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.

introducing gen an experimental llm as a server that serves freshly generated html for any endpoint its fun to explore and stumbling upon something that never existed before you clicked is kinda amazing uses gpt-oss with groq (thanks groq and sama <3)

soham

8,422 subscribers

29,302 Aufrufe • vor 11 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

Apple Intelligence looks amazing, but we can’t try it until later this year. So I created an iPhone shortcut that uses Llama 3 with Groq completely for free, and check out how fast it is 🤯 Full video tutorial in the comments.

Apple Intelligence looks amazing, but we can’t try it until later this year. So I created an iPhone shortcut that uses Llama 3 with Groq completely for free, and check out how fast it is 🤯 Full video tutorial in the comments.

Alvaro Cintas

29,902 Aufrufe • vor 2 Jahren

You don't need a combo clip to see that Final Fantasy XVI is an amazing game with a fun engaging combat with some depth 🔥 Also some boss fights are really nice and fun to engage, especially with the approach that you can have in the game thanks to the amazing combat that the game can offer 💪

You don't need a combo clip to see that Final Fantasy XVI is an amazing game with a fun engaging combat with some depth 🔥 Also some boss fights are really nice and fun to engage, especially with the approach that you can have in the game thanks to the amazing combat that the game can offer 💪

MasterNinjaRyu

28,820 Aufrufe • vor 8 Monaten

"The Government of Pakistan has rightly said that if you have any evidence, put it before an independent and neutral commission. No one has the authority to act as judge, jury, and executioner, and that is precisely what India is doing right now." DG ISPR, Lt Gen Ahmed Sharif Chaudhry

"The Government of Pakistan has rightly said that if you have any evidence, put it before an independent and neutral commission. No one has the authority to act as judge, jury, and executioner, and that is precisely what India is doing right now." DG ISPR, Lt Gen Ahmed Sharif Chaudhry

Government of Pakistan

43,769 Aufrufe • vor 1 Jahr

Bodycam is a shooter that you pick up and play for about an hour before you go do something else. Purely made off of asset flips, yet the idea somehow manages to be fun to engage with no matter how brief because "kill time by killing something: the game" is kinda fuckin cool.

Bodycam is a shooter that you pick up and play for about an hour before you go do something else. Purely made off of asset flips, yet the idea somehow manages to be fun to engage with no matter how brief because "kill time by killing something: the game" is kinda fuckin cool.

-/Kapt’n Krunch/-

187,239 Aufrufe • vor 5 Monaten

WATCH: Temple Israel Rabbi Jen Lader SLAMS anyone using the suspect's alleged loss of family in an Israeli airstrike in Lebanon last week as an excuse for yesterday's attack... "My thoughts are that any relationship that -- that any news organization or anyone is -- is talking about in terms of [the suspect's] family's loss of life -- which is a tragedy in and of itself -- any connection to an attack on an American synagogue in the suburbs of metro Detroit is intensely anti-Semitic and inappropriate and and that's something that -- that we've all been been dealing with too, that you know, using that as an excuse for why somebody might have come after a group of American Jews in Detroit. That's anti-Semitism at its -- at its -- at its peak, and -- and we're hoping that that is not the story that people ar telling. And instead, the story is that that American Jews shouldn't have to live this way in fear to send their children to preschool."

WATCH: Temple Israel Rabbi Jen Lader SLAMS anyone using the suspect's alleged loss of family in an Israeli airstrike in Lebanon last week as an excuse for yesterday's attack... "My thoughts are that any relationship that -- that any news organization or anyone is -- is talking about in terms of [the suspect's] family's loss of life -- which is a tragedy in and of itself -- any connection to an attack on an American synagogue in the suburbs of metro Detroit is intensely anti-Semitic and inappropriate and and that's something that -- that we've all been been dealing with too, that you know, using that as an excuse for why somebody might have come after a group of American Jews in Detroit. That's anti-Semitism at its -- at its -- at its peak, and -- and we're hoping that that is not the story that people ar telling. And instead, the story is that that American Jews shouldn't have to live this way in fear to send their children to preschool."

