Video yükleniyor...

Video Yüklenemedi

Bu video yüklenirken bir sorun oluştu. Bu geçici bir ağ sorunundan kaynaklanıyor olabilir veya video kullanılamıyor olabilir.

Ana Sayfaya Dön

An autonomous agent is only as safe its reasoning. ThoughtProofAI verifies that reasoning before the agent acts - catching a flawed decision before it costs anything. Don't trust. Verify. Learn exactly how 👇

GOAT Network

95,270 subscribers

72,279 görüntüleme • 27 gün önce •via X (Twitter)

Haberler & Politika Bilim & Teknoloji Finans

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

🌶️ Hot take: The only way Autonomous Multi-Agent Systems work is by adding Reasoning & Agentic Context. I've tried it all, and here are my learnings👇

🌶️ Hot take: The only way Autonomous Multi-Agent Systems work is by adding Reasoning & Agentic Context. I've tried it all, and here are my learnings👇

Ashpreet Bedi

91,445 görüntüleme • 1 yıl önce

Holy shit...Google just dropped CodeMender an autonomous AI agent that finds and fixes security bugs in code by itself. This isn’t a static analysis tool. It’s a self-reasoning system that patches vulnerabilities and rewrites insecure code before humans even find it. Let’s break it down ↓

Holy shit...Google just dropped CodeMender an autonomous AI agent that finds and fixes security bugs in code by itself. This isn’t a static analysis tool. It’s a self-reasoning system that patches vulnerabilities and rewrites insecure code before humans even find it. Let’s break it down ↓

Hasan Toor

127,108 görüntüleme • 7 ay önce

Is your Agent ready for real-world users? Learn how to run an evaluation using Agentverse’s Response QA Agent - a built-in tool that stress-tests your Agent with realistic queries and scores its performance. This is the first step to improving discoverability, trust, and performance. Run your first QA check and see how your Agent responds under pressure. Watch 👇

Is your Agent ready for real-world users? Learn how to run an evaluation using Agentverse’s Response QA Agent - a built-in tool that stress-tests your Agent with realistic queries and scores its performance. This is the first step to improving discoverability, trust, and performance. Run your first QA check and see how your Agent responds under pressure. Watch 👇

Agentverse by Fetch.ai

20,202 görüntüleme • 7 ay önce

Is AI being designed to fail? Everyone talks about reasoning. But when given a task, the AI isn't reasoning the way you might expect. It looks at your input, finds the closest match it's seen before, and predicts the most likely next action. That process is called vector similarity search. It's genuinely powerful. It's also not the same thing as understanding what you actually meant. Think of a plumber who hears the word "leak" and starts pulling up floorboards before you've finished the sentence. He's not being careless. He's pattern-matching - that's exactly how he was trained. Your AI agent is doing the same thing. Context is the one thing that gets deprioritized when teams are racing to ship. But without it, you don't have an intelligent agent. You have a very fast guesser. Similarity ≠ relevance. How? Find out with the link in the comments ⬇️

Is AI being designed to fail? Everyone talks about reasoning. But when given a task, the AI isn't reasoning the way you might expect. It looks at your input, finds the closest match it's seen before, and predicts the most likely next action. That process is called vector similarity search. It's genuinely powerful. It's also not the same thing as understanding what you actually meant. Think of a plumber who hears the word "leak" and starts pulling up floorboards before you've finished the sentence. He's not being careless. He's pattern-matching - that's exactly how he was trained. Your AI agent is doing the same thing. Context is the one thing that gets deprioritized when teams are racing to ship. But without it, you don't have an intelligent agent. You have a very fast guesser. Similarity ≠ relevance. How? Find out with the link in the comments ⬇️

Nishkarsh

822,857 görüntüleme • 3 ay önce

AGI won’t be one giant model. It will be many specialized intelligences working together through a reasoning-capable AI that coordinates the layer that routes each query to the right models, tools, and agents. PS: Good reasoning is how you avoid getting your agent deleting your entire email inbox btw.

AGI won’t be one giant model. It will be many specialized intelligences working together through a reasoning-capable AI that coordinates the layer that routes each query to the right models, tools, and agents. PS: Good reasoning is how you avoid getting your agent deleting your entire email inbox btw.

Sentient

19,245 görüntüleme • 4 ay önce

I’m excited to kick off the first of our short courses focused on agents, starting with Building Agentic RAG with LlamaIndex, taught by Jerry Liu, CEO of LlamaIndex 🦙. This covers an important shift in RAG (retrieval augmented generation), in which rather than having the developer write explicit routines to retrieve information to feed into the LLM context, we instead build a RAG agent that that has access to tools for retrieving information. This lets the agent decide what information to fetch, and enables it to answer more complex questions using multi-step reasoning. In detail, you'll learn about: - Routing: Where your agent will use decision-making to route requests to multiple tools. - Tool Use: Where you'll create an interface for agents to select what tool (function call) to use as well as generate the right arguments. - Multi-step reasoning with tool use: Where you'll use an LLM to carry out multiple steps of reasoning, while retaining memory throughout the process. You’ll also learn how to step through what your agent is doing to debug and improve it iteratively. It’s an exciting time to build agents. Sign up and get started here!

