Loading video...

Video Failed to Load

Go Home

Every developer has an IDE. Researchers never had one. We don’t need another research agent, but a full stack workstation powered by AI. Today we're launching Orchestra Orchestra Reseach, the world's first Research IDE 🔬🧵

ZechenZhang5's profile picture

Zechen Zhang

1,745 subscribers

77,581 views • 3 months ago •via X (Twitter)

Science & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

People keep asking us when we're launching an IDE. Today we're proud to share: never. We showed you the CLI. There's one more thing we're building. Here's a sneak peek - and why we'll need new surfaces for AI-augmented software engineering.
2:22

People keep asking us when we're launching an IDE. Today we're proud to share: never. We showed you the CLI. There's one more thing we're building. Here's a sneak peek - and why we'll need new surfaces for AI-augmented software engineering.

Augment Code

763,120 views • 11 months ago

Today we're launching Scholara, the world's first AI-native systematic review platform. The systematic review is the gold standard of evidence in research. It's also one of the most time-consuming and costly things a researcher will ever do with an average of 68 weeks to complete. We rebuilt the entire pipeline into a sub 2-hour conversation. Scholara is already used and trusted by thousands of researchers, completing systematic reviews in hours.
3:30

Today we're launching Scholara, the world's first AI-native systematic review platform. The systematic review is the gold standard of evidence in research. It's also one of the most time-consuming and costly things a researcher will ever do with an average of 68 weeks to complete. We rebuilt the entire pipeline into a sub 2-hour conversation. Scholara is already used and trusted by thousands of researchers, completing systematic reviews in hours.

Liam

21,303 views • 21 days ago

Building products takes too long. We started Lovable to fix this. Today, we're officially launching the world’s first AI Full Stack Engineer Lovable reliably replicates the capabilities of a full stack engineer and handles everything from design to database operations by integrating with Supabase. So what’s new exactly? 🧵
1:28

Building products takes too long. We started Lovable to fix this. Today, we're officially launching the world’s first AI Full Stack Engineer Lovable reliably replicates the capabilities of a full stack engineer and handles everything from design to database operations by integrating with Supabase. So what’s new exactly? 🧵

Lovable

232,599 views • 1 year ago

🚨 Introducing Tempo Labs (YC S23) 🚨 A Visual Editor for React, Powered by AI. Feels like a design tool, works like an IDE. Design visually. Ship code instantly. What Makes Tempo Different: ⚡ Code-First: Works with any codebase just like an IDE. 🤝 Live Collaboration: Share links and build together in real-time. 🚀 AI-Powered: Generate full-stack apps using a text or image prompt 📢 We’re LIVE on Product Hunt! So please support us! Link below👇
1:09

🚨 Introducing Tempo Labs (YC S23) 🚨 A Visual Editor for React, Powered by AI. Feels like a design tool, works like an IDE. Design visually. Ship code instantly. What Makes Tempo Different: ⚡ Code-First: Works with any codebase just like an IDE. 🤝 Live Collaboration: Share links and build together in real-time. 🚀 AI-Powered: Generate full-stack apps using a text or image prompt 📢 We’re LIVE on Product Hunt! So please support us! Link below👇

Kevin Michael

108,425 views • 1 year ago

Introducing Orchids, the world's first vibe coding IDE. Orchids can build, watch, and listen on par with a human developer. Orchids ranks #1 on App Bench, the most rigorous benchmark for end-to-end software development. An agent, IDE, built-in browser, Supabase, and Stripe all in a single tool. Local, no lock in, no browser limitations - the next step forward in building with AI. Comment for 100k free credits at orchids [dot] app.
1:03

Introducing Orchids, the world's first vibe coding IDE. Orchids can build, watch, and listen on par with a human developer. Orchids ranks #1 on App Bench, the most rigorous benchmark for end-to-end software development. An agent, IDE, built-in browser, Supabase, and Stripe all in a single tool. Local, no lock in, no browser limitations - the next step forward in building with AI. Comment for 100k free credits at orchids [dot] app.

