Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Z.ai GLM 5.2 is now live on Eigent from day 0! threw a real long-horizon task: research 30 companies across 6 sectors of the AI infrastructure stack, structure it into JSON, then build an interactive HTML report. same prompt, 5.1 vs 5.2. where 5.2 pulls ahead: → plans deeper... show more

Eigent AI

3,141 subscribers

22,881 views • 1 month ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

🎉 Day-0 support for in vLLM, available today in v0.23.0! Congrats to Z.ai on GLM-5.2, a flagship model built for long-horizon coding agents. ✨ 1M-token context, built to hold project-scale engineering work in a single run ✨ Tuned for long-horizon coding: large-scale implementation, automated research, and performance optimization ✨ One task can carry a full dev workflow, from requirements to a deployable product across platforms ✨ Client-side and mobile engineering, including an on-device debugging loop Try it out running it on vLLM today: 🔗

🎉 Day-0 support for in vLLM, available today in v0.23.0! Congrats to Z.ai on GLM-5.2, a flagship model built for long-horizon coding agents. ✨ 1M-token context, built to hold project-scale engineering work in a single run ✨ Tuned for long-horizon coding: large-scale implementation, automated research, and performance optimization ✨ One task can carry a full dev workflow, from requirements to a deployable product across platforms ✨ Client-side and mobile engineering, including an on-device debugging loop Try it out running it on vLLM today: 🔗

vLLM

36,019 views • 1 month ago

Introducing GLM 5.2 for autoresearch GLM 5.2 is the first open weights model we've tried on our autoresearch pipeline that's proven capable for real research tasks. With Fable 5's restrictions on research, having an open weights alternative is a huge win for open source Watch it carry out fully async vs colocated sync RL training on Harbor code contests across two 8xH100 nodes on top of SkyRL. Resolves setup issues, tracks runs to completion, and produces a full comparison of throughput and reward stability

Introducing GLM 5.2 for autoresearch GLM 5.2 is the first open weights model we've tried on our autoresearch pipeline that's proven capable for real research tasks. With Fable 5's restrictions on research, having an open weights alternative is a huge win for open source Watch it carry out fully async vs colocated sync RL training on Harbor code contests across two 8xH100 nodes on top of SkyRL. Resolves setup issues, tracks runs to completion, and produces a full comparison of throughput and reward stability

alphaXiv

270,089 views • 1 month ago

Last, but not least, don't sleep on this one: Le Chat now has Work mode (Preview) — a powerful agent for complex long-horizon tasks like research, analysis, and actions across your connected tools. Connectors are on by default so the agent pulls context from docs, email, and calendars as it works, and sessions persist across many turns until the task is complete.

Last, but not least, don't sleep on this one: Le Chat now has Work mode (Preview) — a powerful agent for complex long-horizon tasks like research, analysis, and actions across your connected tools. Connectors are on by default so the agent pulls context from docs, email, and calendars as it works, and sessions persist across many turns until the task is complete.

Mistral Vibe

32,521 views • 2 months ago

ClickUp to add artifacts with Brain2 👀 > It will be able to create slides, prototypes, websites, or dashboards. > Brain pulls from workspace context, so the output is built on real project data > Artifacts render inline in the channel and stay fully interactive. When Brain is asked to build a presentation, it will now return a finished, professionally done, navigable deck right in the thread, ready to share or drop into a task.

ClickUp to add artifacts with Brain2 👀 > It will be able to create slides, prototypes, websites, or dashboards. > Brain pulls from workspace context, so the output is built on real project data > Artifacts render inline in the channel and stay fully interactive. When Brain is asked to build a presentation, it will now return a finished, professionally done, navigable deck right in the thread, ready to share or drop into a task.

🚨 AI News | TestingCatalog

12,749 views • 1 month ago

CHINA JUST DROPPED AN AI CODING MODEL WITH A 1M CONTEXT WINDOW. And I connected it to Claude Code to see what it could actually do. Meet GLM-X Preview On paper, a few things immediately stood out: → 1M context window → Agentic coding capabilities → Works inside Claude Code → Designed for large-scale coding and reasoning workflows But specs don't matter much if the model can't deliver in practice. So I gave it a real-world task. THE TEST One prompt: > Build a modern AI lead generation dashboard using React and Tailwind CSS. Requirements: → Dark mode → Analytics dashboard → Lead table → Email outreach section → Responsive design → Production-ready component structure Instead of generating a few snippets, it planned the architecture, generated the dashboard components, created the Tailwind configuration, and walked through the implementation requirements. What impressed me most wasn't the code itself. It was how well it maintained context throughout the workflow. That's where a 1M context window starts becoming useful. Less time re-explaining requirements. Less context loss. More room for complex projects. The AI coding race is getting very interesting. And it's no longer just GPT, Claude, and Gemini competing for attention. Results from my test below 👇

