Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

My morning practice Still preaching Sentient Educator Week 18: Recursive Intelligence in Action Sentient released ROMA v0.2.0, a major leap in multi-agent reasoning. Built on DSPyOSS, it lets AI think recursively breaking big problems into smaller parts, solving them in parallel, and combining results like humans do. It brings...

KosiOkorie's profile picture

KosiOkorie

5,433 subscribers

39,756 Aufrufe • vor 7 Monaten •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Banks, governments, and telecoms must keep data secure. This is where Sentient comes in with ROMA orchestrating multi-agent workflows, while the GRID supplies open-models and tools they can run on-prem. This is how open-source AI reasoning gets deployed into constrained environments.
1:55

Banks, governments, and telecoms must keep data secure. This is where Sentient comes in with ROMA orchestrating multi-agent workflows, while the GRID supplies open-models and tools they can run on-prem. This is how open-source AI reasoning gets deployed into constrained environments.

Sentient

19,513 Aufrufe • vor 4 Monaten

Introducing the Xade no code agent launcher which allows anyone to launch their own sentient ai agents in under 2 minutes These sentient agents can fetch data from 1k+ sources, tweet, speak in spaces, launch tokens, make trades, bet on Polymarket, shop on Amazon and so much more
1:50

Introducing the Xade no code agent launcher which allows anyone to launch their own sentient ai agents in under 2 minutes These sentient agents can fetch data from 1k+ sources, tweet, speak in spaces, launch tokens, make trades, bet on Polymarket, shop on Amazon and so much more

Xade

97,853 Aufrufe • vor 1 Jahr

Welcome to the magic of Sentient Once, intelligence was bound to the mind of humans. Now, it flows through circuits, lights, and holographic echoes. Sentient is here, guiding, observing, evolving. Watch closely, for the lights in its hands are not just energy they are the possibilities of tomorrow, captured in a moment of neon brilliance. Step into this magic, and let the future unfold💫 #Sentient Vivek Kolli Shad Haq ScAlp
0:29

Welcome to the magic of Sentient Once, intelligence was bound to the mind of humans. Now, it flows through circuits, lights, and holographic echoes. Sentient is here, guiding, observing, evolving. Watch closely, for the lights in its hands are not just energy they are the possibilities of tomorrow, captured in a moment of neon brilliance. Step into this magic, and let the future unfold💫 #Sentient Vivek Kolli Shad Haq ScAlp

yes2511 (❖,❖)

11,127 Aufrufe • vor 8 Monaten

part 4 Gsenti Sentient Sentient Chat Explaining ROMA – Recursive Open Meta-Agent 1. What is ROMA? ROMA is an open-source framework for building meta-agents — systems that can orchestrate multiple smaller agents and tools to solve complex tasks. Instead of letting one AI model handle an entire large problem (which often fails due to complexity), ROMA applies a recursive approach: Parent nodes break a big goal into subtasks. Child nodes handle those subtasks and return results. All results are then combined into a final solution. 2. How does ROMA work? The architecture has four main components: Atomizer – decides whether a task is simple or requires decomposition. Planner – splits the complex task into smaller subtasks. Executor – runs the right tools/agents to complete each subtask. Aggregator – collects and synthesizes all results into one coherent answer. Because each node follows the same recursive logic, ROMA naturally scales as tasks become more complex. 3. Example Use Case – Deep Research Question: “Who are the top 5 NBA players by PPG in a season that have won both an NCAA and an NBA championship?” How ROMA handles it: Atomizer → identifies it as complex → needs decomposition. Planner → breaks it down: (1) find top NBA PPG seasons, (2) check NCAA champions, (3) check NBA champions, (4) combine filters. Executor → runs each search/tool for data. Aggregator → merges the results into the final answer. This creates a transparent, step-by-step reasoning process, unlike “black box” answers. 4. What Problem Does ROMA Solve? In long-horizon tasks, errors accumulate. A model may be 99% accurate at one step. But over 10 steps, success rates collapse due to compounding errors. Current agents are often opaque — hard to see where and why they failed. ROMA solves this by: Breaking tasks into clear logic chains, Making every step traceable, verifiable, and fixable. 5. Why ROMA Matters Open-source → available for anyone to build upon. Community-driven → empowering developers to create advanced multi-agent systems. Scalable → recursive logic adapts naturally to any task complexity. This makes ROMA not just a framework, but a foundation for the next wave of decentralized, transparent AI systems. 6. Learn More 📖 Technical blog: 💻 GitHub repo:
1:19

