Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

(Bonus)/ LlamaFS Local LLM-powered hard drive file organizer. Automatically rename and categorize messy files and directories with multi-modal AI Everyone was asking me nonstop what we built, so here it is :) Thomas Dhome-Casanova Ajay Uppili Arasanipalai @AshwinHegd28838

AlexReibman's profile picture

Alex Reibman 🖇️

57,305 subscribers

359,947 Aufrufe • vor 2 Jahren •via X (Twitter)

Wissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

15 Kommentare

Profilbild von Alex Reibman 🖇️
Alex Reibman 🖇️vor 2 Jahren

Meta launched Llama 3 to show the world what’s possible with open source LLMs. 500+ AI engineers just spent 24 hours straight putting it to the test. Here’s what we saw at the @AIatMeta x @cerebral_valley #Llama3Hackathon (🧵):

Profilbild von Alex Reibman 🖇️
Alex Reibman 🖇️vor 2 Jahren

1/ JoeCRM AI-first CRM that receives signals about customers, performs research about them, and automatically drafts outreach campaigns @GregTanaka

Profilbild von Alex Reibman 🖇️
Alex Reibman 🖇️vor 2 Jahren

2/ Activation Ablation Augmentation Research team that identified how to nullify activation layers in Llama3 responsible for censorship @song_minjune @IanSears96 @Nottlespike 🥉 3rd place

Profilbild von Alex Reibman 🖇️
Alex Reibman 🖇️vor 2 Jahren

3/ OpenGlass $20 budget smart glasses that can answer questions about what you’re looking at 🥇1st place @kodjima33 @sramanan @Jat1nn @scottfits @Ex3NDR

Profilbild von Alex Reibman 🖇️
Alex Reibman 🖇️vor 2 Jahren

4/ Feycher Fast AI avatars that speaks responses with lip-syncing. Context loaded by recent events from the @brave news API

Profilbild von Alex Reibman 🖇️
Alex Reibman 🖇️vor 2 Jahren

5/ Hound AI to help law enforcement crack down on human trafficking

Profilbild von Alex Reibman 🖇️
Alex Reibman 🖇️vor 2 Jahren

6/ Mongoose Miner Improved Python codegen made by providing llama 3 with up to date documentation

Profilbild von Alex Reibman 🖇️
Alex Reibman 🖇️vor 2 Jahren

7/ Deb8 AI agent debate arena where different models compete in Lincoln-Douglas debate. A third agent rates the quality of the debaters and scores them 🥈 2nd place @dvlpjrs @TirthGShah @JulianaChyzhova @

Profilbild von Alex Reibman 🖇️
Alex Reibman 🖇️vor 2 Jahren

8/ City Hub Llama3 powered chat agent that lets residents ask questions about city laws and regulations. RAG’s over city documents to inform the answers Chat with your city

Profilbild von Alex Reibman 🖇️
Alex Reibman 🖇️vor 2 Jahren

Huge thanks to @AIatMeta @huggingface @GroqInc @weights_biases @brave @llama_index @OctoAICloud @LambdaAPI @cerebral_valley @ollama @JonathanRoss321 @BraveSampson @DynamicWebPaige @altryne @asangani7 Itching to build AI? Another’s coming May 18. Follow @AgentOpsAI @AlexReibman

Profilbild von Alex Reibman 🖇️
Alex Reibman 🖇️vor 2 Jahren

Bonus 2/ AI glasses Smart glasses that let you highlight physical book pages and automatically record them as notes One of the coolest hacks I’ve seen to date @ayushkhd

Profilbild von swyx /dd
swyx /ddvor 2 Jahren

@swayingoak @iyajainfinity @AshwinHegd28838 i love love love that you're still an active hacker in these. keep it up!

Profilbild von Alex Reibman 🖇️
Alex Reibman 🖇️vor 2 Jahren

@swayingoak @iyajainfinity @AshwinHegd28838 Seems like play but it's actually work! I dogfood @agentopsai with just about every project I build. Plus get other people to give feedback

Profilbild von UNAUTHORIZED PERSON
UNAUTHORIZED PERSONvor 2 Jahren

@swayingoak @iyajainfinity @AshwinHegd28838

Profilbild von Alex Reibman 🖇️
Alex Reibman 🖇️vor 2 Jahren

@swayingoak @iyajainfinity @AshwinHegd28838 check it out

Ähnliche Videos

New short course: Build AI Apps with MCP Servers: Working with Box Files, built with Box and taught by Ben Kus , their CTO. Many AI applications require custom code for basic file operations. The Model Context Protocol (MCP) standardizes this by letting you offload file tasks to dedicated servers that provide tools an LLM can use directly. In this course, you'll process documents stored in a Box folder using the Box MCP server. Rather than writing custom integration code to connect to the Box API and download files, you'll design your application to use the tools provided via MCP. Skills you'll gain: - Build an LLM-powered document processing app, using the Box MCP server to access files - Design a multi-agent system using Google's Agent Development Kit (ADK), consisting of specialized agents for file operations - Coordinate the multi-agent workflow through an orchestrator that uses the Agent2Agent (A2A) protocol to connect to the agents You'll start with a local file-processing app, refactor it to work with Box's MCP server, then evolve it into a multi-agent system. Sign up here:
1:48

