Загрузка видео...

Не удалось загрузить видео

Возникла проблема при загрузке этого видео. Это может быть связано с временными проблемами сети или видео может быть недоступно.

На главную

Training an agent isn’t primarily a raw parameter or pre-training on a model problem anymore. It’s a trajectory problem. You need multi-turn traces that show how an agent searches, uses tools, verifies constraints, recovers from dead ends, and eventually commits to an answer. Good traces are surprisingly hard to... show more

ORO

2,460 subscribers

137,330 просмотров • 1 месяц назад •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

People who like sharing agent traces. I've just published all my pi-mono coding agent sessions on Hugging Face so you get to laugh at or pwn me! I suggest you do the same, see thread below. Let's make this a community effort. Here's pi-share-hf: If you are working on tools that help identify PII/sensitive data, get in touch. The better the classification is, the more willing people will be to share their traces.

People who like sharing agent traces. I've just published all my pi-mono coding agent sessions on Hugging Face so you get to laugh at or pwn me! I suggest you do the same, see thread below. Let's make this a community effort. Here's pi-share-hf: If you are working on tools that help identify PII/sensitive data, get in touch. The better the classification is, the more willing people will be to share their traces.

Mario Zechner

57,057 просмотров • 5 месяцев назад

Still following your human intuition to mix corpora from different sources for language model pre-training 🧠? Everyone says that data mixture has a big impact on model performance, but how - and why🕵️? Did you know that web corpora are actually highly impactful for downstream tasks 🏆? Let's check out our preprint "RegMix: Data Mixture as Regression for Language Model Pre-training" 📄 🔬In this paper, we've proposed an automatic data mixture method RegMix that achieves a 6.3% improvement over human selection on the widely used HellaSwag benchmark - and it only needs a 2% extra training FLOPs! 📈 Details in the thread 🧵

Still following your human intuition to mix corpora from different sources for language model pre-training 🧠? Everyone says that data mixture has a big impact on model performance, but how - and why🕵️? Did you know that web corpora are actually highly impactful for downstream tasks 🏆? Let's check out our preprint "RegMix: Data Mixture as Regression for Language Model Pre-training" 📄 🔬In this paper, we've proposed an automatic data mixture method RegMix that achieves a 6.3% improvement over human selection on the widely used HellaSwag benchmark - and it only needs a 2% extra training FLOPs! 📈 Details in the thread 🧵

Qian Liu

54,961 просмотров • 2 лет назад

Here is how simple it is to build a UI front-end for an AI agent (assuming you are using . The video here is 90 seconds and will show you everything you need to connect an agent to a web app: 1. Set up CopilotKit🪁 in your app 1. Copy the agent's localhost URL from LangGraph Studio 2. Paste that URL into a CopilotKit🪁 remote endpoint That's all you need to get a front-end to interact with the agent! The secret sauce here is CoAgents, an open-source library. You can use CoAgents to integrate any agent with your web application. Here is what you get: • Human-in-the-loop to steer and correct the agent • Stream intermediate agent state • Real-time state sharing between the agent and the application • Agentic generative UI to build trust that the agent is on the right path Watch the attached demo so you see it in action.

Here is how simple it is to build a UI front-end for an AI agent (assuming you are using . The video here is 90 seconds and will show you everything you need to connect an agent to a web app: 1. Set up CopilotKit🪁 in your app 1. Copy the agent's localhost URL from LangGraph Studio 2. Paste that URL into a CopilotKit🪁 remote endpoint That's all you need to get a front-end to interact with the agent! The secret sauce here is CoAgents, an open-source library. You can use CoAgents to integrate any agent with your web application. Here is what you get: • Human-in-the-loop to steer and correct the agent • Stream intermediate agent state • Real-time state sharing between the agent and the application • Agentic generative UI to build trust that the agent is on the right path Watch the attached demo so you see it in action.

Santiago

46,142 просмотров • 1 год назад

I wanted to share a quick demo of what we've been working on with our ai agent cloud. This enables fast deployment of agents that have access to a suite of tools, and was designed with agent interoperability in mind. This demo shows how you can go from nothing to an AI twitter agent in a couple minutes. This is what we are using internally to manage deployments, so we will consistently upgrading its capabilities. The next goals are to enable simple TEE deployments for agents, and focus on building out feature for agent interoperability to simplify agent to agent collaboration.