CHINA JUST DROPPED AN AI CODING MODEL WITH A 1M CONTEXT WINDOW. And I connected it to Claude Code to see what it could actually do. Meet GLM-X Preview On paper, a few things immediately stood out: → 1M context window → Agentic coding capabilities → Works inside Claude Code → Designed for large-scale coding and reasoning workflows But specs don't matter much if the model can't deliver in practice. So I gave it a real-world task. THE TEST One prompt: > Build a modern AI lead generation dashboard using React and Tailwind CSS. Requirements: → Dark mode → Analytics dashboard → Lead table → Email outreach section → Responsive design → Production-ready component structure Instead of generating a few snippets, it planned the architecture, generated the dashboard components, created the Tailwind configuration, and walked through the implementation requirements. What impressed me most wasn't the code itself. It was how well it maintained context throughout the workflow. That's where a 1M context window starts becoming useful. Less time re-explaining requirements. Less context loss. More room for complex projects. The AI coding race is getting very interesting. And it's no longer just GPT, Claude, and Gemini competing for attention. Results from my test below 👇

Md Riyazuddin

31,199 views • 1 month ago

My favorite way of interacting with Claude Code is to have it generate static HTML files as outputs (reports, explorations, code structure, mockups etc.) I wanted to iterate on the file by commenting in browser and having Claude update the output live. So, I built this Claude Skill👇 How it works: - Install Claude Code skill (ask it to clone repo) - Build an HTML page for anything (e.g. research coding agents and generate HTML report) - Ask it to make the page interactive That's it. CC will launch a localhost server and allow you to then leave comments on the page itself and once it updates, will give you a tour of changes. It's like Google Docs kind of comments/iteration but for HTML pages.

My favorite way of interacting with Claude Code is to have it generate static HTML files as outputs (reports, explorations, code structure, mockups etc.) I wanted to iterate on the file by commenting in browser and having Claude update the output live. So, I built this Claude Skill👇 How it works: - Install Claude Code skill (ask it to clone repo) - Build an HTML page for anything (e.g. research coding agents and generate HTML report) - Ask it to make the page interactive That's it. CC will launch a localhost server and allow you to then leave comments on the page itself and once it updates, will give you a tour of changes. It's like Google Docs kind of comments/iteration but for HTML pages.

Paras Chopra

215,134 views • 2 months ago

GLM 5.2 just killed Claude Fable 5. Watch 6:36 first if you only have a minute. That’s where it stops being a tech demo and starts being a game. One small sentence. Two prompts. The AI built Minecraft from scratch. Not a clone. Not a demo. A working game: - inventory + crafting table - ore mining: coal, iron, gold - underground caves - mobs: zombies, sheep, chickens, cows, pigs - day/night cycle - fall damage - locked 60 FPS The numbers are insane: Notch built the original Minecraft solo over months. Microsoft bought it for $2.5B in 2014. GLM 5.2 shipped a working copy in the time it took the creator to grab a coffee. The science is wild too: The model iteratively builds the systems itself. Inventory first. Then crafting. Then mining. Then mobs. No extra instructions in between. The grift opportunity is even wilder: Indie studios charge $50k+ for a survival game prototype. Unity freelancers sit at $80/hr. Now one kid + one prompt + one evening = a shippable MVP. Full timestamps: 0:25 - Minecraft in ONE prompt 6:36 - Minecraft in TWO prompts (caves, mobs, crafting) 9:40 - the verdict: GLM 5.2 or Claude Fable 5? Claude Fable 5 still holds up. But GLM added caves and hostile mobs nobody asked for. Save this before your knowledge cutoff stops mattering.

GLM 5.2 just killed Claude Fable 5. Watch 6:36 first if you only have a minute. That’s where it stops being a tech demo and starts being a game. One small sentence. Two prompts. The AI built Minecraft from scratch. Not a clone. Not a demo. A working game: - inventory + crafting table - ore mining: coal, iron, gold - underground caves - mobs: zombies, sheep, chickens, cows, pigs - day/night cycle - fall damage - locked 60 FPS The numbers are insane: Notch built the original Minecraft solo over months. Microsoft bought it for $2.5B in 2014. GLM 5.2 shipped a working copy in the time it took the creator to grab a coffee. The science is wild too: The model iteratively builds the systems itself. Inventory first. Then crafting. Then mining. Then mobs. No extra instructions in between. The grift opportunity is even wilder: Indie studios charge $50k+ for a survival game prototype. Unity freelancers sit at $80/hr. Now one kid + one prompt + one evening = a shippable MVP. Full timestamps: 0:25 - Minecraft in ONE prompt 6:36 - Minecraft in TWO prompts (caves, mobs, crafting) 9:40 - the verdict: GLM 5.2 or Claude Fable 5? Claude Fable 5 still holds up. But GLM added caves and hostile mobs nobody asked for. Save this before your knowledge cutoff stops mattering.