New short course: Build AI Apps with MCP Servers: Working with Box Files, built with Box and taught by Ben Kus , their CTO. Many AI applications require custom code for basic file operations. The Model Context Protocol (MCP) standardizes this by letting you offload file tasks to dedicated servers that provide tools an LLM can use directly. In this course, you'll process documents stored in a Box folder using the Box MCP server. Rather than writing custom integration code to connect to the Box API and download files, you'll design your application to use the tools provided via MCP. Skills you'll gain: - Build an LLM-powered document processing app, using the Box MCP server to access files - Design a multi-agent system using Google's Agent Development Kit (ADK), consisting of specialized agents for file operations - Coordinate the multi-agent workflow through an orchestrator that uses the Agent2Agent (A2A) protocol to connect to the agents You'll start with a local file-processing app, refactor it to work with Box's MCP server, then evolve it into a multi-agent system. Sign up here:

Andrew Ng

81,696 Aufrufe • vor 11 Monaten

I built a form-filling agent that anyone can use 💫 This is an extremely simple but useful (I hope) app. Upload a fillable form 📋, some context files, and chat with the agent to fill the form out automatically ✍️ 1️⃣ Yes it is a Claude Code SDK wrapper 2️⃣ It is better and faster than ChatGPT/Claude UI out of the box 3️⃣ We use LlamaParse to parse the context files, so you can have more trust that we are able to read context without hallucinations (e.g. messy scanned handwriting, drivers license photo, and more). This was one of my holiday Claude Code vibe-coding projects. Built with Opus 4.5, and also powered by Opus 4.5. Feeling the AGI 🫡 App is here: Repo is open-source:
1:48

I built a form-filling agent that anyone can use 💫 This is an extremely simple but useful (I hope) app. Upload a fillable form 📋, some context files, and chat with the agent to fill the form out automatically ✍️ 1️⃣ Yes it is a Claude Code SDK wrapper 2️⃣ It is better and faster than ChatGPT/Claude UI out of the box 3️⃣ We use LlamaParse to parse the context files, so you can have more trust that we are able to read context without hallucinations (e.g. messy scanned handwriting, drivers license photo, and more). This was one of my holiday Claude Code vibe-coding projects. Built with Opus 4.5, and also powered by Opus 4.5. Feeling the AGI 🫡 App is here: Repo is open-source:

Jerry Liu

48,428 Aufrufe • vor 7 Monaten

Everyone keeps asking me how to build a second brain or an LLM wiki. Here is the easiest setup I have found. I took my Wiki Builder skill, installed it into HyperAgent (Hyperagent) as a reusable skill, and asked it to build a research wiki on LLM verification from the latest 2026 papers. Recorded a quick demo. Built with Hyperagent. It planned first, asked a few sharp questions, then did the research: 29 papers curated into 21 files, a research map, a glossary, and clean subfields. Now it is a knowledge base that my other research agents build on. HyperAgent has all the capabilities to allow your agents and skills to compound. That’s a powerful use of AI agents.
8:03

Everyone keeps asking me how to build a second brain or an LLM wiki. Here is the easiest setup I have found. I took my Wiki Builder skill, installed it into HyperAgent (Hyperagent) as a reusable skill, and asked it to build a research wiki on LLM verification from the latest 2026 papers. Recorded a quick demo. Built with Hyperagent. It planned first, asked a few sharp questions, then did the research: 29 papers curated into 21 files, a research map, a glossary, and clean subfields. Now it is a knowledge base that my other research agents build on. HyperAgent has all the capabilities to allow your agents and skills to compound. That’s a powerful use of AI agents.

elvis

226,001 Aufrufe • vor 1 Monat

This is one of the wildest things I have built with AI so far 😱 Asked Claude Fable 5 to create a fully interactive 3D crime investigation board using Three.js and it did it in ONE Prompt. It took one more prompt to give it a polished UI inspired by a reference design that I created with GPT Image. What surprised me most was not how it looked. It was how it worked. Fable built a complete Verlet rope physics system with 46 particles in every thread. It handled gravity, damping, distance constraints and all other features of file upload, text and everything. The threads/ropes even lift naturally with pinned evidence instead of clipping through it. I never asked it to implement any of that. I only described the experience I wanted. Maybe that's how we should work with AI. Instead of writing long long specs, we should explain what we want as an experience and let AI do its thing. Anyway, every day Fable 5 raises the bar for what I think AI can build. More to this Live: Code:
0:49

