficiency. The other benefit of this is that I can add features as I please. That level of personalization feels magical, and we should all be pursuing more of it. All of this just keeps compounding. Of course, this example is just about writing. But I have similar artifacts for research, design, experimentation, evaluation, and so much more. And no, I didn't actually publish the post example I shared in the clip. It was just for demonstration purposes. I actually spend more time than this when writing together with agents. Lastly, having built my own agent orchestrator tool has made me realize that simplifying the tool stack is a superpower. If you are curious about how all this works, I will do a live session next week:

elvis

18,374 Aufrufe • vor 3 Monaten

I got a message from a lead engineer at one of the largest AI companies freaking out over my use of media they never thought of for high protein AI training data. So I went live to have him listen in. “How the hell did you know all of this and for over 30 years”. 10-4.

I got a message from a lead engineer at one of the largest AI companies freaking out over my use of media they never thought of for high protein AI training data. So I went live to have him listen in. “How the hell did you know all of this and for over 30 years”. 10-4.

Brian Roemmele

184,757 Aufrufe • vor 11 Monaten

Today we're introducing Slite as the first self-maintaining Knowledge Base Your wiki docs go outdated everyday, and your agents depend on them for your most ambitious workflows. Slite monitors your docs' accuracy from all other work tools (slack, jira, linear, codebase, etc) while you sleep and updates them. It even directly talks to your AI agents to give them accurate context without burning their context window or tool calls. You've been trying to build this 'company brain' for months now with hacky MVPs This is the final version of what you need, already built to be collaborative, headless, and secure. Check it out and HMU if you need this for your team, I'll be running personal onboardings for the next few days!

Today we're introducing Slite as the first self-maintaining Knowledge Base Your wiki docs go outdated everyday, and your agents depend on them for your most ambitious workflows. Slite monitors your docs' accuracy from all other work tools (slack, jira, linear, codebase, etc) while you sleep and updates them. It even directly talks to your AI agents to give them accurate context without burning their context window or tool calls. You've been trying to build this 'company brain' for months now with hacky MVPs This is the final version of what you need, already built to be collaborative, headless, and secure. Check it out and HMU if you need this for your team, I'll be running personal onboardings for the next few days!

Christophe Pasquier 🇺🇦

18,084 Aufrufe • vor 2 Monaten

👤 how did you guys feel when yeonjun sunbaenim gifted you the team ring? 🦊 how did you feel? 🐧 when i first saw that he’d prepared this for us, i was so shocked…when did he even prepare something like this? it was so lovely 💗 i’m going to wear it for the rest of my life!!

👤 how did you guys feel when yeonjun sunbaenim gifted you the team ring? 🦊 how did you feel? 🐧 when i first saw that he’d prepared this for us, i was so shocked…when did he even prepare something like this? it was so lovely 💗 i’m going to wear it for the rest of my life!!

💬

58,449 Aufrufe • vor 4 Monaten

Congrats on 1 year back Doki! Thank you so much, Doki, for giving a newbie Animator like me the opportunity to work on the animation for this MV 🏆 I also want to thank all my teammates for their hard work in making this project come out as perfectly as it did ✨ #DokiGallery

Congrats on 1 year back Doki! Thank you so much, Doki, for giving a newbie Animator like me the opportunity to work on the animation for this MV 🏆 I also want to thank all my teammates for their hard work in making this project come out as perfectly as it did ✨ #DokiGallery

Chillifish

18,932 Aufrufe • vor 1 Jahr

Long ago, I did a test for an idea called The Piper. I forgot when I animated it, until we rescanned it and saw erased animation drawings from The Rescuers on the back of some frames. This brings back so many great memories. - Don

Long ago, I did a test for an idea called The Piper. I forgot when I animated it, until we rescanned it and saw erased animation drawings from The Rescuers on the back of some frames. This brings back so many great memories. - Don

Don Bluth

346,272 Aufrufe • vor 2 Jahren

3/ Notebooks: With Web + Work + Pages, you can ideate with AI and collaborate with other people. It has entirely changed my workflow. And now with Notebooks, I can organize all of my heterogeneous data for a project, whether it’s Pages, docs, websites, team meetings – and Copilot will ground itself just on that content. And this might be the best part: I can turn it all into a new modality like an audio overview. For example, I can collect all the latest things I’m reading about agents and agent frameworks, and then I can listen to it.

3/ Notebooks: With Web + Work + Pages, you can ideate with AI and collaborate with other people. It has entirely changed my workflow. And now with Notebooks, I can organize all of my heterogeneous data for a project, whether it’s Pages, docs, websites, team meetings – and Copilot will ground itself just on that content. And this might be the best part: I can turn it all into a new modality like an audio overview. For example, I can collect all the latest things I’m reading about agents and agent frameworks, and then I can listen to it.

Satya Nadella

266,360 Aufrufe • vor 1 Jahr