AdiiX

144,802 views • 1 month ago

A useful trick for making AI photos look 100% real: (it's not always the model — it can be the color grading) Out of the box, Nano Banana Pro can have a gray, flat look. Good composition, but these scream AI. Here's the system that fixes it: → Grab a reference photo from Pinterest with the exact aesthetic you want → Feed it to ChatGPT 5.2 with a prompt that extracts a detailed color grading JSON → Paste that JSON into image generator (Calico AI) → Generate your product photo. (the colors are now based on the reality you specify, not AI defaults) → Save that character as your reference for facial consistency across future shots From here you can build a full UGC model library. No creators. No shoots. Comment "IMAGE" if you want me to send you every prompt in this system (must be following so I can dm you!).

A useful trick for making AI photos look 100% real: (it's not always the model — it can be the color grading) Out of the box, Nano Banana Pro can have a gray, flat look. Good composition, but these scream AI. Here's the system that fixes it: → Grab a reference photo from Pinterest with the exact aesthetic you want → Feed it to ChatGPT 5.2 with a prompt that extracts a detailed color grading JSON → Paste that JSON into image generator (Calico AI) → Generate your product photo. (the colors are now based on the reality you specify, not AI defaults) → Save that character as your reference for facial consistency across future shots From here you can build a full UGC model library. No creators. No shoots. Comment "IMAGE" if you want me to send you every prompt in this system (must be following so I can dm you!).

David Roberts

20,998 views • 5 months ago

FABLE 5 JUST REBUILT FORTNITE FROM 1 PROMPT IN 20 MINUTES. EPIC NEEDED HUNDREDS OF ENGINEERS AND 6 YEARS. The test was simple: Fable 5 vs GLM 5.2, one prompt each, a 100-player battle royale running in the browser with no engine and no team. GLM went first and checked all 8 milestones. The game loaded with a battle bus, a generated map, Tilted Towers, even health and shield bars ripped straight from 2018. Then it fell apart. 2 FPS on landing, S walking forward and W walking backward, a gun that fires upward and a camera that refuses to look up. First fight ended with the enemy standing above physically impossible to aim at. Then Fable 5 took the same prompt on max effort. Different game entirely. Real character models instead of beans, hit reactions lighting up on contact, a shadow tracking every player, movement that just works out of the box. One follow-up prompt “add more Fortnite elements” and it shipped gliders, chests, shield potions, medkits and a sniper without breaking a thing. Final circle at 3:28 AM. Storm closing, 0 bullets left, box to box with medkit spam and a last-second swap to the SMG. Victory Royale in a game an AI wrote from a single sentence. GLM checked more boxes. Fable built something you could actually play and no benchmark on earth measures that gap. Epic needed 6 years. Fable 5 needed 1 prompt.

FABLE 5 JUST REBUILT FORTNITE FROM 1 PROMPT IN 20 MINUTES. EPIC NEEDED HUNDREDS OF ENGINEERS AND 6 YEARS. The test was simple: Fable 5 vs GLM 5.2, one prompt each, a 100-player battle royale running in the browser with no engine and no team. GLM went first and checked all 8 milestones. The game loaded with a battle bus, a generated map, Tilted Towers, even health and shield bars ripped straight from 2018. Then it fell apart. 2 FPS on landing, S walking forward and W walking backward, a gun that fires upward and a camera that refuses to look up. First fight ended with the enemy standing above physically impossible to aim at. Then Fable 5 took the same prompt on max effort. Different game entirely. Real character models instead of beans, hit reactions lighting up on contact, a shadow tracking every player, movement that just works out of the box. One follow-up prompt “add more Fortnite elements” and it shipped gliders, chests, shield potions, medkits and a sniper without breaking a thing. Final circle at 3:28 AM. Storm closing, 0 bullets left, box to box with medkit spam and a last-second swap to the SMG. Victory Royale in a game an AI wrote from a single sentence. GLM checked more boxes. Fable built something you could actually play and no benchmark on earth measures that gap. Epic needed 6 years. Fable 5 needed 1 prompt.

West Lord

80,912 views • 24 days ago

The next internet will not be browsed. It will be operated by agents. OptimAI is building the infrastructure behind that shift. • A research task begins with Search pulling live context from the public web and social web • That context moves into Claw, where the agent can execute directly on your device • Domain knowledge becomes a Persona Agent • Core Node v2 keeps the system running at the edge • And x402 will make access and payment feel native to the flow That is the real shift: - from asking AI questions - to deploying intelligence that can work, learn, and compound. A trader can monitor signals. A founder can prepare reports overnight. A builder can publish a specialized agent once, then let others reuse it. This is what the agent-native internet looks like when it is built from the ground up. Start with OptimAI: • Persona Agent: • Claw / Core Node v2: • Search:

The next internet will not be browsed. It will be operated by agents. OptimAI is building the infrastructure behind that shift. • A research task begins with Search pulling live context from the public web and social web • That context moves into Claw, where the agent can execute directly on your device • Domain knowledge becomes a Persona Agent • Core Node v2 keeps the system running at the edge • And x402 will make access and payment feel native to the flow That is the real shift: - from asking AI questions - to deploying intelligence that can work, learn, and compound. A trader can monitor signals. A founder can prepare reports overnight. A builder can publish a specialized agent once, then let others reuse it. This is what the agent-native internet looks like when it is built from the ground up. Start with OptimAI: • Persona Agent: • Claw / Core Node v2: • Search:

OptimAI Network

18,488 views • 2 months ago

🚨 ALIBABA JUST OPEN-SOURCED THE MOST POWERFUL MODEL IN THE WORLD - Qwen3.5 plus And it changes the AI race forever. This is not another “bigger model” release. This is a complete architectural reset. 397B parameters → only 17B active at inference, Qwen3.5 plus delivers performance on par with GPT-5.2 and Gemini-3-Pro. A new Hybrid Sparse MoE + Linear Attention architecture + Multi-Token Prediction = near-instant long-context responses and massive speed gains. Built as a true native multimodal model, it doesn’t just chat it builds. With a single prompt: “Use the React framework to create a visually impressive Mapbox demo featuring locations in Beijing and Shanghai” it generates a live interactive 3D map UI, structured components, real layouts, and production-ready frontend logic. This is real agentic, multimodal coding not a static code block. MMLU-Pro: 87.8 GPQA: 88.4 IFBench: 76.5 ⚡ up to 8× faster inference And it’s fully open-sourced under Apache-2.0. No locked APIs. No restricted tiers. 201 languages supported bringing frontier AI to developers, startups, and researchers worldwide. The race is no longer about the biggest model. It’s about the most usable intelligence. Open source just entered the top tier.

🚨 ALIBABA JUST OPEN-SOURCED THE MOST POWERFUL MODEL IN THE WORLD - Qwen3.5 plus And it changes the AI race forever. This is not another “bigger model” release. This is a complete architectural reset. 397B parameters → only 17B active at inference, Qwen3.5 plus delivers performance on par with GPT-5.2 and Gemini-3-Pro. A new Hybrid Sparse MoE + Linear Attention architecture + Multi-Token Prediction = near-instant long-context responses and massive speed gains. Built as a true native multimodal model, it doesn’t just chat it builds. With a single prompt: “Use the React framework to create a visually impressive Mapbox demo featuring locations in Beijing and Shanghai” it generates a live interactive 3D map UI, structured components, real layouts, and production-ready frontend logic. This is real agentic, multimodal coding not a static code block. MMLU-Pro: 87.8 GPQA: 88.4 IFBench: 76.5 ⚡ up to 8× faster inference And it’s fully open-sourced under Apache-2.0. No locked APIs. No restricted tiers. 201 languages supported bringing frontier AI to developers, startups, and researchers worldwide. The race is no longer about the biggest model. It’s about the most usable intelligence. Open source just entered the top tier.

RAVI KUMAR SAHU

380,123 views • 5 months ago

This is the best AI tool I have seen so far this year, and everyone can use it. Normally, when you research a topic using tools like Perplexity, Gemini, or ChatGPT, they just give you a wall of text. Try Superagent, a newly launched product by Airtable. It literally builds you an interactive Super Report with high-quality data from a single prompt, ready to present as-is. You can click into research sections, scroll through dynamic graphs, and see visualizations that make complex topics easy to understand. 👉 Use code KUNAL2FREE and get free 2 month access: It’s not just a chatbot. It spins up a team of multiple specialized AI agents that build a research plan, divide the tasks, and execute them simultaneously. You can build presentations, university reports, websites, dashboards, you name it! Shoutout to them for sponsoring this post.

This is the best AI tool I have seen so far this year, and everyone can use it. Normally, when you research a topic using tools like Perplexity, Gemini, or ChatGPT, they just give you a wall of text. Try Superagent, a newly launched product by Airtable. It literally builds you an interactive Super Report with high-quality data from a single prompt, ready to present as-is. You can click into research sections, scroll through dynamic graphs, and see visualizations that make complex topics easy to understand. 👉 Use code KUNAL2FREE and get free 2 month access: It’s not just a chatbot. It spins up a team of multiple specialized AI agents that build a research plan, divide the tasks, and execute them simultaneously. You can build presentations, university reports, websites, dashboards, you name it! Shoutout to them for sponsoring this post.

