Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

Most AI tools stop at generating text. The real test is whether they understand *systems, workflows, and developers*. I tested GLM-4.7 from a builder’s perspective — UI, architecture, apps, and core logic.

Diptish09's profile picture

Dipti Sharma

30,537 subscribers

122,577 görüntüleme • 5 ay önce •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

Google is making a bet on Vibe Coding tools by making it simpler for non-developers to create apps with AI. Gemini Canvas is soon to get a "Select and Ask" feature for "in-painting" of the selected UI area.
0:38

Google is making a bet on Vibe Coding tools by making it simpler for non-developers to create apps with AI. Gemini Canvas is soon to get a "Select and Ask" feature for "in-painting" of the selected UI area.

🚨 AI News | TestingCatalog

54,192 görüntüleme • 10 ay önce

Everyone is learning JS/React. Everyone is learning AI tools. Almost no one is learning: > Kernel internals > Storage engines > Consensus algorithms > CPU architecture > Scheduling > Observability > Load balancing > Caching internals > RPC systems > Event-driven architecture The UI crowd is saturated. The systems crowd is rare.
0:26

Everyone is learning JS/React. Everyone is learning AI tools. Almost no one is learning: > Kernel internals > Storage engines > Consensus algorithms > CPU architecture > Scheduling > Observability > Load balancing > Caching internals > RPC systems > Event-driven architecture The UI crowd is saturated. The systems crowd is rare.

Satyam

32,901 görüntüleme • 2 ay önce

⚡ Ship AI apps faster with Genkit → Benefit from multi-model support, intuitive Dev UI for testing, and full observability of your AI workflows.
0:56

⚡ Ship AI apps faster with Genkit → Benefit from multi-model support, intuitive Dev UI for testing, and full observability of your AI workflows.

Google for Developers

13,893 görüntüleme • 7 ay önce

StarVector is out on Hugging Face StarVector is a foundation model for generating Scalable Vector Graphics (SVG) code from images and text. It utilizes a Vision-Language Modeling architecture to understand both visual and textual inputs, enabling high-quality vectorization and text-guided SVG creation.
0:52

StarVector is out on Hugging Face StarVector is a foundation model for generating Scalable Vector Graphics (SVG) code from images and text. It utilizes a Vision-Language Modeling architecture to understand both visual and textual inputs, enabling high-quality vectorization and text-guided SVG creation.

AK

254,242 görüntüleme • 1 yıl önce

Parallel Search + Extract tools in the @Vercel AI SDK make it easier than ever to give AI agents, apps, and workflows access to the most accurate and token-efficient web context. Here's our very own Manvesh demoing a simple implementation of the tools in an AI project.
2:06

Parallel Search + Extract tools in the @Vercel AI SDK make it easier than ever to give AI agents, apps, and workflows access to the most accurate and token-efficient web context. Here's our very own Manvesh demoing a simple implementation of the tools in an AI project.

Parallel Web Systems

21,913 görüntüleme • 6 ay önce

Artificial intelligence is increasingly embedded in your workday. Filmed from the perspective of AI glasses, this video follows an intellectual property journalist through routine assignments and workplace scenes, showing how AI tools are applied in real tasks and quietly integrated into daily workflows.
1:02

Artificial intelligence is increasingly embedded in your workday. Filmed from the perspective of AI glasses, this video follows an intellectual property journalist through routine assignments and workplace scenes, showing how AI tools are applied in real tasks and quietly integrated into daily workflows.

