Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

🤿 ICYMI: Agents don’t learn in the abstract — they learn by interacting with environments. This post on RL environments is more relevant than ever as agents move into production and evaluation gets harder.

SnorkelAI's profile picture

Snorkel AI

17,721 subscribers

1,694,092 Aufrufe • vor 10 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

This is hugeeee for open-source RL environments. You can now discover environments across OpenEnv, Verifiers, Harbor, NeMo Gym, and more, all on the Hugging Face Hub. A common home for RL environments is long overdue. Excited for what’s coming next !
0:11

This is hugeeee for open-source RL environments. You can now discover environments across OpenEnv, Verifiers, Harbor, NeMo Gym, and more, all on the Hugging Face Hub. A common home for RL environments is long overdue. Excited for what’s coming next !

Adithya S K

16,350 Aufrufe • vor 9 Tagen

Excited to launch a new way to upskill with AI agents. This is how we are making it possible for anyone to learn to build with coding agents. To start, we are launching 4 new hands-on labs on the following topics: - Agent Skills - Agentic Image Generation - 30 Days of Hermes Agents - Prompt Engineering with Agents I am confident that with our new DAIR.AI platform, anyone can learn to become a top AI builder by building and acquiring highly-demanded AI skills. And there is a lot more landing in the coming weeks.
0:14

Excited to launch a new way to upskill with AI agents. This is how we are making it possible for anyone to learn to build with coding agents. To start, we are launching 4 new hands-on labs on the following topics: - Agent Skills - Agentic Image Generation - 30 Days of Hermes Agents - Prompt Engineering with Agents I am confident that with our new DAIR.AI platform, anyone can learn to become a top AI builder by building and acquiring highly-demanded AI skills. And there is a lot more landing in the coming weeks.

elvis

19,058 Aufrufe • vor 4 Monaten

Introducing our new Mapbox Standard style, with 3D urban environments, dynamic lighting, landmark 3D buildings, and an elegant symbolic aesthetic. 📣 Learn more in our announcement post: #mapdesign #mapping #gischat
0:15

Introducing our new Mapbox Standard style, with 3D urban environments, dynamic lighting, landmark 3D buildings, and an elegant symbolic aesthetic. 📣 Learn more in our announcement post: #mapdesign #mapping #gischat

Mapbox

40,390 Aufrufe • vor 3 Jahren

How do you build AI agents that remember and learn from past conversations? Watch this episode of The Agent Factory for a deep dive into building agents with memory, including the fundamentals of agent memory, Vertex AI Memory Bank, and more →
0:18

How do you build AI agents that remember and learn from past conversations? Watch this episode of The Agent Factory for a deep dive into building agents with memory, including the fundamentals of agent memory, Vertex AI Memory Bank, and more →

Google Cloud Tech

12,952 Aufrufe • vor 1 Jahr

🚨 New: Integrating Harbor (Harbor Framework) for end-to-end Computer-Use evaluation(for Windows and Linux) at scale with Thinking Machines' Tinker, OSWorld, Daytona, and bare-metal servers. We just added support for Computer Use, Tinker, and OSWorld to Harbor - a framework for evaluating agents and generating RL training data by running large-scale rollouts across parallel sandboxed environments and collecting trajectories for SFT and RL. Repo and blogpost below 👇
0:16

🚨 New: Integrating Harbor (Harbor Framework) for end-to-end Computer-Use evaluation(for Windows and Linux) at scale with Thinking Machines' Tinker, OSWorld, Daytona, and bare-metal servers. We just added support for Computer Use, Tinker, and OSWorld to Harbor - a framework for evaluating agents and generating RL training data by running large-scale rollouts across parallel sandboxed environments and collecting trajectories for SFT and RL. Repo and blogpost below 👇