Bud

850,142 views • 7 months ago

Hi, I am Sergey, founder of Scade We built the first full stack AI powered marketing system We are launching our token $AICMO on Pond, backed by @CyberFund_ and Delphi Labs Voting starts today, at 15:00 CET Let’s make it happen together 👇
2:23

Hi, I am Sergey, founder of Scade We built the first full stack AI powered marketing system We are launching our token $AICMO on Pond, backed by @CyberFund_ and Delphi Labs Voting starts today, at 15:00 CET Let’s make it happen together 👇

scade.xyz

66,540 views • 10 months ago

Today we're launching Latent-Y: the world's first autonomous agent for drug design, lab-validated end to end. Give it a research goal. Latent-Y reasons, designs, iterates, and delivers lab-ready antibodies, autonomously or collaboratively, with the biological reasoning of a PhD protein design expert. Technical report: Blog post: Apply for access:
1:56

Today we're launching Latent-Y: the world's first autonomous agent for drug design, lab-validated end to end. Give it a research goal. Latent-Y reasons, designs, iterates, and delivers lab-ready antibodies, autonomously or collaboratively, with the biological reasoning of a PhD protein design expert. Technical report: Blog post: Apply for access:

Simon Kohl

120,752 views • 3 months ago

🚨the difference between a $95K developer and a $300K AI architect is knowing this list exists while most people type one-off prompts, a small group stacks specialized Claude skills and runs automated workflow factories 24/7 32 skills across 10 repositories. audited, ranked, and grouped into three stacks: > builder stack: doc-coauthoring, app-docs, research-skill, skill-creator > operator stack: connect-apps, file-organizer, deep-research, Apollo automation > knowledge stack: Skill_Seekers, content-research-writer, wondelai 42-skill pack most developers have never heard of any of these the salary gap is real. the skill gap is fixable in an afternoon. full list with direct GitHub links in the article
0:20

🚨the difference between a $95K developer and a $300K AI architect is knowing this list exists while most people type one-off prompts, a small group stacks specialized Claude skills and runs automated workflow factories 24/7 32 skills across 10 repositories. audited, ranked, and grouped into three stacks: > builder stack: doc-coauthoring, app-docs, research-skill, skill-creator > operator stack: connect-apps, file-organizer, deep-research, Apollo automation > knowledge stack: Skill_Seekers, content-research-writer, wondelai 42-skill pack most developers have never heard of any of these the salary gap is real. the skill gap is fixable in an afternoon. full list with direct GitHub links in the article

Fokki

11,829 views • 1 month ago

🚀🚀 Introducing AI Roleplays by Exec.com I’ve launched a lot of products in my 15 year career. But this is far and away the one I’m most excited about. Today we are launching Roleplays – an AI powered learning experience for practicing high-stake conversations.
3:07

🚀🚀 Introducing AI Roleplays by Exec.com I’ve launched a lot of products in my 15 year career. But this is far and away the one I’m most excited about. Today we are launching Roleplays – an AI powered learning experience for practicing high-stake conversations.

Sean Linehan

23,924 views • 1 year ago

AI made everyone 10x faster. But the faster individuals move, the harder it is to move together. Speed ≠ Progress when no one has the full picture. Today we emerge from stealth with $5M led by @GeneralCatalyst to fix this. Meet Stilla : The first Multiplayer AI. 🧵
1:40

AI made everyone 10x faster. But the faster individuals move, the harder it is to move together. Speed ≠ Progress when no one has the full picture. Today we emerge from stealth with $5M led by @GeneralCatalyst to fix this. Meet Stilla : The first Multiplayer AI. 🧵

Siavash

166,230 views • 5 months ago

70,000 Phones, One AI Agent — The World's Largest Edge AI Fleet Runs on Hermes We turned 70,000 phones into a shared AI compute network. Any device owner contributes idle compute. Any developer taps distributed inference at a fraction of cloud cost. Not a concept. Not a whitepaper. 70K devices online today. The problem: orchestrating a shared network of heterogeneous edge devices — different chipsets, different memory, different thermal profiles, different owners — is a coordination nightmare no human team can handle manually. So we gave the network a brain: Nous Research Hermes Agent. Hermes connects to 16 MCP servers and runs 24/7: 🔬 Research Loop — Tracks every breakthrough in on-device inference: quantization (GPTQ/AWQ/GGUF), speculative decoding on mobile SoCs, federated learning protocols. Auto-imports papers into NotebookLM. 36 research topics, zero manual curation. 🌐 Network Intelligence — Monitors device availability, compute capacity, and workload distribution across the shared fleet. Surfaces bottlenecks before they cascade. 🧬 Tech Tree Optimizer — Maps the full optimization frontier: from KV-cache compression to on-device LoRA to peer-to-peer model sharding. Hermes autonomously identifies which research paths unlock the most network-wide throughput gains. The result: a self-improving shared compute network. Research compounds daily. The fleet gets smarter without human intervention. Cloud AI scales with money. We scale with people. #HermesHackathon Teknium 🪽 Delphi Digital Tommy
0:30