IPR in China

33,986 görüntüleme • 3 ay önce

Most AI builders fail at backend logic. Convex Chef is a new AI agent that builds full-stack apps with real-time data, auth, background jobs, and multiplayer previews. Here’s how it works ↓
0:43

Most AI builders fail at backend logic. Convex Chef is a new AI agent that builds full-stack apps with real-time data, auth, background jobs, and multiplayer previews. Here’s how it works ↓

Prajwal Tomar

41,918 görüntüleme • 1 yıl önce

Mansa AI is an enterprise-grade AI + Web3 platform designed to move artificial intelligence from experimentation into real-world execution. Built for creators, developers, and businesses, it focuses on deploying AI that actually works across modern digital systems, not just in isolated demos. 🚀 Production-ready AI infrastructure Mansa AI enables teams to deploy AI systems designed for live environments, handling real workflows, real data, and real operational demands without constant manual oversight. 🧠 Autonomous AI agents At its core, Mansa AI allows users to build autonomous agents that automate decision-making, coordinate tasks, monitor live signals, and execute complex workflows across dynamic environments. ⚙️ Fully customizable logic Agents can be configured with custom behaviors, triggers, and responses. From content generation and analytics to operational automation and intelligent orchestration, logic adapts to specific business strategies. 🔗 Web3 and off-chain integration Mansa AI bridges blockchain ecosystems with traditional systems, enabling cross-chain coordination, smart contract interactions, and seamless integration with existing enterprise infrastructure. 📊 Real-world use cases The platform supports automation for operations, customer engagement, analytics, data pipelines, content workflows, and AI-driven optimization across products and teams. 📈 Built for scale Whether launching as a startup or deploying across enterprise systems, Mansa AI is designed to scale AI operations without adding complexity or fragmentation. Mansa AI transforms artificial intelligence into deployable infrastructure. By combining autonomy, customization, interoperability, and scalability, it enables teams to own, operate, and grow intelligent systems that deliver real value in production environments.
2:00

Mansa AI is an enterprise-grade AI + Web3 platform designed to move artificial intelligence from experimentation into real-world execution. Built for creators, developers, and businesses, it focuses on deploying AI that actually works across modern digital systems, not just in isolated demos. 🚀 Production-ready AI infrastructure Mansa AI enables teams to deploy AI systems designed for live environments, handling real workflows, real data, and real operational demands without constant manual oversight. 🧠 Autonomous AI agents At its core, Mansa AI allows users to build autonomous agents that automate decision-making, coordinate tasks, monitor live signals, and execute complex workflows across dynamic environments. ⚙️ Fully customizable logic Agents can be configured with custom behaviors, triggers, and responses. From content generation and analytics to operational automation and intelligent orchestration, logic adapts to specific business strategies. 🔗 Web3 and off-chain integration Mansa AI bridges blockchain ecosystems with traditional systems, enabling cross-chain coordination, smart contract interactions, and seamless integration with existing enterprise infrastructure. 📊 Real-world use cases The platform supports automation for operations, customer engagement, analytics, data pipelines, content workflows, and AI-driven optimization across products and teams. 📈 Built for scale Whether launching as a startup or deploying across enterprise systems, Mansa AI is designed to scale AI operations without adding complexity or fragmentation. Mansa AI transforms artificial intelligence into deployable infrastructure. By combining autonomy, customization, interoperability, and scalability, it enables teams to own, operate, and grow intelligent systems that deliver real value in production environments.

King

155,637 görüntüleme • 6 ay önce

🚨 Out now: Inside the Robot: Architecture Benchmark Report 1,000 developers share what’s shaping robotics today, from AI-driven systems to real-world deployment challenges. What’s holding the industry back, and what’s next? 🔗
0:52

🚨 Out now: Inside the Robot: Architecture Benchmark Report 1,000 developers share what’s shaping robotics today, from AI-driven systems to real-world deployment challenges. What’s holding the industry back, and what’s next? 🔗

QNX News

21,725 görüntüleme • 19 gün önce

2026 is the year of the robot, but developer tools are stuck in workflows similar to 2009 pre-GitHub software workflows. We’re changing that at Tnkr, building workflows so developers can, build, fork, mod/remix, and deploy more robots in the real world! Happy new year !
0:36

2026 is the year of the robot, but developer tools are stuck in workflows similar to 2009 pre-GitHub software workflows. We’re changing that at Tnkr, building workflows so developers can, build, fork, mod/remix, and deploy more robots in the real world! Happy new year !