Kunal Kushwaha

15,150 views • 5 months ago

The gap between a PM getting AI slop from Claude Code and one getting 10x output is about one hour of file structure. Three folders. > A knowledge folder with static context: who you work with, what each stakeholder cares about, reference material that rarely changes. > A projects folder where every task accumulates research, drafts, and artifacts that load instantly into your next session. > And a people folder that auto-updates from meeting transcripts through Granola's MCP. The people folder is the part that compounds. Build a skill that pulls what each person said in your last meeting, what they pushed back on, what they committed to. Now when you draft a message to your VP of Engineering, Claude Code already knows their communication preferences from 30 real conversations. That's context no prompt can replicate. Carl walked through this system on the episode and the compounding math stuck with me. Day 1, Claude Code knows nothing about your work. Day 30, it knows your stakeholders, your project history, your patterns. Day 90, it's surfacing connections across your work you haven't consciously noticed. Then layer on skills. A standup command that pulls from GitHub, Linear, your calendar, and your task folder in one shot. Website traffic compared against your LinkedIn posts this week. Analyses that would be impossible clicking between individual UIs, running before your first meeting. One hour of setup. Compounding returns every day after. The PMs typing prompts into a blank terminal and the PMs who built the operating system around it are already producing completely different categories of work. Build the operating system.

The gap between a PM getting AI slop from Claude Code and one getting 10x output is about one hour of file structure. Three folders. > A knowledge folder with static context: who you work with, what each stakeholder cares about, reference material that rarely changes. > A projects folder where every task accumulates research, drafts, and artifacts that load instantly into your next session. > And a people folder that auto-updates from meeting transcripts through Granola's MCP. The people folder is the part that compounds. Build a skill that pulls what each person said in your last meeting, what they pushed back on, what they committed to. Now when you draft a message to your VP of Engineering, Claude Code already knows their communication preferences from 30 real conversations. That's context no prompt can replicate. Carl walked through this system on the episode and the compounding math stuck with me. Day 1, Claude Code knows nothing about your work. Day 30, it knows your stakeholders, your project history, your patterns. Day 90, it's surfacing connections across your work you haven't consciously noticed. Then layer on skills. A standup command that pulls from GitHub, Linear, your calendar, and your task folder in one shot. Website traffic compared against your LinkedIn posts this week. Analyses that would be impossible clicking between individual UIs, running before your first meeting. One hour of setup. Compounding returns every day after. The PMs typing prompts into a blank terminal and the PMs who built the operating system around it are already producing completely different categories of work. Build the operating system.

Aakash Gupta

82,865 views • 3 months ago

JUST IN: Perplexity launched "Perplexity Computer" — and it might be the most complete AI agent system available right now. Not a chatbot upgrade. Not a research tool with a new name. A system that plans entire projects, delegates to specialist AI models, and runs autonomously for hours, days, or months (their words). Here's what makes the architecture genuinely different: → Opus 4.6 handles core reasoning and orchestration → Gemini handles deep research (spawning its own sub-agents) → Grok handles lightweight speed tasks → Veo 3.1 handles video generation → Nano Banana handles image creation → ChatGPT 5.2 handles long-context recall and wide search → You can override model choices per subtask 19 models total. Each task runs in an isolated environment with a real filesystem, real browser, and real tool integrations. You describe an outcome. It breaks it into tasks and subtasks, creates sub-agents for each, and coordinates them automatically. When a sub-agent hits a problem, it spawns more sub-agents to solve it. And it connects to your existing stack — GitHub, Google Drive, Gmail, Slack, Jira, Linear, Notion, Confluence, Ahrefs, Airtable, and more. Critically, it doesn't just run once. It can run on a schedule. Reading your docs, checking your project boards, pulling from your CRM, and acting on what it finds. Market monitoring. Competitor tracking. Weekly reports with charts. Content pipelines. CRON jobs that actually execute. Not "AI that helps you once." AI that runs in the background for days or months. Think of it as managed OpenClaw — similar autonomous capability (scheduled tasks, multi-step workflows, tool integrations) but fully managed. No Mac Mini. No security config. No infrastructure to maintain. I tested it with a complex prompt — a full stock trading simulator with what-if scenarios, correlation heatmaps, sentiment analysis, and a Bloomberg Terminal aesthetic. Two prompts later: deployed to Netlify via GitHub, with working CRON jobs updating live data. I've started using it to analyze my portfolio. But coding is just one lane. This thing researches, writes reports, generates datasets, creates videos, processes documents, and connects to your existing tools — all in one coordinated workflow. The real shift: you don't choose a model anymore. You describe what you need. The system routes each piece of work to whichever model does it best — and spawns new agents when it hits a wall. 19 models, dynamic sub-agents, scheduled tasks, and your entire tool stack connected. Thoughts?