This is one of the wildest things I have built with AI so far 😱 Asked Claude Fable 5 to create a fully interactive 3D crime investigation board using Three.js and it did it in ONE Prompt. It took one more prompt to give it a polished UI inspired by a reference design that I created with GPT Image. What surprised me most was not how it looked. It was how it worked. Fable built a complete Verlet rope physics system with 46 particles in every thread. It handled gravity, damping, distance constraints and all other features of file upload, text and everything. The threads/ropes even lift naturally with pinned evidence instead of clipping through it. I never asked it to implement any of that. I only described the experience I wanted. Maybe that's how we should work with AI. Instead of writing long long specs, we should explain what we want as an experience and let AI do its thing. Anyway, every day Fable 5 raises the bar for what I think AI can build. More to this Live: Code:

The Bugged Dev

103,991 Aufrufe • vor 1 Monat

This Is Absolutely Mind Blowing ⚠️ Barack Obama’s New Movie, Leave The World Behind, When Downloaded & Put Into An Editing Program Has 4 Audio Files Instead Of The Standard 1 One Of The Audio Files Is Just A Frequency 🚨 “Low Frequency Infrasound” Other Movies Do Not Have This. The Guy Has Done Thousands Of Movies & Never Seen This “When you open this this movie right here is Jurassic Park, for instance. Okay? I'm just showing this to people who have never seen this. For the last 15 years that I have been using Sony Vegas and other editing software and have gone through downloading movies And using them in our own video production, 100% of the time, it's either an MKV or a MP For occasionally, you'll download a torrent that's in AVR, but not very often. And this is what it will always look like. One video file right here. One audio file right here always. That's been my experience. Now let me show you what happened when we downloaded and put, Sony put the, uh, movie Leave the World Behind onto Sony Vegas. Here you go. Stunning. Stunning. One video file, 4 audio files opened up. And this one, This 4th audio file seems to be the weapon. This is a low ex uh, ELF, Uh, Low Frequency Infrasound. Infrasonic wave right here. And, um, so we We are gonna let me put the camera back on again. So this is big news just just so people realize. In in 15 years of video editing, I have never downloaded now speaking specifically a movie file. Okay. A Hollywood movie from a torrent downloading it in either MKV, MP4, occasionally AVI. 100% of the time, over a thousands movies I've done this with, you have video file, audio file, period. This is the very first time I've ever seen anything like this with the 4 files. Bonnie's gonna go into now talking about the The infrasonic sound waves and what we found out about that and the fact that there's one here. We're in the point is we're going to go back after Bonnie gives you some information about what it is we're dealing with, how this is a weapon. Then we're gonna go back, uh, towards the end of the live stream here. And I'm gonna hit specific places where this weapon was used against anybody who watches it. Okay.”
2:26

This Is Absolutely Mind Blowing ⚠️ Barack Obama’s New Movie, Leave The World Behind, When Downloaded & Put Into An Editing Program Has 4 Audio Files Instead Of The Standard 1 One Of The Audio Files Is Just A Frequency 🚨 “Low Frequency Infrasound” Other Movies Do Not Have This. The Guy Has Done Thousands Of Movies & Never Seen This “When you open this this movie right here is Jurassic Park, for instance. Okay? I'm just showing this to people who have never seen this. For the last 15 years that I have been using Sony Vegas and other editing software and have gone through downloading movies And using them in our own video production, 100% of the time, it's either an MKV or a MP For occasionally, you'll download a torrent that's in AVR, but not very often. And this is what it will always look like. One video file right here. One audio file right here always. That's been my experience. Now let me show you what happened when we downloaded and put, Sony put the, uh, movie Leave the World Behind onto Sony Vegas. Here you go. Stunning. Stunning. One video file, 4 audio files opened up. And this one, This 4th audio file seems to be the weapon. This is a low ex uh, ELF, Uh, Low Frequency Infrasound. Infrasonic wave right here. And, um, so we We are gonna let me put the camera back on again. So this is big news just just so people realize. In in 15 years of video editing, I have never downloaded now speaking specifically a movie file. Okay. A Hollywood movie from a torrent downloading it in either MKV, MP4, occasionally AVI. 100% of the time, over a thousands movies I've done this with, you have video file, audio file, period. This is the very first time I've ever seen anything like this with the 4 files. Bonnie's gonna go into now talking about the The infrasonic sound waves and what we found out about that and the fact that there's one here. We're in the point is we're going to go back after Bonnie gives you some information about what it is we're dealing with, how this is a weapon. Then we're gonna go back, uh, towards the end of the live stream here. And I'm gonna hit specific places where this weapon was used against anybody who watches it. Okay.”