Curtis Houck

198,502 Aufrufe • vor 5 Monaten

LLM Wikis + HTML Artifacts are insanely powerful. You should seriously consider this in your workflows. LLM Wikis captures all the important information that lets you and your agents do meaningful work. HTML artifacts present that information in interesting ways that allow you to take important actions along with your agents. My HTML artifacts sit on top of my LLM wikis. They are dynamic and are easily extended as needs arise. I have hooked my Artifacts to talk to my agents, and similarly, the agents can talk to artifacts. This has allowed me to build powerful artifacts that reduce my inbox to zero, keep me updated on any topic of interest, fast prototyping, do deep research, design/trigger new experiments, generate figures to improve understanding, schedule research, search relevant information, discover topics, and so much more. What you see in the clip is not a website. It's a simple interactive HTML artifact. HTML artifacts are useful for designers, engineers, researchers, students, and anyone working with agents. Lastly, HTML doesn't replace Markdown. They are a much better combination working together.

LLM Wikis + HTML Artifacts are insanely powerful. You should seriously consider this in your workflows. LLM Wikis captures all the important information that lets you and your agents do meaningful work. HTML artifacts present that information in interesting ways that allow you to take important actions along with your agents. My HTML artifacts sit on top of my LLM wikis. They are dynamic and are easily extended as needs arise. I have hooked my Artifacts to talk to my agents, and similarly, the agents can talk to artifacts. This has allowed me to build powerful artifacts that reduce my inbox to zero, keep me updated on any topic of interest, fast prototyping, do deep research, design/trigger new experiments, generate figures to improve understanding, schedule research, search relevant information, discover topics, and so much more. What you see in the clip is not a website. It's a simple interactive HTML artifact. HTML artifacts are useful for designers, engineers, researchers, students, and anyone working with agents. Lastly, HTML doesn't replace Markdown. They are a much better combination working together.

elvis

248,638 Aufrufe • vor 3 Monaten

Have you been deceived to believe that Jesus never existed or that the Bible is a script from the Illuminati or that the name of Jesus is a false name without any power or that you think we live in a faked “simulation” as an excuse to not follow God and Jesus? Bible & Jesus Wins!

Have you been deceived to believe that Jesus never existed or that the Bible is a script from the Illuminati or that the name of Jesus is a false name without any power or that you think we live in a faked “simulation” as an excuse to not follow God and Jesus? Bible & Jesus Wins!

Bret Flat Earth Bible Jesus

43,370 Aufrufe • vor 1 Jahr

Introducing Open MCP Client 🪁 Chat with any MCP server in your own app, just grab a URL from . The team and I vibe coded with Cursor this weekend and built: 1. The first web-based MCP client (link👇) 2. An open-source client you can add into any app How it's built It uses CopilotKit🪁 for the client and interactivity layer, and connects to a 40 line LangGraph ReAct agent that coordinates MCP calls. Hosted on Vercel. Kudos to Suhas Deshpande and Tyler Slaton for hacking and thanks to Harrison Chase for pointers!

Introducing Open MCP Client 🪁 Chat with any MCP server in your own app, just grab a URL from . The team and I vibe coded with Cursor this weekend and built: 1. The first web-based MCP client (link👇) 2. An open-source client you can add into any app How it's built It uses CopilotKit🪁 for the client and interactivity layer, and connects to a 40 line LangGraph ReAct agent that coordinates MCP calls. Hosted on Vercel. Kudos to Suhas Deshpande and Tyler Slaton for hacking and thanks to Harrison Chase for pointers!

Atai Barkai

299,864 Aufrufe • vor 1 Jahr

These are the nights that never die. A big thank you to everyone for the memories made <3 This is my first music video and I've had a ton of fun filming and editing! Alt Link:

These are the nights that never die. A big thank you to everyone for the memories made <3 This is my first music video and I've had a ton of fun filming and editing! Alt Link:

Kazuki

24,054 Aufrufe • vor 1 Jahr

I'm still picking my jaw off the floor with this MCP update: Postman will now automatically build an MCP server for an API. Automatically! You select your API and the requests you want to include, and Potman will generate a Zip file with everything you need. In collaboration with Postman, I recorded a video showing how I generated an MCP server for the Google Maps API. It's glorious! Also, and before I forget: You can now test any MCP server with your Postman application. They built MCP right in, so now you can: • Connect to an MCP server • List out all of the available tools • Test any of the tools This is a 10x boost for the MCP ecosystem. If you've tried the default MCP debugger, you'll understand how huge a deal it is that you can do all of that from Postman now. Go here to give this a try:

I'm still picking my jaw off the floor with this MCP update: Postman will now automatically build an MCP server for an API. Automatically! You select your API and the requests you want to include, and Potman will generate a Zip file with everything you need. In collaboration with Postman, I recorded a video showing how I generated an MCP server for the Google Maps API. It's glorious! Also, and before I forget: You can now test any MCP server with your Postman application. They built MCP right in, so now you can: • Connect to an MCP server • List out all of the available tools • Test any of the tools This is a 10x boost for the MCP ecosystem. If you've tried the default MCP debugger, you'll understand how huge a deal it is that you can do all of that from Postman now. Go here to give this a try:

Santiago

215,882 Aufrufe • vor 1 Jahr

Today I want to make an announcement. Kyogen was started from my love for Ukiyo-e art and it was made real by my fam T̶h̶e̶S̶o̶c̶i̶a̶l̶T̶r̶a̶u̶m̶a̶. I was constantly looking for an artist that can hand draw Kyogen as I do not want it to be AI generated and he reached out saying he can do it. SocialTrauma is an amazing artist that you all should be following as he is doing amazing stuff and if you want to launch a collection, he is the person you should have a chat with. Do follow him as more will come. Kyogen is just the start for me as I have other plans to do more art drop to people to make Ordinals Fun again.

Today I want to make an announcement. Kyogen was started from my love for Ukiyo-e art and it was made real by my fam T̶h̶e̶S̶o̶c̶i̶a̶l̶T̶r̶a̶u̶m̶a̶. I was constantly looking for an artist that can hand draw Kyogen as I do not want it to be AI generated and he reached out saying he can do it. SocialTrauma is an amazing artist that you all should be following as he is doing amazing stuff and if you want to launch a collection, he is the person you should have a chat with. Do follow him as more will come. Kyogen is just the start for me as I have other plans to do more art drop to people to make Ordinals Fun again.

Naqib

12,430 Aufrufe • vor 1 Jahr

i spent the afternoon experimenting with Gemma 4's vision capabilities made an app that uses roboflow RF-DETR for a first pass of object detections and Gemma to summarize the scene in one sentence for fun i asked Gemma to "describe what you see as if you were a medieval bard" all made with free local AI models (running via webgpu in the browser thanks to transformers js) lots more possibilities to explore with this

i spent the afternoon experimenting with Gemma 4's vision capabilities made an app that uses roboflow RF-DETR for a first pass of object detections and Gemma to summarize the scene in one sentence for fun i asked Gemma to "describe what you see as if you were a medieval bard" all made with free local AI models (running via webgpu in the browser thanks to transformers js) lots more possibilities to explore with this

AA

700,941 Aufrufe • vor 4 Monaten

A conversational agent with no hallucinations! This is huge! Here is the $1M problem: Build a customer-facing AI agent that works consistently, doesn't hallucinate, and is fully aligned with the business rules. Check out Parlant, a FREE, open-source library. I've talked about them before, and here is the TL;DR: 1. Parlant gives you 10x more control over what your agent says 2. It helps you control how agents conduct conversations 3. It helps you control the service protocols and rules agents follow 4. It helps you control what agents can and can't say They do something pretty clever: 1. They have a set of predefined potential responses that the agent can use to reply to the customer. 2. When a customer sends a message, the agent generates a fluid response draft using an LLM and matches and renders the closest pre-approved reply template. 3. The agent returns the rendered pre-approved reply, not the one generated by the LLM. This maintains fluidity while avoiding unpredictability. Parlant also uses your domain terminology, invokes your tools, and implements self-critique to craft/evaluate its response iteratively. This pretty much solves any hallucination issues with your agent.