Ayo

44,231 görüntüleme • 5 ay önce

Last week we launched our Superagents. This is the fastest I’ve seen a product grow from 0. A lot of excitement from users, and more importantly – people actually started using it in real workflows almost immediately. We started getting a lot of feedback from how people were actually using it. We shipped 8 things to Base44 Superagent this week. The one I can't stop demoing: Mini Apps is wild. Your agent can now build and show a small working app right inside the conversation. Not text, actual interactive UI with your real data.
0:25

Last week we launched our Superagents. This is the fastest I’ve seen a product grow from 0. A lot of excitement from users, and more importantly – people actually started using it in real workflows almost immediately. We started getting a lot of feedback from how people were actually using it. We shipped 8 things to Base44 Superagent this week. The one I can't stop demoing: Mini Apps is wild. Your agent can now build and show a small working app right inside the conversation. Not text, actual interactive UI with your real data.

Maor Shlomo

14,175 görüntüleme • 2 ay önce

Destra Network | $DSYNC We’re launching a new series on X to help our community understand the real power of Destra NPC & Primus. Platforms like Clawd have shown how AI can automate workflows and connect tools. But they are primitive But automation is only the first step. What we’re building with NPC & Primus goes much further. This series will cover: • How to use the NPC platform • How Primus thinks, plans, and executes independently • How full systems are built end-to-end by AI • Why native AI infrastructure outperforms simple integrations Most platforms focus on triggering actions. Primus doesn’t just connect apps—it designs logic, writes contracts, deploys infrastructure, and manages execution end to end. Below is a demo of Primus building a decentralized voting system from scratch. No templates, no rigid flows, no hand-holding—just fully autonomous systems. Good tools helped start the movement. NPC is defining the next phase. More episodes coming soon. — Destra Network
3:31

Destra Network | $DSYNC We’re launching a new series on X to help our community understand the real power of Destra NPC & Primus. Platforms like Clawd have shown how AI can automate workflows and connect tools. But they are primitive But automation is only the first step. What we’re building with NPC & Primus goes much further. This series will cover: • How to use the NPC platform • How Primus thinks, plans, and executes independently • How full systems are built end-to-end by AI • Why native AI infrastructure outperforms simple integrations Most platforms focus on triggering actions. Primus doesn’t just connect apps—it designs logic, writes contracts, deploys infrastructure, and manages execution end to end. Below is a demo of Primus building a decentralized voting system from scratch. No templates, no rigid flows, no hand-holding—just fully autonomous systems. Good tools helped start the movement. NPC is defining the next phase. More episodes coming soon. — Destra Network

Destra Network

17,919 görüntüleme • 4 ay önce

General AI is already a dated concept. ThinkingAI connects an entire business ecosystem through MCP, pulling data, tools, and workflows into a single execution layer. Not isolated AI tools working separately. Coordinated agent systems triggering real actions across the whole operation. The shift is from using AI to running on it. Every company becomes an AI-powered system built on custom agent teams through the ThinkingAI Agentic Engine.
5:06

General AI is already a dated concept. ThinkingAI connects an entire business ecosystem through MCP, pulling data, tools, and workflows into a single execution layer. Not isolated AI tools working separately. Coordinated agent systems triggering real actions across the whole operation. The shift is from using AI to running on it. Every company becomes an AI-powered system built on custom agent teams through the ThinkingAI Agentic Engine.