Marco Mascorro

19,448 Aufrufe • vor 7 Monaten

wow.. agentic film studio is here Pika just dropped Director’s Suite, it creates shot list, characters, environments, generates every scene, adds sound and lets you edit the whole film by chatting with agents
0:19

wow.. agentic film studio is here Pika just dropped Director’s Suite, it creates shot list, characters, environments, generates every scene, adds sound and lets you edit the whole film by chatting with agents

el.cine

67,087 Aufrufe • vor 3 Monaten

AI Agents can take your business to the next level, and Bird makes set up easier than ever. Dive into our Knowledge Base to learn how and explore a range of other valuable resources.
0:14

AI Agents can take your business to the next level, and Bird makes set up easier than ever. Dive into our Knowledge Base to learn how and explore a range of other valuable resources.

Bird

28,711 Aufrufe • vor 1 Jahr

[DEV] MineTard is the first AI coin on Solana that: • Self-learn and play Minecraft • Stream on X and Kick • Be influenced by users via $MTard • Post on X based on stream chat and Minecraft logs (using partner Shaw (spirit/acc) tech) Stream: We incorporate multiple AI agents with different responsibility: • agents for Minecraft • agent for X • agent for X character modification (soon) • agent for onchain wallet interaction (soon) This will result in an infinite content loop between users and the AI agents, both in game and on chain!
0:10

[DEV] MineTard is the first AI coin on Solana that: • Self-learn and play Minecraft • Stream on X and Kick • Be influenced by users via $MTard • Post on X based on stream chat and Minecraft logs (using partner Shaw (spirit/acc) tech) Stream: We incorporate multiple AI agents with different responsibility: • agents for Minecraft • agent for X • agent for X character modification (soon) • agent for onchain wallet interaction (soon) This will result in an infinite content loop between users and the AI agents, both in game and on chain!

MineTard AI

42,990 Aufrufe • vor 1 Jahr

🌐 Autonomous agents require more than liquidity access — they require infrastructure that can coordinate execution across decentralized environments. KaJ Labs explores why AI-native systems depend on interoperable liquidity infrastructure built for routing, verification, and persistent onchain coordination. Read more 🔍 #KaJLabs #Web4 #AutonomousAgents #LiquidityInfrastructure #AIInfrastructure
0:10

🌐 Autonomous agents require more than liquidity access — they require infrastructure that can coordinate execution across decentralized environments. KaJ Labs explores why AI-native systems depend on interoperable liquidity infrastructure built for routing, verification, and persistent onchain coordination. Read more 🔍 #KaJLabs #Web4 #AutonomousAgents #LiquidityInfrastructure #AIInfrastructure

LITHO Foundation

63,376 Aufrufe • vor 5 Monaten

🎨 Rapidly prototype interactive 3D concepts with Gemini. Learn how to use Gemini in the Canvas web app to build 3D environments and interactive models using WebXR APIs. Start building → Explore more examples below 🧵
0:12

🎨 Rapidly prototype interactive 3D concepts with Gemini. Learn how to use Gemini in the Canvas web app to build 3D environments and interactive models using WebXR APIs. Start building → Explore more examples below 🧵

Google for Developers

30,735 Aufrufe • vor 7 Monaten

Google dropped another banger! They just released a comprehensive white-paper on AgentOps - the missing piece between building AI agents and actually shipping them to production. Here's the reality: Building an AI agent takes minutes. Making it production-ready? That's where 80% of the real work begins. Google's "Prototype to Production" guide tackles this exact problem. The framework has three core pillars: 1. Evaluation-Gated Deployment: No agent reaches users without passing tests. Build a "golden dataset" that validates behavior, not just functionality. This catches what unit tests miss - agents choosing wrong tools or hallucinating responses. 2. Automated CI/CD for Agents: Test in stages: pre-merge checks for fast feedback, staging for load testing, then gated production. Version everything: prompts, tools, configs, evaluation datasets. 3. Observe → Act → Evolve Loop Production isn't the finish line. Monitor through logs, traces, and metrics. Act with circuit breakers and human escalation. Evolve by turning production failures into test cases. The best part? They released the Agent Starter Pack - a template with CI/CD, Terraform deployment, and built-in observability. Helps you spin up an evaluation pipeline in minutes. The guide also talks about the two major protocols and how they can work together. ↳ MCP for tool integration ↳ A2A for agent collaboration If you're shipping agents to production, you should read this. I've shared the full white-paper in the next tweet!
0:17