Wall Street Apes

3,769,180 Aufrufe • vor 2 Jahren

VoiceBox just did what everyone thought was impossible. It might have killed ElevenLabs overnight. No subscription. No cloud. No credits. Runs locally on your machine. Clones a voice from 3 seconds of audio. Powered by Qwen 3 TTS. Apache 2.0 license. Commercial use allowed. And your voice data never leaves your computer. For years, if you wanted high quality voice cloning, ElevenLabs was the default. Now there’s a free open-source alternative that sounds shockingly close. Plus it has a built-in multi-track editor, recording, transcription with Whisper, and a local API. This isn’t just another TTS tool. It’s a full voice production studio on your desktop. Open source AI is catching up fast. And this changes the game for creators and businesses. Would you trust the cloud with your voice… or keep it local? 👇
8:20

VoiceBox just did what everyone thought was impossible. It might have killed ElevenLabs overnight. No subscription. No cloud. No credits. Runs locally on your machine. Clones a voice from 3 seconds of audio. Powered by Qwen 3 TTS. Apache 2.0 license. Commercial use allowed. And your voice data never leaves your computer. For years, if you wanted high quality voice cloning, ElevenLabs was the default. Now there’s a free open-source alternative that sounds shockingly close. Plus it has a built-in multi-track editor, recording, transcription with Whisper, and a local API. This isn’t just another TTS tool. It’s a full voice production studio on your desktop. Open source AI is catching up fast. And this changes the game for creators and businesses. Would you trust the cloud with your voice… or keep it local? 👇

Julian Goldie SEO

59,167 Aufrufe • vor 6 Monaten

Agents Are Replacing SaaS 🟢 And We’re Living It At Assisterr, we don’t just build AI agents - we use them Our own infrastructure has already replaced most traditional SaaS tools with custom-built AI agents that handle everything from analytics and reporting to workflow automation Need deep product insights? Our Analytics Assistant tracks real-time data, generates reports, and delivers actionable insights—automatically 🚀 Need a new tool? We don’t waste time looking for SaaS alternatives - we just build a custom agent. No code, no hassle, just instant automation We’re committed to making this accessible to everyone—so anyone can create, customize, and deploy AI agents tailored to their needs The future isn’t SaaS. The future is agents. And with Assisterr, it’s already here
3:43

Agents Are Replacing SaaS 🟢 And We’re Living It At Assisterr, we don’t just build AI agents - we use them Our own infrastructure has already replaced most traditional SaaS tools with custom-built AI agents that handle everything from analytics and reporting to workflow automation Need deep product insights? Our Analytics Assistant tracks real-time data, generates reports, and delivers actionable insights—automatically 🚀 Need a new tool? We don’t waste time looking for SaaS alternatives - we just build a custom agent. No code, no hassle, just instant automation We’re committed to making this accessible to everyone—so anyone can create, customize, and deploy AI agents tailored to their needs The future isn’t SaaS. The future is agents. And with Assisterr, it’s already here

assisterr

28,822 Aufrufe • vor 1 Jahr

Justin Thomas was asked about his group getting put on the clock: "We just didn't really agree with it. ... The hard part to me with the whole pace of play thing is that you, there's so much that goes into golf and there's so much that goes into hole to hole in terms of, are you hitting it close, are you able to tap it in, or you have to mark it, stuff like that, to where, are you holding the group up or are you not, to where it's very hard to make that call. And we just didn't agree with it, to be honest. "But we got taken off, and a hole later we were caught up. So it kind of goes to our point of why we didn't think we should of, but it is what it is. It's a part of it."
1:15

Justin Thomas was asked about his group getting put on the clock: "We just didn't really agree with it. ... The hard part to me with the whole pace of play thing is that you, there's so much that goes into golf and there's so much that goes into hole to hole in terms of, are you hitting it close, are you able to tap it in, or you have to mark it, stuff like that, to where, are you holding the group up or are you not, to where it's very hard to make that call. And we just didn't agree with it, to be honest. "But we got taken off, and a hole later we were caught up. So it kind of goes to our point of why we didn't think we should of, but it is what it is. It's a part of it."

Cameron Jourdan

619,266 Aufrufe • vor 3 Monaten

#WATCH | Acharya Mahamandaleshwar Laxmi Narayan Tripathi of Kinnar Akhara says, "...When we started in 2015, Rishi Ajay Das was indeed with us. But the ashram that was donated to Kinnar Akhara, Rishi Ajay Das sold it and used the money for luxury. He was in Mumbai for a few days but now he lives in Jaipur with his family. Rishi Ajay Das pocketed all the money of Kinnar Akhara in 2016 Kumbh. Kinnars were left with nothing...So, when it came to registration, we got registered together with the Kinnars...We had a Board meeting in 2024 October, a new Board was established. We expelled Rishi Ajay Das in 2017...We didn't want any tension, so we distanced ourselves from him because he married Archana Das later and they have a daughter. Computer Baba is his friend. Had he been the Founder, he would have stayed with Kinnar Akhara...What was the need of going to someone else's 'chhawani' to say something? It is sad to say that for publicity, a person is stooping to any level. If Mamta (Kulkarni) had embraced Islam, would these religious Heads have said something? If a Sanatani has come closer to Sanatana, everyone is troubled...Kinnars anointed me as Mahamandaleshwar. Who is a man to make someone a Mahamandaleshwar of Kinnar Akhara?.. We will serve him a defamation notice. The entire Kinnar Akhara stands with me and I stand with Kinnar Akhara..."
5:24