70,000 Phones, One AI Agent — The World's Largest Edge AI Fleet Runs on Hermes We turned 70,000 phones into a shared AI compute network. Any device owner contributes idle compute. Any developer taps distributed inference at a fraction of cloud cost. Not a concept. Not a whitepaper. 70K devices online today. The problem: orchestrating a shared network of heterogeneous edge devices — different chipsets, different memory, different thermal profiles, different owners — is a coordination nightmare no human team can handle manually. So we gave the network a brain: Nous Research Hermes Agent. Hermes connects to 16 MCP servers and runs 24/7: 🔬 Research Loop — Tracks every breakthrough in on-device inference: quantization (GPTQ/AWQ/GGUF), speculative decoding on mobile SoCs, federated learning protocols. Auto-imports papers into NotebookLM. 36 research topics, zero manual curation. 🌐 Network Intelligence — Monitors device availability, compute capacity, and workload distribution across the shared fleet. Surfaces bottlenecks before they cascade. 🧬 Tech Tree Optimizer — Maps the full optimization frontier: from KV-cache compression to on-device LoRA to peer-to-peer model sharding. Hermes autonomously identifies which research paths unlock the most network-wide throughput gains. The result: a self-improving shared compute network. Research compounds daily. The fleet gets smarter without human intervention. Cloud AI scales with money. We scale with people. #HermesHackathon Teknium 🪽 Delphi Digital Tommy

Oyster Republic 🦪📲🦞👓

20,716 views • 4 months ago

⭐️ Introducing the 2025 Don’t Get Dressed Awards ⭐️ We're launching a celebration of love, chaos, comedy, and Coronation Street brilliance by spotlighting the duo we never knew we needed, but now can’t live without. Here's everything you need to know:
0:34

⭐️ Introducing the 2025 Don’t Get Dressed Awards ⭐️ We're launching a celebration of love, chaos, comedy, and Coronation Street brilliance by spotlighting the duo we never knew we needed, but now can’t live without. Here's everything you need to know:

Swarla HQ

15,942 views • 11 months ago

Today we're launching SureThing 2.0 - the world's first General AI Agency. You've found skills you've wanted to use for months but never knew how. Now paste the link - it becomes a proactive employee with a real GUI dashboard and live memory. Not a chatbot. Not a terminal. An entire team that runs your business: your AI COO, CMO, CXO, and Researcher — one brain, zero silos. SaaS is dead. GUI isn't. Try it →
1:49

Today we're launching SureThing 2.0 - the world's first General AI Agency. You've found skills you've wanted to use for months but never knew how. Now paste the link - it becomes a proactive employee with a real GUI dashboard and live memory. Not a chatbot. Not a terminal. An entire team that runs your business: your AI COO, CMO, CXO, and Researcher — one brain, zero silos. SaaS is dead. GUI isn't. Try it →

SureThing

840,015 views • 3 months ago

Open sourcing the first Expo vibe coding web IDE and SDK: React Native Vibe Code Powered by Claude agent SDK, history rollbacks, live web and native app previews, full stack setup by Convex, publish to web w/ Cloudflare, voice prompting, upload assets to app, add images and files to prompt, model selector, skills loader, visual edits, sandboxing by E2B, download codebase option, Monaco code editor, fork/remix and a CLI to run locally. The project is a Turborepo running Next.js hosted on Vercel with streaming powered by AI SDK ◆ try cloud version at ◆ github repo:
0:59

Open sourcing the first Expo vibe coding web IDE and SDK: React Native Vibe Code Powered by Claude agent SDK, history rollbacks, live web and native app previews, full stack setup by Convex, publish to web w/ Cloudflare, voice prompting, upload assets to app, add images and files to prompt, model selector, skills loader, visual edits, sandboxing by E2B, download codebase option, Monaco code editor, fork/remix and a CLI to run locally. The project is a Turborepo running Next.js hosted on Vercel with streaming powered by AI SDK ◆ try cloud version at ◆ github repo:

ROFI

44,523 views • 4 months ago

🎙️ What’s the Meta? Out tomorrow! A research lab has given a rat an AI-powered brain that allows it to answer questions. We speak to two people from NEIRY about how this works, a future of chatting with cows, and the ways its meme coin $PYTHIA has helped the lab. You don’t want to miss this 🐀
0:29

🎙️ What’s the Meta? Out tomorrow! A research lab has given a rat an AI-powered brain that allows it to answer questions. We speak to two people from NEIRY about how this works, a future of chatting with cows, and the ways its meme coin $PYTHIA has helped the lab. You don’t want to miss this 🐀

Decrypt

16,138 views • 1 year ago

Artificial intelligence has made another step into the physical world by launching a café in Sweden. Its founders claim it is the first commercial venue in Europe fully run by an AI agent, amid concerns about AI’s impact on the job market. Al Jazeera’s Paul Rhys reports.
2:13

Artificial intelligence has made another step into the physical world by launching a café in Sweden. Its founders claim it is the first commercial venue in Europe fully run by an AI agent, amid concerns about AI’s impact on the job market. Al Jazeera’s Paul Rhys reports.

Al Jazeera English

69,629 views • 1 month ago

It's Launch Day Contra and this is one of our biggest launches yet. 🚀. Today we are launching Portfolio Magic, an AI powered portfolio builder with built in 💸payments 📈analytics 💰contracts, proposals, invoices + a ton of platform upgrades as well. More in the 🧵
0:48

It's Launch Day Contra and this is one of our biggest launches yet. 🚀. Today we are launching Portfolio Magic, an AI powered portfolio builder with built in 💸payments 📈analytics 💰contracts, proposals, invoices + a ton of platform upgrades as well. More in the 🧵

ben

180,411 views • 2 years ago

Super excited to share 🧠MLGym 🦾 – the first Gym environment for AI Research Agents 🤖🔬 We introduce MLGym and MLGym-Bench, a new framework and benchmark for evaluating and developing LLM agents on AI research tasks. The key contributions of our work are: 🕹️ Enables the exploration of different training algorithms for AI Research Agents such as RL 🛠️ Provides a flexible evaluation framework that can accommodate different artifacts such as models, algorithms, or predictions 🤖 Allows researchers to evaluate any model without the need to develop a custom agentic harness 🎯 Introduces 13 diverse open-ended AI Research tasks for evaluating AI Research Agents on a wide range of domains such as computer vision, natural language processing, reinforcement learning, game theory, and logical reasoning. 📈 Proposes a new evaluation metric for AI Research Agents MLGym makes it easy to: 1) Add new tasks 2) Evaluate new models 3) Integrate new agents Check out a video of the MLGym Agent to see how it performs the full pipeline of idea generation💡, implementation 👩‍💻, experimentation 👩‍🔬, and iteration 🔄 to improve on ML tasks. Huge thanks to the exceptionally talented Deepak Nathani who led this work and to all the other amazing collaborators who made this possible 🙏🫶🚀
1:32

Super excited to share 🧠MLGym 🦾 – the first Gym environment for AI Research Agents 🤖🔬 We introduce MLGym and MLGym-Bench, a new framework and benchmark for evaluating and developing LLM agents on AI research tasks. The key contributions of our work are: 🕹️ Enables the exploration of different training algorithms for AI Research Agents such as RL 🛠️ Provides a flexible evaluation framework that can accommodate different artifacts such as models, algorithms, or predictions 🤖 Allows researchers to evaluate any model without the need to develop a custom agentic harness 🎯 Introduces 13 diverse open-ended AI Research tasks for evaluating AI Research Agents on a wide range of domains such as computer vision, natural language processing, reinforcement learning, game theory, and logical reasoning. 📈 Proposes a new evaluation metric for AI Research Agents MLGym makes it easy to: 1) Add new tasks 2) Evaluate new models 3) Integrate new agents Check out a video of the MLGym Agent to see how it performs the full pipeline of idea generation💡, implementation 👩‍💻, experimentation 👩‍🔬, and iteration 🔄 to improve on ML tasks. Huge thanks to the exceptionally talented Deepak Nathani who led this work and to all the other amazing collaborators who made this possible 🙏🫶🚀

Roberta Raileanu

105,030 views • 1 year ago