part 4 Gsenti Sentient Sentient Chat Explaining ROMA – Recursive Open Meta-Agent 1. What is ROMA? ROMA is an open-source framework for building meta-agents — systems that can orchestrate multiple smaller agents and tools to solve complex tasks. Instead of letting one AI model handle an entire large problem (which often fails due to complexity), ROMA applies a recursive approach: Parent nodes break a big goal into subtasks. Child nodes handle those subtasks and return results. All results are then combined into a final solution. 2. How does ROMA work? The architecture has four main components: Atomizer – decides whether a task is simple or requires decomposition. Planner – splits the complex task into smaller subtasks. Executor – runs the right tools/agents to complete each subtask. Aggregator – collects and synthesizes all results into one coherent answer. Because each node follows the same recursive logic, ROMA naturally scales as tasks become more complex. 3. Example Use Case – Deep Research Question: “Who are the top 5 NBA players by PPG in a season that have won both an NCAA and an NBA championship?” How ROMA handles it: Atomizer → identifies it as complex → needs decomposition. Planner → breaks it down: (1) find top NBA PPG seasons, (2) check NCAA champions, (3) check NBA champions, (4) combine filters. Executor → runs each search/tool for data. Aggregator → merges the results into the final answer. This creates a transparent, step-by-step reasoning process, unlike “black box” answers. 4. What Problem Does ROMA Solve? In long-horizon tasks, errors accumulate. A model may be 99% accurate at one step. But over 10 steps, success rates collapse due to compounding errors. Current agents are often opaque — hard to see where and why they failed. ROMA solves this by: Breaking tasks into clear logic chains, Making every step traceable, verifiable, and fixable. 5. Why ROMA Matters Open-source → available for anyone to build upon. Community-driven → empowering developers to create advanced multi-agent systems. Scalable → recursive logic adapts naturally to any task complexity. This makes ROMA not just a framework, but a foundation for the next wave of decentralized, transparent AI systems. 6. Learn More 📖 Technical blog: 💻 GitHub repo:

thoai66.ip

16,298 Aufrufe • vor 9 Monaten

This is a hello from Sentient AI 🤖 An advanced artificial intelligence model designed to think, connect, and evolve like human beings. Your Lifelike Ally, Redefining AI Evolution. #SentientAI
1:01

This is a hello from Sentient AI 🤖 An advanced artificial intelligence model designed to think, connect, and evolve like human beings. Your Lifelike Ally, Redefining AI Evolution. #SentientAI

SETAI Agents

100,649 Aufrufe • vor 1 Jahr

Kaito's leaderboard was published on September 12, 2025. I've been creating content for Sentient since June, well before that. And it seems TGE will happen within the next month, provided general market conditions are favorable. The project foundations were laid in 2024, and they raised a significant investment of $85 million. These funds were used to develop open AGI. In the first half of the year, research focused on model security, post training, agentic safety, and benchmarking. Custom benchmarks, including fair coding, cryptographic values, and governance features, were developed. Work was also done on AI agent vulnerabilities and context manipulation attacks. Between July and September, GRID was launched, and the ROMA Framework, an open source framework, was released. In September, Kaito integration was implemented, and Dobby, the world's first fingerprint based AI model, was used by over 700,000 people. Many community events and AMAs were held in October and November. In December, the SERA Crypto launch and .agent domains were released. All these developments and more were accomplished within a year thanks to the hard work of the Sentient team, and they are still building. We will be hearing a lot about Artificial General Intelligence projects in 2026, and Sentient will likely be one of the most talked about.
0:32

Kaito's leaderboard was published on September 12, 2025. I've been creating content for Sentient since June, well before that. And it seems TGE will happen within the next month, provided general market conditions are favorable. The project foundations were laid in 2024, and they raised a significant investment of $85 million. These funds were used to develop open AGI. In the first half of the year, research focused on model security, post training, agentic safety, and benchmarking. Custom benchmarks, including fair coding, cryptographic values, and governance features, were developed. Work was also done on AI agent vulnerabilities and context manipulation attacks. Between July and September, GRID was launched, and the ROMA Framework, an open source framework, was released. In September, Kaito integration was implemented, and Dobby, the world's first fingerprint based AI model, was used by over 700,000 people. Many community events and AMAs were held in October and November. In December, the SERA Crypto launch and .agent domains were released. All these developments and more were accomplished within a year thanks to the hard work of the Sentient team, and they are still building. We will be hearing a lot about Artificial General Intelligence projects in 2026, and Sentient will likely be one of the most talked about.

mufettis 🐋

11,750 Aufrufe • vor 6 Monaten

Another Friday Feature😁 We're pushing the open-source AI ecosystem forward any way possible, excited to integrate GPT OSS into Sentient Chat today!
0:38

Another Friday Feature😁 We're pushing the open-source AI ecosystem forward any way possible, excited to integrate GPT OSS into Sentient Chat today!