A conversational agent with no hallucinations! This is huge! Here is the $1M problem: Build a customer-facing AI agent that works consistently, doesn't hallucinate, and is fully aligned with the business rules. Check out Parlant, a FREE, open-source library. I've talked about them before, and here is the TL;DR: 1. Parlant gives you 10x more control over what your agent says 2. It helps you control how agents conduct conversations 3. It helps you control the service protocols and rules agents follow 4. It helps you control what agents can and can't say They do something pretty clever: 1. They have a set of predefined potential responses that the agent can use to reply to the customer. 2. When a customer sends a message, the agent generates a fluid response draft using an LLM and matches and renders the closest pre-approved reply template. 3. The agent returns the rendered pre-approved reply, not the one generated by the LLM. This maintains fluidity while avoiding unpredictability. Parlant also uses your domain terminology, invokes your tools, and implements self-critique to craft/evaluate its response iteratively. This pretty much solves any hallucination issues with your agent.

Santiago

64,237 Aufrufe • vor 1 Jahr

New course: MCP: Build Rich-Context AI Apps with Anthropic. Learn to build AI apps that access tools, data, and prompts using the Model Context Protocol in this short course, created in partnership with Anthropic Anthropic and taught by Elie Schoppik Elie Schoppik, its Head of Technical Education. Connecting AI applications to external systems that bring rich context to LLM-based applications has often meant writing custom integrations for each use case. MCP is an open protocol that standardizes how LLMs access tools, data, and prompts from external sources, and simplifies how you provide context to your LLM-based applications. For example, you can provide context via third-party tools that let your LLM make API calls to search the web, access data from local docs, retrieve code from a GitHub repo, and so on. MCP, developed by Anthropic, is based on a client-server architecture that defines the communication details between an MCP client, hosted inside the AI application, and an MCP server that exposes tools, resources, and prompt templates. The server can be a subprocess launched by the client that runs locally or an independent process running remotely. In this hands-on course, you'll learn the core architecture behind MCP. You’ll create an MCP-compatible chatbot, build and deploy an MCP server, and connect the chatbot to your MCP server and other open-source servers. Here’s what you’ll do: - Understand why MCP makes AI development less fragmented and standardizes connections between AI applications and external data sources - Learn the core components of the client-server architecture of MCP and the underlying communication mechanism - Build a chatbot with custom tools for searching academic papers, and transform it into an MCP-compatible application - Build a local MCP server that exposes tools, resources, and prompt templates using FastMCP, and test it using MCP Inspector - Create an MCP client inside your chatbot to dynamically connect to your server - Connect your chatbot to reference servers built by Anthropic’s MCP team, such as filesystem, which implements filesystem operations, and fetch, which extracts contents from the web as markdown - Configure Claude Desktop to connect to your server and others, and explore how it abstracts away the low-level logic of MCP clients - Deploy your MCP server remotely and test it with the Inspector or other MCP-compatible applications - Learn about the roadmap for future MCP development, such as multi-agent architecture, MCP registry API, server discovery, authorization, and authentication MCP is an exciting and important technology that lets you build rich-context AI applications that connect to a growing ecosystem of MCP servers, with minimal integration work. Please sign up here!

New course: MCP: Build Rich-Context AI Apps with Anthropic. Learn to build AI apps that access tools, data, and prompts using the Model Context Protocol in this short course, created in partnership with Anthropic Anthropic and taught by Elie Schoppik Elie Schoppik, its Head of Technical Education. Connecting AI applications to external systems that bring rich context to LLM-based applications has often meant writing custom integrations for each use case. MCP is an open protocol that standardizes how LLMs access tools, data, and prompts from external sources, and simplifies how you provide context to your LLM-based applications. For example, you can provide context via third-party tools that let your LLM make API calls to search the web, access data from local docs, retrieve code from a GitHub repo, and so on. MCP, developed by Anthropic, is based on a client-server architecture that defines the communication details between an MCP client, hosted inside the AI application, and an MCP server that exposes tools, resources, and prompt templates. The server can be a subprocess launched by the client that runs locally or an independent process running remotely. In this hands-on course, you'll learn the core architecture behind MCP. You’ll create an MCP-compatible chatbot, build and deploy an MCP server, and connect the chatbot to your MCP server and other open-source servers. Here’s what you’ll do: - Understand why MCP makes AI development less fragmented and standardizes connections between AI applications and external data sources - Learn the core components of the client-server architecture of MCP and the underlying communication mechanism - Build a chatbot with custom tools for searching academic papers, and transform it into an MCP-compatible application - Build a local MCP server that exposes tools, resources, and prompt templates using FastMCP, and test it using MCP Inspector - Create an MCP client inside your chatbot to dynamically connect to your server - Connect your chatbot to reference servers built by Anthropic’s MCP team, such as filesystem, which implements filesystem operations, and fetch, which extracts contents from the web as markdown - Configure Claude Desktop to connect to your server and others, and explore how it abstracts away the low-level logic of MCP clients - Deploy your MCP server remotely and test it with the Inspector or other MCP-compatible applications - Learn about the roadmap for future MCP development, such as multi-agent architecture, MCP registry API, server discovery, authorization, and authentication MCP is an exciting and important technology that lets you build rich-context AI applications that connect to a growing ecosystem of MCP servers, with minimal integration work. Please sign up here!