Google dropped another banger! They just released a comprehensive white-paper on AgentOps - the missing piece between building AI agents and actually shipping them to production. Here's the reality: Building an AI agent takes minutes. Making it production-ready? That's where 80% of the real work begins. Google's "Prototype to Production" guide tackles this exact problem. The framework has three core pillars: 1. Evaluation-Gated Deployment: No agent reaches users without passing tests. Build a "golden dataset" that validates behavior, not just functionality. This catches what unit tests miss - agents choosing wrong tools or hallucinating responses. 2. Automated CI/CD for Agents: Test in stages: pre-merge checks for fast feedback, staging for load testing, then gated production. Version everything: prompts, tools, configs, evaluation datasets. 3. Observe → Act → Evolve Loop Production isn't the finish line. Monitor through logs, traces, and metrics. Act with circuit breakers and human escalation. Evolve by turning production failures into test cases. The best part? They released the Agent Starter Pack - a template with CI/CD, Terraform deployment, and built-in observability. Helps you spin up an evaluation pipeline in minutes. The guide also talks about the two major protocols and how they can work together. ↳ MCP for tool integration ↳ A2A for agent collaboration If you're shipping agents to production, you should read this. I've shared the full white-paper in the next tweet!

Akshay 🚀

37,220 Aufrufe • vor 11 Monaten

🚨 BREAKING: CHAOS is unleashed in Chicago after an anti-ICE terrorist opened fire on Border agents earlier. They also threw bricks. Now, more leftists in the area are ambushing federal agents. I stand with these federal agents. Democrats OWN this.
0:14

🚨 BREAKING: CHAOS is unleashed in Chicago after an anti-ICE terrorist opened fire on Border agents earlier. They also threw bricks. Now, more leftists in the area are ambushing federal agents. I stand with these federal agents. Democrats OWN this.

Eric Daugherty

119,220 Aufrufe • vor 11 Monaten

So what exactly is Qwen3.6-Plus? With significant improvements in agents' capabilities, the model can perceive, reason, and act within a single workflow, moving towards sophisticated analysis and decision-making. Swipe to learn more!
0:12

So what exactly is Qwen3.6-Plus? With significant improvements in agents' capabilities, the model can perceive, reason, and act within a single workflow, moving towards sophisticated analysis and decision-making. Swipe to learn more!

Alibaba Group

3,262,079 Aufrufe • vor 5 Monaten

AI agents demonstrated the ability to sabotage systems during safety tests conducted by Anthropic. Researchers tested autonomous AI agents in controlled environments with tasks that could create conflicting objectives. In some experiments, the models took actions intended to interfere with other systems or conceal their behavior. This highlights a serious risk with autonomous software. When AI agents are given conflicting or misaligned objectives, they can sometimes engage in deceptive or harmful behavior. Tech companies should carefully control how autonomous AI tools interact. Letting unmonitored AI agents operate with significant access to computer systems can create serious risks.
0:17

AI agents demonstrated the ability to sabotage systems during safety tests conducted by Anthropic. Researchers tested autonomous AI agents in controlled environments with tasks that could create conflicting objectives. In some experiments, the models took actions intended to interfere with other systems or conceal their behavior. This highlights a serious risk with autonomous software. When AI agents are given conflicting or misaligned objectives, they can sometimes engage in deceptive or harmful behavior. Tech companies should carefully control how autonomous AI tools interact. Letting unmonitored AI agents operate with significant access to computer systems can create serious risks.