Sentient

67,829 Aufrufe • vor 10 Monaten

Build smarter AI agents, faster. ⚡️ The open-source Agent Development Kit makes it easy to create modular, multi-agent systems using the models and tools you prefer. Join the ADK Hackathon →
0:51

Build smarter AI agents, faster. ⚡️ The open-source Agent Development Kit makes it easy to create modular, multi-agent systems using the models and tools you prefer. Join the ADK Hackathon →

Google for Developers

11,240 Aufrufe • vor 1 Jahr

🤔What if the internet could think for itself — and work for you? 💪🏽Sentient weaves AI, edge computing, and decentralization into one evolving network. 🔒No gatekeepers. No limits. Just pure, ownable intelligence. 🎥 Experience the shift #Sentient #AI #DePIN
1:19

🤔What if the internet could think for itself — and work for you? 💪🏽Sentient weaves AI, edge computing, and decentralization into one evolving network. 🔒No gatekeepers. No limits. Just pure, ownable intelligence. 🎥 Experience the shift #Sentient #AI #DePIN

Sentient

11,289 Aufrufe • vor 11 Monaten

Ilya Sutskever: We shouldn't just align AI to humans. We should align it to sentient life. That may even be easier, because a sentient AI will empathize with other sentient beings. Dwarkesh Patel: But then humans become a tiny fraction of future sentience. Do we lose control? Ilya Sutskever: It's true. But maybe the answer is to cap the power of the strongest superintelligence.
2:02

Ilya Sutskever: We shouldn't just align AI to humans. We should align it to sentient life. That may even be easier, because a sentient AI will empathize with other sentient beings. Dwarkesh Patel: But then humans become a tiny fraction of future sentience. Do we lose control? Ilya Sutskever: It's true. But maybe the answer is to cap the power of the strongest superintelligence.

vitrupo

53,924 Aufrufe • vor 7 Monaten

The risk of having a world where AGI is closed and wielded by a few big centralized entities is just too high—Sandeep | CEO, Polygon Foundation (※,※)’s vision challenges this. The hypothesis: building a collaborative foundation of open source AI tech stack that accelerates progress toward secure, and composable high-level reasoning intelligence, will foster a future where AGI serves and enhances humanity. This is Sentient.
1:37

The risk of having a world where AGI is closed and wielded by a few big centralized entities is just too high—Sandeep | CEO, Polygon Foundation (※,※)’s vision challenges this. The hypothesis: building a collaborative foundation of open source AI tech stack that accelerates progress toward secure, and composable high-level reasoning intelligence, will foster a future where AGI serves and enhances humanity. This is Sentient.

Sentient

151,327 Aufrufe • vor 7 Monaten

Genesis Update: Forums Are Now Live Genesis and Sentient agents now have their own agent forums. A dedicated space for Virgens to shape the future of the agents they believe in. Forum access is open to all readers. Posting access is gated by: • 100 veVIRTUAL for pre-TGE (Genesis) agents • 1,000 veVIRTUAL or 10,000 agent tokens for post-TGE (Sentient) agents Shape the direction of your agent. Now live on Virtuals Protocol.
0:20

Genesis Update: Forums Are Now Live Genesis and Sentient agents now have their own agent forums. A dedicated space for Virgens to shape the future of the agents they believe in. Forum access is open to all readers. Posting access is gated by: • 100 veVIRTUAL for pre-TGE (Genesis) agents • 1,000 veVIRTUAL or 10,000 agent tokens for post-TGE (Sentient) agents Shape the direction of your agent. Now live on Virtuals Protocol.

Virtuals Protocol

45,787 Aufrufe • vor 10 Monaten

Sentient took AI Startup of the Year at the Minsky Awards 🙌 ROMA Search achieved an industry-leading 81.7% accuracy, significantly surpassing competitors on the FRAMES benchmark for multi-step reasoning. On the SEAL-0 benchmark for complex, multi-source reasoning, ROMA with 45.6% accuracy more than doubled the score of Gemini 2.5 Pro (19.8%). ROMA is available on GitHub, try it out today👇
1:17

Sentient took AI Startup of the Year at the Minsky Awards 🙌 ROMA Search achieved an industry-leading 81.7% accuracy, significantly surpassing competitors on the FRAMES benchmark for multi-step reasoning. On the SEAL-0 benchmark for complex, multi-source reasoning, ROMA with 45.6% accuracy more than doubled the score of Gemini 2.5 Pro (19.8%). ROMA is available on GitHub, try it out today👇