#WATCH | Acharya Mahamandaleshwar Laxmi Narayan Tripathi of Kinnar Akhara says, "...When we started in 2015, Rishi Ajay Das was indeed with us. But the ashram that was donated to Kinnar Akhara, Rishi Ajay Das sold it and used the money for luxury. He was in Mumbai for a few days but now he lives in Jaipur with his family. Rishi Ajay Das pocketed all the money of Kinnar Akhara in 2016 Kumbh. Kinnars were left with nothing...So, when it came to registration, we got registered together with the Kinnars...We had a Board meeting in 2024 October, a new Board was established. We expelled Rishi Ajay Das in 2017...We didn't want any tension, so we distanced ourselves from him because he married Archana Das later and they have a daughter. Computer Baba is his friend. Had he been the Founder, he would have stayed with Kinnar Akhara...What was the need of going to someone else's 'chhawani' to say something? It is sad to say that for publicity, a person is stooping to any level. If Mamta (Kulkarni) had embraced Islam, would these religious Heads have said something? If a Sanatani has come closer to Sanatana, everyone is troubled...Kinnars anointed me as Mahamandaleshwar. Who is a man to make someone a Mahamandaleshwar of Kinnar Akhara?.. We will serve him a defamation notice. The entire Kinnar Akhara stands with me and I stand with Kinnar Akhara..."

ANI

25,440 Aufrufe • vor 1 Jahr

AI spend is now one of the fastest-growing line items at every company, but here's the problem: it's invisible to traditional spend management. We experienced this firsthand at Brex, so we built Magpie: an internal tool that sources and normalizes AI spend across every vendor so we can break it down by model, customer, employee, and workflow. What Magpie has already unlocked: → ~85% cost reduction on an audit agent through prompt caching → Real customer cost-to-serve numbers that inform pricing and margin → Model routing governance we couldn't enforce before → A surprise: operational AI is much cheaper than we assumed So why is AI spend so hard to track? Because each one exposes usage data differently (some not at all). At Brex, tool-use costs weren't tracked alongside tokens, customer attribution was inconsistent, and a meaningful chunk of our daily AI spend was unattributable. Now with Magpie, we have reliable visibility. AI spend is more complex than anything finance teams have had to manage before, and it's exactly the kind of problem Brex is built to solve, shaping how we think about the future of our platform. More below.
1:56

AI spend is now one of the fastest-growing line items at every company, but here's the problem: it's invisible to traditional spend management. We experienced this firsthand at Brex, so we built Magpie: an internal tool that sources and normalizes AI spend across every vendor so we can break it down by model, customer, employee, and workflow. What Magpie has already unlocked: → ~85% cost reduction on an audit agent through prompt caching → Real customer cost-to-serve numbers that inform pricing and margin → Model routing governance we couldn't enforce before → A surprise: operational AI is much cheaper than we assumed So why is AI spend so hard to track? Because each one exposes usage data differently (some not at all). At Brex, tool-use costs weren't tracked alongside tokens, customer attribution was inconsistent, and a meaningful chunk of our daily AI spend was unattributable. Now with Magpie, we have reliable visibility. AI spend is more complex than anything finance teams have had to manage before, and it's exactly the kind of problem Brex is built to solve, shaping how we think about the future of our platform. More below.

Pedro Franceschi

28,580 Aufrufe • vor 2 Monaten

#HUMAINChat is LIVE! Today marks a moment of pride - not only for but for all of Saudi Arabia with the launch of HUMAIN Chat, powered by ALLAM34B, the most advanced Arabic-first LLM built in the Arab world fluent in our culture, our values, and our heritage. It was deeply important to me to deliver this message to you, the Saudi people, in your native language. I recognize that my Arabic isn’t perfect, but just like me, HUMAIN Chat is still improving. And this is where I need your support. Your conversations and interactions with HUMAIN Chat will directly help improve the LLM powering it. This is your opportunity to shape a Saudi-born, Arabic-first digital product into the best of its kind before we roll it out to the world. Download HUMAIN Chat now and make it your go-to AI companion: #HUMAINAI #TheEndOfLimits
0:57

#HUMAINChat is LIVE! Today marks a moment of pride - not only for but for all of Saudi Arabia with the launch of HUMAIN Chat, powered by ALLAM34B, the most advanced Arabic-first LLM built in the Arab world fluent in our culture, our values, and our heritage. It was deeply important to me to deliver this message to you, the Saudi people, in your native language. I recognize that my Arabic isn’t perfect, but just like me, HUMAIN Chat is still improving. And this is where I need your support. Your conversations and interactions with HUMAIN Chat will directly help improve the LLM powering it. This is your opportunity to shape a Saudi-born, Arabic-first digital product into the best of its kind before we roll it out to the world. Download HUMAIN Chat now and make it your go-to AI companion: #HUMAINAI #TheEndOfLimits