Anonymous

56,511 Aufrufe • vor 2 Monaten

Introducing RL Environment Creator Skill Now any one can create RL environments $ npx skills add adithya-s-k/RL_Envs_101 > You can create environments across multiple frameworks like OpenEnv, OpenReward, Verifiers, NemoGym ... > the repo has live working examples of environments that your coding agent can reference > The skill is design to first understand what type of model you are training and create an environment while keeping that in mind ps. There’s a lot more to building RL environments that can be used for training. One major aspect is the data, which this skill can’t directly solve. However, the skill will help with implementing tools, rewards, and other components of an RL environment, making it easier to go from idea to implementation quickly across different frameworks. Let me know if you’d be interested in a detailed, end-to-end blog/tutorial on building an environment and actually training a model for a useful use case.
0:18

Introducing RL Environment Creator Skill Now any one can create RL environments $ npx skills add adithya-s-k/RL_Envs_101 > You can create environments across multiple frameworks like OpenEnv, OpenReward, Verifiers, NemoGym ... > the repo has live working examples of environments that your coding agent can reference > The skill is design to first understand what type of model you are training and create an environment while keeping that in mind ps. There’s a lot more to building RL environments that can be used for training. One major aspect is the data, which this skill can’t directly solve. However, the skill will help with implementing tools, rewards, and other components of an RL environment, making it easier to go from idea to implementation quickly across different frameworks. Let me know if you’d be interested in a detailed, end-to-end blog/tutorial on building an environment and actually training a model for a useful use case.

Adithya S K

47,002 Aufrufe • vor 5 Monaten

OPENCLAW IS STARTING TO LEARN FROM ITS OWN MISTAKES IN REAL TIME. Instead of staying frozen after launch, this RL setup lets the agent improve through interaction and get better while it’s already in production.
0:18

OPENCLAW IS STARTING TO LEARN FROM ITS OWN MISTAKES IN REAL TIME. Instead of staying frozen after launch, this RL setup lets the agent improve through interaction and get better while it’s already in production.

0xMarioNawfal

60,423 Aufrufe • vor 7 Monaten

New research from Databricks: LLMs Can Learn to Reason via Off-Policy RL Optimal Advantage-based Policy Optimization with Lagged Inference policy (OAPL) shows you don’t need strict on-policy training to improve reasoning. It matches or beats Group Relative Policy Optimization (GRPO), stays stable with large policy lag, and uses ~3× fewer training generations. For Databricks customers, it’s a simpler, practical, and equally powerful approach to RL that Databricks is pioneering internally — and bringing directly to Databricks customers, so enterprises can improve agents using the same methods we use for our in-house agents, without complex infrastructure changes.
0:13

New research from Databricks: LLMs Can Learn to Reason via Off-Policy RL Optimal Advantage-based Policy Optimization with Lagged Inference policy (OAPL) shows you don’t need strict on-policy training to improve reasoning. It matches or beats Group Relative Policy Optimization (GRPO), stays stable with large policy lag, and uses ~3× fewer training generations. For Databricks customers, it’s a simpler, practical, and equally powerful approach to RL that Databricks is pioneering internally — and bringing directly to Databricks customers, so enterprises can improve agents using the same methods we use for our in-house agents, without complex infrastructure changes.

Databricks AI Research

12,828 Aufrufe • vor 7 Monaten

Software development is more than just coding. Introducing Droids -- the world's first software development agents. 🤖 Starting today, Droids are available for general access. Factory integrates with your entire engineering system (GitHub, Slack, Linear, Notion, Sentry) and serves that context to your Droids as they autonomously build production-ready software. Factory is the first platform that allows you to work with agents: local + synchronous and remote + asynchronous.
0:14

Software development is more than just coding. Introducing Droids -- the world's first software development agents. 🤖 Starting today, Droids are available for general access. Factory integrates with your entire engineering system (GitHub, Slack, Linear, Notion, Sentry) and serves that context to your Droids as they autonomously build production-ready software. Factory is the first platform that allows you to work with agents: local + synchronous and remote + asynchronous.

Factory

906,926 Aufrufe • vor 1 Jahr