Andrew Ng

142,010 Aufrufe • vor 1 Jahr

Grok 4.5 is a "Wow!" moment. 🤯 > Opus 4.8 & GPT-5.5 level on benchmarks > Costs less than Sonnet 5 Is that real? Hard to believe. Added Grok 4.5 as an implementer agent in fable-advisor. It replaces Sonnet 5. Use Fable as the orchestrator and a combo of: 1. Grok 4.5 2. Opus 4.8 3. GPT-5.5 As implementer agents. Uses the Grok Build CLI so if you log in with an X premium account you don't have to pay API fees.

Grok 4.5 is a "Wow!" moment. 🤯 > Opus 4.8 & GPT-5.5 level on benchmarks > Costs less than Sonnet 5 Is that real? Hard to believe. Added Grok 4.5 as an implementer agent in fable-advisor. It replaces Sonnet 5. Use Fable as the orchestrator and a combo of: 1. Grok 4.5 2. Opus 4.8 3. GPT-5.5 As implementer agents. Uses the Grok Build CLI so if you log in with an X premium account you don't have to pay API fees.

Dan McAteer

191,013 Aufrufe • vor 1 Monat

Nvidia just made its biggest acquisition ever... A small startup. On Christmas Eve. While everyone was distracted. The startup is Groq. They make AI chips that run faster than Nvidia's. In September, Groq raised $750 million at a $6.9 billion valuation. Investors included BlackRock, Samsung, Cisco, and Donald Trump Jr.'s fund 1789 Capital. Yesterday, Nvidia paid $20 billion for them. That's a 3x markup in 90 days. Trump Jr. just made a fortune overnight. But the money isn't even the craziest part... Nvidia dominates AI chips. They have 90%+ market share. All of big tech depends on them. So why would they pay 3X for a tiny competitor? Let me explain: Groq was building inference chips that threatened Nvidia's monopoly. Faster processing. Lower costs. Better architecture. If Groq succeeded, they'd crack open the market. So Nvidia did what monopolies always do: bought them before they became a threat. They're buying silence - not innovation. And this isn't a one-off. In September, Nvidia spent $900 million on Enfabrica, another AI chip startup. Same playbook. They committed $100 billion to OpenAI with a requirement that OpenAI deploy 10 gigawatts of Nvidia products. Now $20 billion for Groq. Nvidia isn't competing anymore. They're consolidating. They're using their cash pile to swallow every potential rival before they grow. The founder and CEO of Groq, Jonathan Ross, is joining Nvidia. So is the president and the entire leadership team. Groq's cloud business will keep running independently. But the tech, the IP, the competitive advantage? All Nvidia's now. This is the largest acquisition Nvidia has EVER made. Their previous record was $7 billion for Mellanox in 2019. They just tripled that. And nobody's questioning why. Everyone's celebrating "innovation" and "consolidation" and "strategic partnerships." But what actually happened is this: Nvidia looked at the one company that could challenge their monopoly and paid whatever it took to kill them. $20 billion is cheap insurance when you're worth trillions. The only question left is who's next.