Future Stacked

52,003 görüntüleme • 1 ay önce

Introducing /ui-test Give your agent a PR, and it'll test your feature in a real browser, generating an HTML report with UI fixes The planner agent generates adversarial test cases to break your app, assigns them to subagents, and evaluates the page using the Browserbase CLI We reviewed a merged PR on Cal.com and found a bunch of small UI nits:
0:35

Introducing /ui-test Give your agent a PR, and it'll test your feature in a real browser, generating an HTML report with UI fixes The planner agent generates adversarial test cases to break your app, assigns them to subagents, and evaluates the page using the Browserbase CLI We reviewed a merged PR on Cal.com and found a bunch of small UI nits:

Shrey Pandya

57,480 görüntüleme • 2 ay önce

Current AI cannot solve difficult, real-world problems. The path to AGI is a focus on improving reasoning systems, multi agent workflows, and coordination.
0:33

Current AI cannot solve difficult, real-world problems. The path to AGI is a focus on improving reasoning systems, multi agent workflows, and coordination.

Sentient

12,844 görüntüleme • 4 ay önce

How does the #1 open Text Arena model hold up in agentic coding tasks? We tested GLM-5 in Code Arena with head-to-head SVG prompts vs. top frontier AI models. What do you think? Scores for Z.ai 's GLM-5 in Code Arena coming soon. Test out GLM-5 for yourself and get voting.
0:52

How does the #1 open Text Arena model hold up in agentic coding tasks? We tested GLM-5 in Code Arena with head-to-head SVG prompts vs. top frontier AI models. What do you think? Scores for Z.ai 's GLM-5 in Code Arena coming soon. Test out GLM-5 for yourself and get voting.

Arena.ai

115,220 görüntüleme • 4 ay önce

Elon Musk: In 5-6 years, the phone becomes an AI edge node — basically a screen and audio "no apps, no operating systems" a cloud AI talks to your on-device AI, generating real-time video you'll get everything through AI that anticipates what you want
1:46

Elon Musk: In 5-6 years, the phone becomes an AI edge node — basically a screen and audio "no apps, no operating systems" a cloud AI talks to your on-device AI, generating real-time video you'll get everything through AI that anticipates what you want

Haider.

1,024,430 görüntüleme • 7 ay önce

You don’t need a dev team anymore. You need one prompt. Zoer takes your idea and turns it into a fully working app, not just code, but a real product you can use. Here’s what it handles for you: • Database (already structured) • Backend (logic + APIs) • Frontend (clean, production-ready UI) • Auth (Google + email login) • Deployment (live in one click) Most AI tools stop at “here’s your code.” Zoer goes further: It builds the entire system and puts it live. From: “build me a CRM / SaaS / tool” To: A real, working product you can open, test, and share. Try it → No setup. No configs. No extra tools. This is what building should feel like in 2026.
0:53

You don’t need a dev team anymore. You need one prompt. Zoer takes your idea and turns it into a fully working app, not just code, but a real product you can use. Here’s what it handles for you: • Database (already structured) • Backend (logic + APIs) • Frontend (clean, production-ready UI) • Auth (Google + email login) • Deployment (live in one click) Most AI tools stop at “here’s your code.” Zoer goes further: It builds the entire system and puts it live. From: “build me a CRM / SaaS / tool” To: A real, working product you can open, test, and share. Try it → No setup. No configs. No extra tools. This is what building should feel like in 2026.

Tanvir

18,160 görüntüleme • 1 ay önce

last few weeks in AI has been truly amazing as a reporter *and a user *and a mom from watching my kids vibecode working apps on Replit to unlocking high-level (to me) Excel workflows w Claude to seeing Chinese models like Zhipu’s GLM 4.7 bridge the gap feels bigger & more immediate than initial chatGPT moment bc its not just chatting, its building (pictured: 10 yo's geometry dash seahawks edition)
0:31

last few weeks in AI has been truly amazing as a reporter *and a user *and a mom from watching my kids vibecode working apps on Replit to unlocking high-level (to me) Excel workflows w Claude to seeing Chinese models like Zhipu’s GLM 4.7 bridge the gap feels bigger & more immediate than initial chatGPT moment bc its not just chatting, its building (pictured: 10 yo's geometry dash seahawks edition)

Deirdre Bosa

13,490 görüntüleme • 4 ay önce