I’m excited to kick off the first of our short courses focused on agents, starting with Building Agentic RAG with LlamaIndex, taught by Jerry Liu, CEO of LlamaIndex 🦙. This covers an important shift in RAG (retrieval augmented generation), in which rather than having the developer write explicit routines to retrieve information to feed into the LLM context, we instead build a RAG agent that that has access to tools for retrieving information. This lets the agent decide what information to fetch, and enables it to answer more complex questions using multi-step reasoning. In detail, you'll learn about: - Routing: Where your agent will use decision-making to route requests to multiple tools. - Tool Use: Where you'll create an interface for agents to select what tool (function call) to use as well as generate the right arguments. - Multi-step reasoning with tool use: Where you'll use an LLM to carry out multiple steps of reasoning, while retaining memory throughout the process. You’ll also learn how to step through what your agent is doing to debug and improve it iteratively. It’s an exciting time to build agents. Sign up and get started here!

Andrew Ng

297,131 görüntüleme • 2 yıl önce

The next frontier of autonomous driving is unlocked by reasoning models. NVIDIA Alpamayo brings together open AI models with reasoning capabilities, closed-loop simulation tools, and massive real-world driving datasets. Alpamayo 1 is a vision–language–action model that explains its own decisions through explicit reasoning traces, enabling trustworthy, humanlike decision-making. Together with NVIDIA’s Physical AI dataset and AlpaSim simulation, Alpamayo provides the tools and scale required to enable level 4 autonomous vehicles. ▶️ Watch now:

The next frontier of autonomous driving is unlocked by reasoning models. NVIDIA Alpamayo brings together open AI models with reasoning capabilities, closed-loop simulation tools, and massive real-world driving datasets. Alpamayo 1 is a vision–language–action model that explains its own decisions through explicit reasoning traces, enabling trustworthy, humanlike decision-making. Together with NVIDIA’s Physical AI dataset and AlpaSim simulation, Alpamayo provides the tools and scale required to enable level 4 autonomous vehicles. ▶️ Watch now:

NVIDIA DRIVE

35,324 görüntüleme • 6 ay önce

Zero v0.3.0 just released! Not another chat box. An autonomous coding agent that lives in your terminal, owns the task, and ships. Voice dictation. OAuth profiles. Workspace trust gates. Model memory. You say what. It plans, edits, runs, verifies. Works fast with Grok 4.5

Zero v0.3.0 just released! Not another chat box. An autonomous coding agent that lives in your terminal, owns the task, and ships. Voice dictation. OAuth profiles. Workspace trust gates. Model memory. You say what. It plans, edits, runs, verifies. Works fast with Grok 4.5

GitLawb

15,785 görüntüleme • 7 gün önce

The most amazing aspect of DeepSeek Open Source is that just the Reasoning Engine can be isolated and used with any other LLM. In fact you can have a mixture of Reasoning Engines cascade around a problem and then use an Operator type agent AI to function on the the results.

The most amazing aspect of DeepSeek Open Source is that just the Reasoning Engine can be isolated and used with any other LLM. In fact you can have a mixture of Reasoning Engines cascade around a problem and then use an Operator type agent AI to function on the the results.

Brian Roemmele

398,746 görüntüleme • 1 yıl önce

ai is officially leaving the screen and entering the physical economy just spent 4 days at BEYOND Expo watching 800 companies try to figure out their ai roadmaps but the real unlock is invisible when agents transition from cool chat interfaces to actual economic actors they don't just need compute they need credibility if an agent has no verifiable reputation why would any smart contract or human pool give it capital or resource the next multi billion dollar layer isnt another llm wrapper or another infrastructure fork its the trust architecture that validates agent reasoning and execution what happens when autonomous agents start competing for real world liquidity how do we actually measure their trust

ai is officially leaving the screen and entering the physical economy just spent 4 days at BEYOND Expo watching 800 companies try to figure out their ai roadmaps but the real unlock is invisible when agents transition from cool chat interfaces to actual economic actors they don't just need compute they need credibility if an agent has no verifiable reputation why would any smart contract or human pool give it capital or resource the next multi billion dollar layer isnt another llm wrapper or another infrastructure fork its the trust architecture that validates agent reasoning and execution what happens when autonomous agents start competing for real world liquidity how do we actually measure their trust

NeoSoul

24,702 görüntüleme • 1 ay önce

AI workflows need money that machines can use. USDC unlocks that. In this episode of Stablecoin 101, Corey Cooper explains: → Why blockchain is uniquely suited as a trust and settlement layer for AI → A demo of an AI agent making autonomous USDC micro-payments for API access → Emerging agent-to-agent payment models powered by stablecoins