I wanted to share a quick demo of what we've been working on with our ai agent cloud. This enables fast deployment of agents that have access to a suite of tools, and was designed with agent interoperability in mind. This demo shows how you can go from nothing to an AI twitter agent in a couple minutes. This is what we are using internally to manage deployments, so we will consistently upgrading its capabilities. The next goals are to enable simple TEE deployments for agents, and focus on building out feature for agent interoperability to simplify agent to agent collaboration.

Johnny

27,179 просмотров • 1 год назад

New Course: Post-training of LLMs Learn to post-train and customize an LLM in this short course, taught by Banghua Zhu, Assistant Professor at the University of Washington University of Washington, and co-founder of @NexusflowX. Training an LLM to follow instructions or answer questions has two key stages: pre-training and post-training. In pre-training, it learns to predict the next word or token from large amounts of unlabeled text. In post-training, it learns useful behaviors such as following instructions, tool use, and reasoning. Post-training transforms a general-purpose token predictor—trained on trillions of unlabeled text tokens—into an assistant that follows instructions and performs specific tasks. Because it is much cheaper than pre-training, it is practical for many more teams to incorporate post-training methods into their workflows than pre-training. In this course, you’ll learn three common post-training methods—Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and Online Reinforcement Learning (RL)—and how to use each one effectively. With SFT, you train the model on pairs of input and ideal output responses. With DPO, you provide both a preferred (chosen) and a less preferred (rejected) response and train the model to favor the preferred output. With RL, the model generates an output, receives a reward score based on human or automated feedback, and updates the model to improve performance. You’ll learn the basic concepts, common use cases, and principles for curating high-quality data for effective training. Through hands-on labs, you’ll download a pre-trained model from Hugging Face and post-train it using SFT, DPO, and RL to see how each technique shapes model behavior. In detail, you’ll: - Understand what post-training is, when to use it, and how it differs from pre-training. - Build an SFT pipeline to turn a base model into an instruct model. - Explore how DPO reshapes behavior by minimizing contrastive loss—penalizing poor responses and reinforcing preferred ones. - Implement a DPO pipeline to change the identity of a chat assistant. - Learn online RL methods such as Proximal Policy Optimization (PPO) and Group Relative Policy Optimization (GRPO), and how to design reward functions. - Train a model with GRPO to improve its math capabilities using a verifiable reward. Post-training is one of the most rapidly developing areas of LLM training. Whether you’re building a high-accuracy context-specific assistant, fine-tuning a model's tone, or improving task-specific accuracy, this course will give you experience with the most important techniques shaping how LLMs are post-trained today. Please sign up here:

New Course: Post-training of LLMs Learn to post-train and customize an LLM in this short course, taught by Banghua Zhu, Assistant Professor at the University of Washington University of Washington, and co-founder of @NexusflowX. Training an LLM to follow instructions or answer questions has two key stages: pre-training and post-training. In pre-training, it learns to predict the next word or token from large amounts of unlabeled text. In post-training, it learns useful behaviors such as following instructions, tool use, and reasoning. Post-training transforms a general-purpose token predictor—trained on trillions of unlabeled text tokens—into an assistant that follows instructions and performs specific tasks. Because it is much cheaper than pre-training, it is practical for many more teams to incorporate post-training methods into their workflows than pre-training. In this course, you’ll learn three common post-training methods—Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and Online Reinforcement Learning (RL)—and how to use each one effectively. With SFT, you train the model on pairs of input and ideal output responses. With DPO, you provide both a preferred (chosen) and a less preferred (rejected) response and train the model to favor the preferred output. With RL, the model generates an output, receives a reward score based on human or automated feedback, and updates the model to improve performance. You’ll learn the basic concepts, common use cases, and principles for curating high-quality data for effective training. Through hands-on labs, you’ll download a pre-trained model from Hugging Face and post-train it using SFT, DPO, and RL to see how each technique shapes model behavior. In detail, you’ll: - Understand what post-training is, when to use it, and how it differs from pre-training. - Build an SFT pipeline to turn a base model into an instruct model. - Explore how DPO reshapes behavior by minimizing contrastive loss—penalizing poor responses and reinforcing preferred ones. - Implement a DPO pipeline to change the identity of a chat assistant. - Learn online RL methods such as Proximal Policy Optimization (PPO) and Group Relative Policy Optimization (GRPO), and how to design reward functions. - Train a model with GRPO to improve its math capabilities using a verifiable reward. Post-training is one of the most rapidly developing areas of LLM training. Whether you’re building a high-accuracy context-specific assistant, fine-tuning a model's tone, or improving task-specific accuracy, this course will give you experience with the most important techniques shaping how LLMs are post-trained today. Please sign up here:

Andrew Ng

125,146 просмотров • 1 год назад

Here is a step-by-step introduction to building a workflow with a custom AI agent that uses MCP. I explain every component in the video: 1. Building the MCP server 2. Building the agent and an MCP client 3. Building a workflow that uses the agent The goal is simple: Generate a dialogue between two people and make one yell and the other answer with sarcasm. Kestra is sponsoring this video. They are an open-source orchestration platform (repo link below), and I used them to build the workflow that connects every component.

Here is a step-by-step introduction to building a workflow with a custom AI agent that uses MCP. I explain every component in the video: 1. Building the MCP server 2. Building the agent and an MCP client 3. Building a workflow that uses the agent The goal is simple: Generate a dialogue between two people and make one yell and the other answer with sarcasm. Kestra is sponsoring this video. They are an open-source orchestration platform (repo link below), and I used them to build the workflow that connects every component.

Santiago

51,527 просмотров • 1 год назад

Sharing an OS tool I have been building for a few weeks: - git for agent traces. With OT, you have a local client that helps you santise, review and securely share traces from your coding sessions, privately or publicly, as a Hugging Face dataset. 0.3 adds experimental session blame which I am very excited about - attributing commit/PR changes back to the traces that produced them (all local) unlocks a new layer in observability and issue tracking. A few short demos of the local TUI client and the upcoming opentraces hub platform. Try it out! keen on your feedback🙏

Sharing an OS tool I have been building for a few weeks: - git for agent traces. With OT, you have a local client that helps you santise, review and securely share traces from your coding sessions, privately or publicly, as a Hugging Face dataset. 0.3 adds experimental session blame which I am very excited about - attributing commit/PR changes back to the traces that produced them (all local) unlocks a new layer in observability and issue tracking. A few short demos of the local TUI client and the upcoming opentraces hub platform. Try it out! keen on your feedback🙏

Gabriele Farei

10,565 просмотров • 4 месяцев назад

OpenClaw meets RL! OpenClaw Agents adapt through memory files and skills, but the base model weights never actually change. OpenClaw-RL solves this! It wraps a self-hosted model as an OpenAI-compatible API, intercepts live conversations from OpenClaw, and trains the policy in the background using RL. The architecture is fully async. This means serving, reward scoring, and training all run in parallel. Once done, weights get hot-swapped after every batch while the agent keeps responding. Currently, it has two training modes: - Binary RL (GRPO): A process reward model scores each turn as good, bad, or neutral. That scalar reward drives policy updates via a PPO-style clipped objective. - On-Policy Distillation: When concrete corrections come in like "you should have checked that file first," it uses that feedback as a richer, directional training signal at the token level. When to use OpenClaw-RL? To be fair, a lot of agent behavior can already be improved through better memory and skill design. OpenClaw's existing skill ecosystem and community-built self-improvement skills handle a wide range of use cases without touching model weights at all. If the agent keeps forgetting preferences, that's a memory problem. And if it doesn't know how to handle a specific workflow, that's a skill problem. Both are solvable at the prompt and context layer. Where RL becomes interesting is when the failure pattern lives deeper in the model's reasoning itself. Things like consistently poor tool selection order, weak multi-step planning, or failing to interpret ambiguous instructions the way a specific user intends. Research on agentic RL (like ARTIST and Agent-R1) has shown that these behavioral patterns hit a ceiling with prompt-based approaches alone, especially in complex multi-turn tasks where the model needs to recover from tool failures or adapt its strategy mid-execution. That's the layer OpenClaw-RL targets, and it's a meaningful distinction from what OpenClaw offers. I have shared the repo in the replies!