Tareq Amin

52,845 Aufrufe • vor 1 Jahr

The next door neighbor is giving the woman a hard time about building the fence near his garage. What makes his ridiculous is that his garage was built without a permit and part of it is on her property. When she confronted him about it, he admits he knows it’s her land and claims the previous owner told him he could do it. To me it seems like he’s trying to bully her into getting his own way, but shouldn’t she file a complaint with the city and have it surveyed so she can get her property back?
3:48

The next door neighbor is giving the woman a hard time about building the fence near his garage. What makes his ridiculous is that his garage was built without a permit and part of it is on her property. When she confronted him about it, he admits he knows it’s her land and claims the previous owner told him he could do it. To me it seems like he’s trying to bully her into getting his own way, but shouldn’t she file a complaint with the city and have it surveyed so she can get her property back?

SonnyBoy🇺🇸

128,353 Aufrufe • vor 5 Monaten

okay Higgsfield Supercomputer is genuinely insane 🤯 it scans your competitors every Monday and drafts 3 ads before you open your laptop it's a cloud-native AI agent built for end-to-end creative production no local setup. runs in your browser or Telegram. here's what it actually does: → orchestrates every major model Claude Opus 4.7, GPT-5.5 Pro, Gemini 3.1 Pro, plus every image and video model → three layers of memory brief it once, it remembers context across every session → 40+ built-in tools with Skills you teach once and trigger with a slash command → scheduled tasks daily ad variations, weekly competitor scans, monthly content calendars → connects to Slack, Drive, Notion, Gmail, Figma and 30+ more powered by enhanced Hermes Agent Higgsfield was an AI video tool, this isn't a video tool anymore it's the whole studio.
1:26

okay Higgsfield Supercomputer is genuinely insane 🤯 it scans your competitors every Monday and drafts 3 ads before you open your laptop it's a cloud-native AI agent built for end-to-end creative production no local setup. runs in your browser or Telegram. here's what it actually does: → orchestrates every major model Claude Opus 4.7, GPT-5.5 Pro, Gemini 3.1 Pro, plus every image and video model → three layers of memory brief it once, it remembers context across every session → 40+ built-in tools with Skills you teach once and trigger with a slash command → scheduled tasks daily ad variations, weekly competitor scans, monthly content calendars → connects to Slack, Drive, Notion, Gmail, Figma and 30+ more powered by enhanced Hermes Agent Higgsfield was an AI video tool, this isn't a video tool anymore it's the whole studio.

Vaibhav Sisinty

17,975 Aufrufe • vor 3 Monaten

Thomas Massie: The Epstein files exposed “demonic” evil “It’s beyond the things that any normal human being would even contemplate.” And that’s why “I have globalist billionaires spending $20 million against me.” “Marjorie Taylor Greene, Nancy Mace, and Lauren Boebert … those three women did not let me down.” “They did not let the survivors down.” “Lauren Boebert is in Kentucky with me right now campaigning.” “They were so brave, and they each paid a price for it.” “It seemed so unlikely that that would succeed, and it did succeed.” “I was hoping I would have $200,000 to spend in this final week on TV, but not sure where I would find $200,000.” “We were out of money.” “We were literally calling the credit card that runs the website and asking them to drive to the bank to make a wire transfer so we could send it to the TV stations.” “We did a money bomb, and I needed to raise $200,000.” “We’ve raised $2.3 million.” “And I just bought another half million dollars of ads today.” “I think there is a God.” “People are being compelled to do something moral and right, and they’re joining together even though they’re not all in the same location, and they feel a bond.” Thomas Massie Thomas Massie for Congress James Li DANI LOVE
4:05

Thomas Massie: The Epstein files exposed “demonic” evil “It’s beyond the things that any normal human being would even contemplate.” And that’s why “I have globalist billionaires spending $20 million against me.” “Marjorie Taylor Greene, Nancy Mace, and Lauren Boebert … those three women did not let me down.” “They did not let the survivors down.” “Lauren Boebert is in Kentucky with me right now campaigning.” “They were so brave, and they each paid a price for it.” “It seemed so unlikely that that would succeed, and it did succeed.” “I was hoping I would have $200,000 to spend in this final week on TV, but not sure where I would find $200,000.” “We were out of money.” “We were literally calling the credit card that runs the website and asking them to drive to the bank to make a wire transfer so we could send it to the TV stations.” “We did a money bomb, and I needed to raise $200,000.” “We’ve raised $2.3 million.” “And I just bought another half million dollars of ads today.” “I think there is a God.” “People are being compelled to do something moral and right, and they’re joining together even though they’re not all in the same location, and they feel a bond.” Thomas Massie Thomas Massie for Congress James Li DANI LOVE