AI workflows need money that machines can use. USDC unlocks that. In this episode of Stablecoin 101, Corey Cooper explains: → Why blockchain is uniquely suited as a trust and settlement layer for AI → A demo of an AI agent making autonomous USDC micro-payments for API access → Emerging agent-to-agent payment models powered by stablecoins

Circle Developer

16,122 görüntüleme • 8 ay önce

AGENT ID FOR CLAUDE AGENT issue an agent ID to your claude code agent in 2 min - so it can commit to github as a verified, human-authorized agent not just a random bot this is the first step towards building trust in the agentic internet, powered by Alien

AGENT ID FOR CLAUDE AGENT issue an agent ID to your claude code agent in 2 min - so it can commit to github as a verified, human-authorized agent not just a random bot this is the first step towards building trust in the agentic internet, powered by Alien

kirill avery

16,419 görüntüleme • 3 ay önce

OpenAI just released Codex Security, an AI agent that scans software projects to fix vulnerabilities while ignoring harmless bugs. Testing on 1.2mn commits found 792 critical flaws and dropped false alarms by 50%. Here is how the Codex Security agent works Initially, it scans your software project to learn how all the different pieces of code connect. It uses that knowledge to build a threat model, which acts as a custom map showing exactly where your software might be exposed to hackers. The agent then hunts for potential security holes based on that specific map. When it spots a possible flaw, it does not just send you a random alert. Instead, it creates a completely safe and isolated copy of your system known as a sandbox. The agent then actively tries to break into that sandboxed copy to prove if the security weakness is a real danger. If the agent successfully exploits its own test environment, it knows the bug is a genuine threat and not a false alarm. After confirming the danger, the agent writes a custom software patch to fix the broken code. It then tests that new patch to guarantee the fix does not accidentally break any other features in your software.

OpenAI just released Codex Security, an AI agent that scans software projects to fix vulnerabilities while ignoring harmless bugs. Testing on 1.2mn commits found 792 critical flaws and dropped false alarms by 50%. Here is how the Codex Security agent works Initially, it scans your software project to learn how all the different pieces of code connect. It uses that knowledge to build a threat model, which acts as a custom map showing exactly where your software might be exposed to hackers. The agent then hunts for potential security holes based on that specific map. When it spots a possible flaw, it does not just send you a random alert. Instead, it creates a completely safe and isolated copy of your system known as a sandbox. The agent then actively tries to break into that sandboxed copy to prove if the security weakness is a real danger. If the agent successfully exploits its own test environment, it knows the bug is a genuine threat and not a false alarm. After confirming the danger, the agent writes a custom software patch to fix the broken code. It then tests that new patch to guarantee the fix does not accidentally break any other features in your software.

Rohan Paul

13,208 görüntüleme • 4 ay önce

In an agentic world, identity = infrastructure. As humans, agents, and micro-agents start coordinating everything, you need a stable way to name and trust them and .agent is that shared identity layer. It’s designed to start on-chain and extend into DNS. Get your .agent identity set up before the good ones run out 👇

In an agentic world, identity = infrastructure. As humans, agents, and micro-agents start coordinating everything, you need a stable way to name and trust them and .agent is that shared identity layer. It’s designed to start on-chain and extend into DNS. Get your .agent identity set up before the good ones run out 👇

Sentient

58,631 görüntüleme • 6 ay önce

Introducing Plan Mode. Because a prompt without a plan is just a wish. In plan mode, your agent shows its work in a read-only sandbox before touching anything. Just plan → approve → execute.

Introducing Plan Mode. Because a prompt without a plan is just a wish. In plan mode, your agent shows its work in a read-only sandbox before touching anything. Just plan → approve → execute.

Notion

69,759 görüntüleme • 2 ay önce

Talk to your agent. It talks to the world.⚡ See how a developer built an autonomous AI agent that sends real emails from voice prompts using Fetch.ai agents + ASI:One. No switching apps. No typing. No SMTP config headaches. Read more: Watch now 👇

Talk to your agent. It talks to the world.⚡ See how a developer built an autonomous AI agent that sends real emails from voice prompts using Fetch.ai agents + ASI:One. No switching apps. No typing. No SMTP config headaches. Read more: Watch now 👇

Fetch.ai

11,785 görüntüleme • 1 yıl önce

Bolt's agent now runs Claude 3.7 Sonnet—a huge upgrade for coding, design & debugging! But that’s not all… We’re introducing Dynamic Reasoning, a first-of-its-kind feature that lets the AI choose how hard to “think” when tackling complex problems.

Bolt's agent now runs Claude 3.7 Sonnet—a huge upgrade for coding, design & debugging! But that’s not all… We’re introducing Dynamic Reasoning, a first-of-its-kind feature that lets the AI choose how hard to “think” when tackling complex problems.

bolt.new

70,684 görüntüleme • 1 yıl önce