OpenClaw meets RL! OpenClaw Agents adapt through memory files and skills, but the base model weights never actually change. OpenClaw-RL solves this! It wraps a self-hosted model as an OpenAI-compatible API, intercepts live conversations from OpenClaw, and trains the policy in the background using RL. The architecture is fully async. This means serving, reward scoring, and training all run in parallel. Once done, weights get hot-swapped after every batch while the agent keeps responding. Currently, it has two training modes: - Binary RL (GRPO): A process reward model scores each turn as good, bad, or neutral. That scalar reward drives policy updates via a PPO-style clipped objective. - On-Policy Distillation: When concrete corrections come in like "you should have checked that file first," it uses that feedback as a richer, directional training signal at the token level. When to use OpenClaw-RL? To be fair, a lot of agent behavior can already be improved through better memory and skill design. OpenClaw's existing skill ecosystem and community-built self-improvement skills handle a wide range of use cases without touching model weights at all. If the agent keeps forgetting preferences, that's a memory problem. And if it doesn't know how to handle a specific workflow, that's a skill problem. Both are solvable at the prompt and context layer. Where RL becomes interesting is when the failure pattern lives deeper in the model's reasoning itself. Things like consistently poor tool selection order, weak multi-step planning, or failing to interpret ambiguous instructions the way a specific user intends. Research on agentic RL (like ARTIST and Agent-R1) has shown that these behavioral patterns hit a ceiling with prompt-based approaches alone, especially in complex multi-turn tasks where the model needs to recover from tool failures or adapt its strategy mid-execution. That's the layer OpenClaw-RL targets, and it's a meaningful distinction from what OpenClaw offers. I have shared the repo in the replies!

Avi Chawla

138,769 просмотров • 6 месяцев назад

At first, ICE didn’t want to talk. This may be the only video of a real conversation with an ICE agent. After following them from an elementary school where they’d been circling to a parking lot, I was able to get a few words in. This is part of that conversation. As you’ll see, in a genuine conversation, even this ICE agent understands that they must be accountable. And when I’m elected to congress, we will hold ICE accountable- every agent who abused their authority, pepper sprayed kids, or illegally broke into someone’s home. But until November, we have to use our voice in whatever ways we can. Protest. Make noise. Talk to your friends and neighbors. Support your community. And if you get the chance at a safe distance- even talk to an ICE agent– and make it clear that if they want things to change, they must be part of that change. This is how we get ICE out of Minnesota.

At first, ICE didn’t want to talk. This may be the only video of a real conversation with an ICE agent. After following them from an elementary school where they’d been circling to a parking lot, I was able to get a few words in. This is part of that conversation. As you’ll see, in a genuine conversation, even this ICE agent understands that they must be accountable. And when I’m elected to congress, we will hold ICE accountable- every agent who abused their authority, pepper sprayed kids, or illegally broke into someone’s home. But until November, we have to use our voice in whatever ways we can. Protest. Make noise. Talk to your friends and neighbors. Support your community. And if you get the chance at a safe distance- even talk to an ICE agent– and make it clear that if they want things to change, they must be part of that change. This is how we get ICE out of Minnesota.

Matt Little

63,285 просмотров • 7 месяцев назад

Is your job actually safe from AI? I’ve been thinking about this a lot. To get some real answers, I'm using Frank AI Researcher to let you talk to an AI agent yourself. It takes 5 minutes. You tell the agent what you do every day and what tech you use. Then, it gives you a "future-proof score" to show how much of your work can be automated right now. I really want to see what you guys find out. Link to talk to the agent:👇

Is your job actually safe from AI? I’ve been thinking about this a lot. To get some real answers, I'm using Frank AI Researcher to let you talk to an AI agent yourself. It takes 5 minutes. You tell the agent what you do every day and what tech you use. Then, it gives you a "future-proof score" to show how much of your work can be automated right now. I really want to see what you guys find out. Link to talk to the agent:👇

AI Panda

70,835 просмотров • 5 месяцев назад

At DevCon 6, See how Palantir Group Lead Christopher Jeganathan uses AIP Inspect and Agent Timeline to turn raw agent telemetry into a readable narrative automatically: "Most platforms will give you raw telemetry and expect you to drink from the firehose, but we want to give you a way in which you can derive value from your telemetry." "We're not adding logs ourselves. We're not asking you to think about how you're going to monitor this in the future." "The use of our platform gets you to these outcomes sooner." "There's no homework for you. This telemetry is generated by every agent."

At DevCon 6, See how Palantir Group Lead Christopher Jeganathan uses AIP Inspect and Agent Timeline to turn raw agent telemetry into a readable narrative automatically: "Most platforms will give you raw telemetry and expect you to drink from the firehose, but we want to give you a way in which you can derive value from your telemetry." "We're not adding logs ourselves. We're not asking you to think about how you're going to monitor this in the future." "The use of our platform gets you to these outcomes sooner." "There's no homework for you. This telemetry is generated by every agent."