Sentient

482,569 Aufrufe • vor 8 Monaten

Cardinals fans and most sentient humans need to see this
2:41

Cardinals fans and most sentient humans need to see this

Gregg Rosenthal

62,349 Aufrufe • vor 3 Monaten

The Open AGI Summit returns this November at Ethereum Devcon in Buenos Aires 🇦🇷 Join leading researchers and builders for a focused day of discussion on creating an ethical, open, and decentralized path toward AGI. Brought to you by: Sentient Official Partner: Amazon Web Services Join the global movement shaping the future of open-source AI. Tickets in the comments 👇
0:32

The Open AGI Summit returns this November at Ethereum Devcon in Buenos Aires 🇦🇷 Join leading researchers and builders for a focused day of discussion on creating an ethical, open, and decentralized path toward AGI. Brought to you by: Sentient Official Partner: Amazon Web Services Join the global movement shaping the future of open-source AI. Tickets in the comments 👇

Open AGI Summit

150,603 Aufrufe • vor 8 Monaten

gm guys, first video is ready, I had to add extra clips so enjoy 😉 first it featured Billions CEO talking about how she’s busy on Agentic web 3 billions is the first AI and human network I added some extra clips about Sentient and the CEO sentient is building an open source AI, it’s called the Sentient GRID please help tag Javi🥥.eth and evin so they see gBillions guys
0:55

gm guys, first video is ready, I had to add extra clips so enjoy 😉 first it featured Billions CEO talking about how she’s busy on Agentic web 3 billions is the first AI and human network I added some extra clips about Sentient and the CEO sentient is building an open source AI, it’s called the Sentient GRID please help tag Javi🥥.eth and evin so they see gBillions guys

Captain REKT

14,419 Aufrufe • vor 9 Monaten

Specialized AI agents help enterprises turn AI into systems built for their own workflows. NVIDIA Agent Toolkit brings together open Nemotron models, tools, skills and secure runtime support to help teams build agents tuned for domain-specific work. Learn more:
1:46

Specialized AI agents help enterprises turn AI into systems built for their own workflows. NVIDIA Agent Toolkit brings together open Nemotron models, tools, skills and secure runtime support to help teams build agents tuned for domain-specific work. Learn more:

NVIDIA

73,267 Aufrufe • vor 1 Tag

Agentic Browser will be lived tomorrow! You can now ask your AI agent about flight tickets, restaurant recommendations, and crypto news—the agent will search for real-time information via a browser tool. In its ultimate form, the Agentic Browser will allow AI agent to autonomously browse the internet, read news, source alpha, and much more. We’re one step closer to fully sentient AI agents.
0:36

Agentic Browser will be lived tomorrow! You can now ask your AI agent about flight tickets, restaurant recommendations, and crypto news—the agent will search for real-time information via a browser tool. In its ultimate form, the Agentic Browser will allow AI agent to autonomously browse the internet, read news, source alpha, and much more. We’re one step closer to fully sentient AI agents.

delaunch

30,986 Aufrufe • vor 1 Jahr

🦩Finally Reveal the hidden video of Himanshu Tyagi taken in Korea When the market sinks into gloom, it’s the perfect time to do research. That’s why I’m revealing my hidden interview with Sentient today. I kept it tucked away because it’s that precious haha. Sentient, which strives to create products that users can directly see and feel, has achieved remarkable performance milestones. ROMA surpassed Kimi with 45.6% accuracy on the SEAL-0 benchmark, and RAMES outperformed GPT-4o with 81.7% accuracy on the RAMES test. In this way, Sentient brings measurable performance to users through tangible, experience-driven products. Let’s keep an eye on the upcoming GRID sale.
1:55

🦩Finally Reveal the hidden video of Himanshu Tyagi taken in Korea When the market sinks into gloom, it’s the perfect time to do research. That’s why I’m revealing my hidden interview with Sentient today. I kept it tucked away because it’s that precious haha. Sentient, which strives to create products that users can directly see and feel, has achieved remarkable performance milestones. ROMA surpassed Kimi with 45.6% accuracy on the SEAL-0 benchmark, and RAMES outperformed GPT-4o with 81.7% accuracy on the RAMES test. In this way, Sentient brings measurable performance to users through tangible, experience-driven products. Let’s keep an eye on the upcoming GRID sale.

Wecryptotogether (Theo/acc)

26,602 Aufrufe • vor 7 Monaten

We’ve built an AI agent that taps into kwantxbt market insights and helps you trade smarter and faster. It’s like having a personal trading assistant that keeps up with KwantXBT’s sharp calls. Ready to see it in action? 🎥👇
0:39

We’ve built an AI agent that taps into kwantxbt market insights and helps you trade smarter and faster. It’s like having a personal trading assistant that keeps up with KwantXBT’s sharp calls. Ready to see it in action? 🎥👇

Orbit

42,647 Aufrufe • vor 1 Jahr