JUST IN: Perplexity launched "Perplexity Computer" — and it might be the most complete AI agent system available right now. Not a chatbot upgrade. Not a research tool with a new name. A system that plans entire projects, delegates to specialist AI models, and runs autonomously for hours, days, or months (their words). Here's what makes the architecture genuinely different: → Opus 4.6 handles core reasoning and orchestration → Gemini handles deep research (spawning its own sub-agents) → Grok handles lightweight speed tasks → Veo 3.1 handles video generation → Nano Banana handles image creation → ChatGPT 5.2 handles long-context recall and wide search → You can override model choices per subtask 19 models total. Each task runs in an isolated environment with a real filesystem, real browser, and real tool integrations. You describe an outcome. It breaks it into tasks and subtasks, creates sub-agents for each, and coordinates them automatically. When a sub-agent hits a problem, it spawns more sub-agents to solve it. And it connects to your existing stack — GitHub, Google Drive, Gmail, Slack, Jira, Linear, Notion, Confluence, Ahrefs, Airtable, and more. Critically, it doesn't just run once. It can run on a schedule. Reading your docs, checking your project boards, pulling from your CRM, and acting on what it finds. Market monitoring. Competitor tracking. Weekly reports with charts. Content pipelines. CRON jobs that actually execute. Not "AI that helps you once." AI that runs in the background for days or months. Think of it as managed OpenClaw — similar autonomous capability (scheduled tasks, multi-step workflows, tool integrations) but fully managed. No Mac Mini. No security config. No infrastructure to maintain. I tested it with a complex prompt — a full stock trading simulator with what-if scenarios, correlation heatmaps, sentiment analysis, and a Bloomberg Terminal aesthetic. Two prompts later: deployed to Netlify via GitHub, with working CRON jobs updating live data. I've started using it to analyze my portfolio. But coding is just one lane. This thing researches, writes reports, generates datasets, creates videos, processes documents, and connects to your existing tools — all in one coordinated workflow. The real shift: you don't choose a model anymore. You describe what you need. The system routes each piece of work to whichever model does it best — and spawns new agents when it hits a wall. 19 models, dynamic sub-agents, scheduled tasks, and your entire tool stack connected. Thoughts?

Paweł Huryn

219,498 views • 5 months ago

We spent months building this so you don't have to figure it out alone. A free 7-day course that takes you from zero to building real things with AI, no coding background, no expensive tools, no fluff, just results. From 0 -> to Claude code expert, completely free: > In 7 days, you’ll learn vibe coding, set up Claude Code, build your first AI app, create a prompt-built website, automate a task with n8n, and deploy it live to a real URL. No theory, no filler, just a real project you can show people by the end of the week. For those who want to go further, we spent even longer building another one, designed for people who are genuinely interested in AI deep learning and launching products. From Expert to Your First $10k Product {You can find it on the link above as well} The complete masterclass, full-stack AI apps, Supabase, n8n automations, AI agents, Telegram bots, SaaS products built from scratch, Stripe, subscriptions, client work, freelancing, pricing and scaling. This is the course that turns the skill into actual income. Me and Noisy put everything we know into both of these, you can start free, build something real, then decide how far you want to take it.

We spent months building this so you don't have to figure it out alone. A free 7-day course that takes you from zero to building real things with AI, no coding background, no expensive tools, no fluff, just results. From 0 -> to Claude code expert, completely free: > In 7 days, you’ll learn vibe coding, set up Claude Code, build your first AI app, create a prompt-built website, automate a task with n8n, and deploy it live to a real URL. No theory, no filler, just a real project you can show people by the end of the week. For those who want to go further, we spent even longer building another one, designed for people who are genuinely interested in AI deep learning and launching products. From Expert to Your First $10k Product {You can find it on the link above as well} The complete masterclass, full-stack AI apps, Supabase, n8n automations, AI agents, Telegram bots, SaaS products built from scratch, Stripe, subscriptions, client work, freelancing, pricing and scaling. This is the course that turns the skill into actual income. Me and Noisy put everything we know into both of these, you can start free, build something real, then decide how far you want to take it.

Defileo🔮

695,073 views • 3 months ago

We’re entering the 10x speed of research publication workflow with AI. SciSpace (SciSpace), the first AI Agent built exclusively for the scientific community, is releasing so many inredibly useful features. 🎯 This is the AI Agent that can use 150+ tools, 59 databases, and 280M+ papers A few weeks back they launched BioMed Agent - It can design entire molecular biology workflows and even create publication-ready illustrations in a single prompt. This is its new domain-specialized AI co-scientist that sits on top of the existing SciSpace Agent and automates full biomedical workflows, from raw data and papers to analysis, decisions, and the final production-grade illustrations. You just need to give it 1 prompt. And today the added the following - Library Search, so it can search and analyze the PDFs already sitting in My Library, letting people ask questions across their own paper pile while keeping it private. - Now connects directly to Zotero, so the Agent can pull and work with the papers you already saved there without manual uploads. - For bigger prompts, it auto-triggers a Report Writing Sub-Agent that turns the chat into a structured research-style report, which is way cleaner for literature reviews and long summaries. - And when you get something worth keeping, Save to Notebook lets you store the output as .md notes with citations in My notebooks, so the work becomes reusable research notes instead of disappearing into chat. Behind the scenes, it indexes the PDF text, pulls a few relevant chunks for the question, then writes an answer grounded on those chunks.