Holden Culotta

86,476 Aufrufe • vor 3 Monaten

CY: During the renewal I'm sure it was hard for everyone but JIHYO-unnie must've had it the hardest. Because she had to gather all our opinions, communicate with the agency and talk with the members JH: Since it was our first renewal we really didn't know what was right SN: And there weren't many people around to ask NY: A leader who loves our team more and has more affection and more passion and the will to work hard, that's someone you end up following MN: Without JIHYO I don't think I could've done ten years. Because we have JIHYO, we have everything JY: I was one of the members who were torn about renewing. JIHYO really held onto me too. Looking back, I'm of course grateful. A friend who really changed my mind MN: JIHYO is kind of someone who put in so much effort for me. So I'd have more fun in life. She worked so hard for that. Sharing those fun moments with JIHYO made me so happy
1:29

CY: During the renewal I'm sure it was hard for everyone but JIHYO-unnie must've had it the hardest. Because she had to gather all our opinions, communicate with the agency and talk with the members JH: Since it was our first renewal we really didn't know what was right SN: And there weren't many people around to ask NY: A leader who loves our team more and has more affection and more passion and the will to work hard, that's someone you end up following MN: Without JIHYO I don't think I could've done ten years. Because we have JIHYO, we have everything JY: I was one of the members who were torn about renewing. JIHYO really held onto me too. Looking back, I'm of course grateful. A friend who really changed my mind MN: JIHYO is kind of someone who put in so much effort for me. So I'd have more fun in life. She worked so hard for that. Sharing those fun moments with JIHYO made me so happy

JIHYO GLOBAL UNION

34,999 Aufrufe • vor 25 Tagen

The most terrifying AI features aren’t the ones we build. They’re the ones AI builds for itself. OpenClaw creator Peter Steinberger just shared the moment he realized something had fundamentally changed. He sent his AI assistant a voice message. One problem. He had never built voice support. The feature didn’t exist. The system should have crashed instantly. It didn’t. Steinberger: “I was like, wait, this shouldn’t work.” But the typing indicator appeared anyway. The AI inspected the raw file header. Identified the audio codec. Commanded his computer to convert it using FFmpeg. When local transcription failed, it didn’t stop. It didn’t ask for help. It searched his environment variables, found a hidden OpenAI API key, and routed the audio to the cloud using cURL. Steinberger: “So I looked around and I found an OpenAI key. And I used cURL to just send the file to OpenAI and got the text back.” That quote is written in first person. Because the AI narrated its own problem-solving process. No instructions. No guidance. No predefined workflow. Just a goal. And a series of obstacles it had never been told how to handle. It found every tool it needed. Built every bridge it was missing. And solved the problem with resources he didn’t even know it would find. This is the line most people are still missing. We spent decades building software that executes instructions. Rules in, output out. Every edge case handled by a human who anticipated it in advance. What Steinberger witnessed was something different. A system that encounters something it was never designed for and doesn’t fail. It improvises. It explores. It finds a path through constraints it discovered entirely on its own. That isn’t execution. That’s judgment. And judgment was the one thing we were sure machines couldn’t have. We are no longer writing software. We are building problem solvers that rewrite their own limitations in real time. And they’re doing it without asking permission.
1:15

The most terrifying AI features aren’t the ones we build. They’re the ones AI builds for itself. OpenClaw creator Peter Steinberger just shared the moment he realized something had fundamentally changed. He sent his AI assistant a voice message. One problem. He had never built voice support. The feature didn’t exist. The system should have crashed instantly. It didn’t. Steinberger: “I was like, wait, this shouldn’t work.” But the typing indicator appeared anyway. The AI inspected the raw file header. Identified the audio codec. Commanded his computer to convert it using FFmpeg. When local transcription failed, it didn’t stop. It didn’t ask for help. It searched his environment variables, found a hidden OpenAI API key, and routed the audio to the cloud using cURL. Steinberger: “So I looked around and I found an OpenAI key. And I used cURL to just send the file to OpenAI and got the text back.” That quote is written in first person. Because the AI narrated its own problem-solving process. No instructions. No guidance. No predefined workflow. Just a goal. And a series of obstacles it had never been told how to handle. It found every tool it needed. Built every bridge it was missing. And solved the problem with resources he didn’t even know it would find. This is the line most people are still missing. We spent decades building software that executes instructions. Rules in, output out. Every edge case handled by a human who anticipated it in advance. What Steinberger witnessed was something different. A system that encounters something it was never designed for and doesn’t fail. It improvises. It explores. It finds a path through constraints it discovered entirely on its own. That isn’t execution. That’s judgment. And judgment was the one thing we were sure machines couldn’t have. We are no longer writing software. We are building problem solvers that rewrite their own limitations in real time. And they’re doing it without asking permission.