Nvidia just made its biggest acquisition ever... A small startup. On Christmas Eve. While everyone was distracted. The startup is Groq. They make AI chips that run faster than Nvidia's. In September, Groq raised $750 million at a $6.9 billion valuation. Investors included BlackRock, Samsung, Cisco, and Donald Trump Jr.'s fund 1789 Capital. Yesterday, Nvidia paid $20 billion for them. That's a 3x markup in 90 days. Trump Jr. just made a fortune overnight. But the money isn't even the craziest part... Nvidia dominates AI chips. They have 90%+ market share. All of big tech depends on them. So why would they pay 3X for a tiny competitor? Let me explain: Groq was building inference chips that threatened Nvidia's monopoly. Faster processing. Lower costs. Better architecture. If Groq succeeded, they'd crack open the market. So Nvidia did what monopolies always do: bought them before they became a threat. They're buying silence - not innovation. And this isn't a one-off. In September, Nvidia spent $900 million on Enfabrica, another AI chip startup. Same playbook. They committed $100 billion to OpenAI with a requirement that OpenAI deploy 10 gigawatts of Nvidia products. Now $20 billion for Groq. Nvidia isn't competing anymore. They're consolidating. They're using their cash pile to swallow every potential rival before they grow. The founder and CEO of Groq, Jonathan Ross, is joining Nvidia. So is the president and the entire leadership team. Groq's cloud business will keep running independently. But the tech, the IP, the competitive advantage? All Nvidia's now. This is the largest acquisition Nvidia has EVER made. Their previous record was $7 billion for Mellanox in 2019. They just tripled that. And nobody's questioning why. Everyone's celebrating "innovation" and "consolidation" and "strategic partnerships." But what actually happened is this: Nvidia looked at the one company that could challenge their monopoly and paid whatever it took to kill them. $20 billion is cheap insurance when you're worth trillions. The only question left is who's next.

Ricardo

224,264 Aufrufe • vor 7 Monaten

Mattel Inc. is introducing an autistic Barbie as the newest member of its line intended to celebrate diversity, developed in partnership with a nonprofit organization that advocates for the rights and better media representation of people with autism.

Mattel Inc. is introducing an autistic Barbie as the newest member of its line intended to celebrate diversity, developed in partnership with a nonprofit organization that advocates for the rights and better media representation of people with autism.

ABC News

370,227 Aufrufe • vor 7 Monaten

Introducing `gut` - an AI agent for git 🤖🧑‍💻 This is a really neat CLI-based tool from Clelia Bertelli that lets you ask about and execute git commands through natural language! Describe what you want to do in English (e.g. a complex rebase), and it’ll let you review and auto-execute each command while explaining what it does. It’s a neat, minimal helper tool for anyone ramping up on version control tools like git + GitHub. Powered by LlamaIndex 🦙 workflows and Groq Inc To use it: `pip install gut-ai` Repo:

Introducing `gut` - an AI agent for git 🤖🧑‍💻 This is a really neat CLI-based tool from Clelia Bertelli that lets you ask about and execute git commands through natural language! Describe what you want to do in English (e.g. a complex rebase), and it’ll let you review and auto-execute each command while explaining what it does. It’s a neat, minimal helper tool for anyone ramping up on version control tools like git + GitHub. Powered by LlamaIndex 🦙 workflows and Groq Inc To use it: `pip install gut-ai` Repo:

Jerry Liu

17,065 Aufrufe • vor 1 Jahr

i built an ai agent that talks to my girlfriend 24/7. fully open source. sometimes i am on a plane or just working, so i built an ai that uses Nozomio Labs’s search api to index and search through 5,000 pickup lines and methods on how to talk to women. it also has its own telegram that uses my account to send, receive, record, and schedule messages to my girlfriend, with built-in memory that analyzes her mood and tells me when something is wrong. here is a demo of me asking an agent to search for some pickup lines and create a 7-day meal plan for her:

i built an ai agent that talks to my girlfriend 24/7. fully open source. sometimes i am on a plane or just working, so i built an ai that uses Nozomio Labs’s search api to index and search through 5,000 pickup lines and methods on how to talk to women. it also has its own telegram that uses my account to send, receive, record, and schedule messages to my girlfriend, with built-in memory that analyzes her mood and tells me when something is wrong. here is a demo of me asking an agent to search for some pickup lines and create a 7-day meal plan for her:

Arlan

396,501 Aufrufe • vor 7 Monaten