We’re entering the 10x speed of research publication workflow with AI. SciSpace (SciSpace), the first AI Agent built exclusively for the scientific community, is releasing so many inredibly useful features. 🎯 This is the AI Agent that can use 150+ tools, 59 databases, and 280M+ papers A few weeks back they launched BioMed Agent - It can design entire molecular biology workflows and even create publication-ready illustrations in a single prompt. This is its new domain-specialized AI co-scientist that sits on top of the existing SciSpace Agent and automates full biomedical workflows, from raw data and papers to analysis, decisions, and the final production-grade illustrations. You just need to give it 1 prompt. And today the added the following - Library Search, so it can search and analyze the PDFs already sitting in My Library, letting people ask questions across their own paper pile while keeping it private. - Now connects directly to Zotero, so the Agent can pull and work with the papers you already saved there without manual uploads. - For bigger prompts, it auto-triggers a Report Writing Sub-Agent that turns the chat into a structured research-style report, which is way cleaner for literature reviews and long summaries. - And when you get something worth keeping, Save to Notebook lets you store the output as .md notes with citations in My notebooks, so the work becomes reusable research notes instead of disappearing into chat. Behind the scenes, it indexes the PDF text, pulls a few relevant chunks for the question, then writes an answer grounded on those chunks.

Rohan Paul

11,574 views • 5 months ago

THIS GUY SPENT 5 MINUTES SETTING UP A $20 CLAUDE WORKSPACE AND TURNED 30 MINUTES OF DAILY PROMPT CHAOS INTO A SYSTEM Most people open Claude, type 1 messy prompt, rewrite it 10 times, get the same generic answer and call the model “bad.” He opens Claude Cowork, adds the project rules, past context, working files, examples, decisions and a clean place for the model to remember what it is doing. Same Claude. Same $20 tool. Completely different output. The funny part is there is no magic prompt here. No secret template. No “10x Claude” trick. Just the boring layer Karpathy keeps pointing at: context, memory and structure before output. A setup like this can save 30 minutes a day, which is 15 hours a month. If you use Claude for client work at $50 to $100/hour, that is $750 to $1,500/month in time you stop burning on repeated prompts. The model is real. The output is real. The edge is in not making Claude start from zero every single time.

THIS GUY SPENT 5 MINUTES SETTING UP A $20 CLAUDE WORKSPACE AND TURNED 30 MINUTES OF DAILY PROMPT CHAOS INTO A SYSTEM Most people open Claude, type 1 messy prompt, rewrite it 10 times, get the same generic answer and call the model “bad.” He opens Claude Cowork, adds the project rules, past context, working files, examples, decisions and a clean place for the model to remember what it is doing. Same Claude. Same $20 tool. Completely different output. The funny part is there is no magic prompt here. No secret template. No “10x Claude” trick. Just the boring layer Karpathy keeps pointing at: context, memory and structure before output. A setup like this can save 30 minutes a day, which is 15 hours a month. If you use Claude for client work at $50 to $100/hour, that is $750 to $1,500/month in time you stop burning on repeated prompts. The model is real. The output is real. The edge is in not making Claude start from zero every single time.

Gipp 🦅

14,871 views • 1 month ago

🦾 From seeing to doing. We're closing the loop between video prediction and real-world action. On the final day of Robbyant Open Source Week, we bring you LingBot-VA—the world's first causal video-action world model for generalist robot control. 🔥 Key Highlights: 🤖 Predicts & Acts: A single model generates both future video and the actions to make it real. 🧠 Remembers the Past: True long-term memory for complex, sequential tasks. ⚡ Learns in a Snap: Masters new skills with just 30-50 real-world demos. The result? 📈 SOTA on RoboTwin (92.9%) and LIBERO (98.5%), +20% over π0.5 on challenging real-world long-horizon & high-precision tasks. More below 👇 #AI #Robotics #EmbodiedAI #WorldModel #OpenSource

🦾 From seeing to doing. We're closing the loop between video prediction and real-world action. On the final day of Robbyant Open Source Week, we bring you LingBot-VA—the world's first causal video-action world model for generalist robot control. 🔥 Key Highlights: 🤖 Predicts & Acts: A single model generates both future video and the actions to make it real. 🧠 Remembers the Past: True long-term memory for complex, sequential tasks. ⚡ Learns in a Snap: Masters new skills with just 30-50 real-world demos. The result? 📈 SOTA on RoboTwin (92.9%) and LIBERO (98.5%), +20% over π0.5 on challenging real-world long-horizon & high-precision tasks. More below 👇 #AI #Robotics #EmbodiedAI #WorldModel #OpenSource