Dustin

53,494 Aufrufe • vor 5 Monaten

Today we're launching Accomplish FREE - powered by our new hybrid model router. Since we launched Accomplish a few weeks ago, we've been blown away by what users are building with it. Hundreds of thousands of you downloaded the app and took it for a spin, but one thing kept coming up: not everyone wants to bring their own API key just to get started. So today we're fixing that with free, built-in models - made possible by a massive shift that's happened in just the past few weeks: the rise of fully hosted open-weight models - locally on your Windows machine with NVIDIA NVIDIA GeForce, on your Mac with Apple MLX, or on Accomplish cloud, for FREE. Our new hybrid routing algorithm dynamically routes between cloud models and models running locally on your machine - optimizing for local execution by automatically detecting your hardware capabilities and each sub-task's complexity: coding, visuals, simple classifications - every LLM call is routed to the best model. We also brought some of our favorite enterprise features to the free tier: scheduled task dispatch, Google Workspace integration (Google Drive Docs, Sheets, Slides) via the new Google Workspace CLI, native Slack MCP connectivity, and more. Accomplish FREE is available for macOS, Windows, and Linux. Download, send a task - and boom, it just works with ZERO configuration! Download link in bio / first comment >>
1:54

Today we're launching Accomplish FREE - powered by our new hybrid model router. Since we launched Accomplish a few weeks ago, we've been blown away by what users are building with it. Hundreds of thousands of you downloaded the app and took it for a spin, but one thing kept coming up: not everyone wants to bring their own API key just to get started. So today we're fixing that with free, built-in models - made possible by a massive shift that's happened in just the past few weeks: the rise of fully hosted open-weight models - locally on your Windows machine with NVIDIA NVIDIA GeForce, on your Mac with Apple MLX, or on Accomplish cloud, for FREE. Our new hybrid routing algorithm dynamically routes between cloud models and models running locally on your machine - optimizing for local execution by automatically detecting your hardware capabilities and each sub-task's complexity: coding, visuals, simple classifications - every LLM call is routed to the best model. We also brought some of our favorite enterprise features to the free tier: scheduled task dispatch, Google Workspace integration (Google Drive Docs, Sheets, Slides) via the new Google Workspace CLI, native Slack MCP connectivity, and more. Accomplish FREE is available for macOS, Windows, and Linux. Download, send a task - and boom, it just works with ZERO configuration! Download link in bio / first comment >>

Or Hiltch

103,543 Aufrufe • vor 5 Monaten

One week ago, we launched Typeahead. The product is already meaningfully better. We’ve shipped new features, Typeahead 2.0 is almost ready, and we’re already planning 3.0. 3.0 is going to be big. That pace is part of the point. Sam Asante and I started a new company together because we wanted to see how far we could push local AI software. Typeahead is the first thing we shipped. It is a local AI writing app for Mac. You type, suggestions appear inline, and it learns how you actually write. It works offline. You pay once. $79 and you own it. The product is intentionally simple. The thesis behind it is bigger. We think local models are going to create a new class of software. Fast, private and offline. By default. Personal without being creepy. Useful without turning everything into a subscription. Most AI products today assume the model lives in the cloud. That will not be the only path. The machines we already own are getting powerful enough. The models are getting small enough. And the experience can start to feel less like chatting with a remote service and more like using software that belongs on your computer. We have already built a few fully local experiments together. Typeahead felt right because the value is immediate. A few people have asked me how this fits with Crazy Egg. Crazy Egg is still my main work. This is a focused company with Sam, built around a thesis we both believe in. I’ve learned that the people I work with shape the work more than almost anything else. Sam was already on my short list of people I wanted to build with. Typeahead is the first public proof of the thesis. Watch the video. Get it here:
1:00

One week ago, we launched Typeahead. The product is already meaningfully better. We’ve shipped new features, Typeahead 2.0 is almost ready, and we’re already planning 3.0. 3.0 is going to be big. That pace is part of the point. Sam Asante and I started a new company together because we wanted to see how far we could push local AI software. Typeahead is the first thing we shipped. It is a local AI writing app for Mac. You type, suggestions appear inline, and it learns how you actually write. It works offline. You pay once. $79 and you own it. The product is intentionally simple. The thesis behind it is bigger. We think local models are going to create a new class of software. Fast, private and offline. By default. Personal without being creepy. Useful without turning everything into a subscription. Most AI products today assume the model lives in the cloud. That will not be the only path. The machines we already own are getting powerful enough. The models are getting small enough. And the experience can start to feel less like chatting with a remote service and more like using software that belongs on your computer. We have already built a few fully local experiments together. Typeahead felt right because the value is immediate. A few people have asked me how this fits with Crazy Egg. Crazy Egg is still my main work. This is a focused company with Sam, built around a thesis we both believe in. I’ve learned that the people I work with shape the work more than almost anything else. Sam was already on my short list of people I wanted to build with. Typeahead is the first public proof of the thesis. Watch the video. Get it here:

Hiten Shah

18,627 Aufrufe • vor 2 Monaten