Robbyant

704,157 views • 5 months ago

i watched gemma 4 12b build something genuinely impressive today, and then loop itself to death right in front of me. the full run is in the video, sped up but completely uncut, watch it to the end and you will catch the exact moment it stops building and starts looping right in the middle of the work. the task was clean, build a single file gravity simulator, n-body physics, orbits, collisions, running locally on one 3090 through an agent. and for ten minutes it was a joy to watch. it reached for a symplectic integrator on its own, the correct one, the kind that keeps orbits stable instead of spiralling out. real gravity with softening, proper orbital velocities, momentum conserved on collision. the physics was right. the thing actually worked. then on the very last step, writing a few tests to prove its own code, it fell into a loop. not a crash, a loop. it started repeating itself and would not stop. ten more minutes, thirty four thousand tokens into a single answer, the same fragments over and over, until i killed it myself. so it's not that gemma can't code. it did the hard part beautifully. it cannot finish. it cannot hold a long task together without unravelling, and finishing is the entire job in agentic work. here's the part that stings. i run this exact task, same harness, same card, on the chinese open models, qwen especially, and i never see this. they build it, they test it, they stop. every single time. google has the raw capability, you can see it sitting right there in the code, and then the model loops itself to death on a task a 27b from alibaba finishes clean. open weights, apache 2.0, so much to love on paper. i just need it to know when to stop talking.

i watched gemma 4 12b build something genuinely impressive today, and then loop itself to death right in front of me. the full run is in the video, sped up but completely uncut, watch it to the end and you will catch the exact moment it stops building and starts looping right in the middle of the work. the task was clean, build a single file gravity simulator, n-body physics, orbits, collisions, running locally on one 3090 through an agent. and for ten minutes it was a joy to watch. it reached for a symplectic integrator on its own, the correct one, the kind that keeps orbits stable instead of spiralling out. real gravity with softening, proper orbital velocities, momentum conserved on collision. the physics was right. the thing actually worked. then on the very last step, writing a few tests to prove its own code, it fell into a loop. not a crash, a loop. it started repeating itself and would not stop. ten more minutes, thirty four thousand tokens into a single answer, the same fragments over and over, until i killed it myself. so it's not that gemma can't code. it did the hard part beautifully. it cannot finish. it cannot hold a long task together without unravelling, and finishing is the entire job in agentic work. here's the part that stings. i run this exact task, same harness, same card, on the chinese open models, qwen especially, and i never see this. they build it, they test it, they stop. every single time. google has the raw capability, you can see it sitting right there in the code, and then the model loops itself to death on a task a 27b from alibaba finishes clean. open weights, apache 2.0, so much to love on paper. i just need it to know when to stop talking.

Sudo su

39,574 views • 1 month ago

Tencent just dropped Hy3, and it's worth a look if you're building AI agents. I spent some time putting it through its paces today. A quick rundown of what makes this release notable: → 295B total parameters (Mixture-of-Experts), but only 21B active at inference — a real efficiency play → 256K context window for handling large codebases or long documents → Purpose-built improvements for coding and multi-step agent tasks → Fully open under Apache 2.0 — no restrictive commercial terms → A free two-week API window currently live on OpenRouter On the practical side: prompts involving layered instructions and coding tasks came back fast and coherent. Tencent says this release builds directly on feedback from 50+ internal product teams following an earlier preview, with reported drops in hallucination rate (12.5% → 5.4%) and commonsense errors (25.4% → 12.7%). Those are Tencent's own numbers, so treat them as a starting point rather than gospel until third parties weigh in. For context: Tencent's own comparisons put Hy3 behind GLM-5.2 specifically on coding benchmarks — GLM is a much bigger model (~744B total), so the trade-off makes sense. Hy3's pitch isn't "biggest," it's "efficient enough to actually deploy." Bottom line — if you're evaluating open-weight options for agent workloads, this is a solid one to add to the testing queue while the free window is open. Try it here: Tencent Hy #Hy3 #Hunyuan #TencentAI #AICoding

Tencent just dropped Hy3, and it's worth a look if you're building AI agents. I spent some time putting it through its paces today. A quick rundown of what makes this release notable: → 295B total parameters (Mixture-of-Experts), but only 21B active at inference — a real efficiency play → 256K context window for handling large codebases or long documents → Purpose-built improvements for coding and multi-step agent tasks → Fully open under Apache 2.0 — no restrictive commercial terms → A free two-week API window currently live on OpenRouter On the practical side: prompts involving layered instructions and coding tasks came back fast and coherent. Tencent says this release builds directly on feedback from 50+ internal product teams following an earlier preview, with reported drops in hallucination rate (12.5% → 5.4%) and commonsense errors (25.4% → 12.7%). Those are Tencent's own numbers, so treat them as a starting point rather than gospel until third parties weigh in. For context: Tencent's own comparisons put Hy3 behind GLM-5.2 specifically on coding benchmarks — GLM is a much bigger model (~744B total), so the trade-off makes sense. Hy3's pitch isn't "biggest," it's "efficient enough to actually deploy." Bottom line — if you're evaluating open-weight options for agent workloads, this is a solid one to add to the testing queue while the free window is open. Try it here: Tencent Hy #Hy3 #Hunyuan #TencentAI #AICoding

Felix

36,925 views • 20 days ago