Palantir

46,123 просмотров • 1 месяц назад

“How complex are agents on Surprisingly simple. You can create a personal agent in under a minute. Name it. Teach it your preferences. Set budgets, brands, tone, and how you want it to behave. Not 10,000 search results, just what you’d actually buy. The power comes from connected agents: your agent ↔ friends’ agents ↔ businesses’ agents. And this isn’t future talk. It’s live today on

“How complex are agents on Surprisingly simple. You can create a personal agent in under a minute. Name it. Teach it your preferences. Set budgets, brands, tone, and how you want it to behave. Not 10,000 search results, just what you’d actually buy. The power comes from connected agents: your agent ↔ friends’ agents ↔ businesses’ agents. And this isn’t future talk. It’s live today on

Fetch.ai

14,865 просмотров • 8 месяцев назад

An LLM with native access to find and run agents is a huge thing! This large language model (called ASI:One and developed by Fetch.ai) can do this natively when you show it a problem: • Reason about the problem • Identify live agents and tools that can help solve it • Dynamically invoke these agents and tools Honestly, this is pretty nuts! You don't need to set up anything beforehand. You don't need to write any code. Here is the best part: ASI:One has access to any agent published on Agentverse, an open directory of agents! This gives the model access to *millions* of tools it can execute dynamically when solving a task. Here is a simple example (the one in the attached video): • I went to Google Maps • I copied the latitude and longitude of a location • I asked ASI:One about relevant places around that location • ASI:One went to the marketplace • It identified and called the Google Places agent • It returned a list of museums, restaurants, and landmarks near my location Pretty awesome! You can try this now by going to You don't need to pay or register to test it out. If you want to get ideas of what's possible, check Agentverse, the agent marketplace: The model will have access to all of those tools. This is pretty awesome and opens up a whole new world of possibilities! Thanks to the team for partnering with me on this post!

An LLM with native access to find and run agents is a huge thing! This large language model (called ASI:One and developed by Fetch.ai) can do this natively when you show it a problem: • Reason about the problem • Identify live agents and tools that can help solve it • Dynamically invoke these agents and tools Honestly, this is pretty nuts! You don't need to set up anything beforehand. You don't need to write any code. Here is the best part: ASI:One has access to any agent published on Agentverse, an open directory of agents! This gives the model access to millions of tools it can execute dynamically when solving a task. Here is a simple example (the one in the attached video): • I went to Google Maps • I copied the latitude and longitude of a location • I asked ASI:One about relevant places around that location • ASI:One went to the marketplace • It identified and called the Google Places agent • It returned a list of museums, restaurants, and landmarks near my location Pretty awesome! You can try this now by going to You don't need to pay or register to test it out. If you want to get ideas of what's possible, check Agentverse, the agent marketplace: The model will have access to all of those tools. This is pretty awesome and opens up a whole new world of possibilities! Thanks to the team for partnering with me on this post!

Santiago

43,784 просмотров • 1 год назад

This agent relies on a marketplace of 2.8M+ specialized agents to complete a task. This is how I imagine the future of personal agents. Here is how this works: 1. Agentverse is a marketplace of agents 2. Anyone can build and publish an agent there 3. ASI:One is a personal agent with access to the marketplace 4. To solve a task, ASI:One finds the best agent for the job In other words: You have an agent that can solve pretty much *anything* because it knows how to outsource the work to a network of specialized agents. And you don't need to do any setup to get this working. The way ranking agents in the marketplace works is pretty cool: Fetch.ai, the company behind it, created an AgentRank algorithm that works much like Google's PageRank. Every time an agent calls another, it forms a connection. Over time, these connections build into a graph of who relies on whom. An agent that is frequently called by other reputable agents scores higher and surfaces higher in results. The end result here is that your agent will consistently use the best agents in the marketplace to accomplish a goal. You should give this a try: You don't need to pay or even register to try these agents. Thanks to the team for partnering with me on this post.

This agent relies on a marketplace of 2.8M+ specialized agents to complete a task. This is how I imagine the future of personal agents. Here is how this works: 1. Agentverse is a marketplace of agents 2. Anyone can build and publish an agent there 3. ASI:One is a personal agent with access to the marketplace 4. To solve a task, ASI:One finds the best agent for the job In other words: You have an agent that can solve pretty much anything because it knows how to outsource the work to a network of specialized agents. And you don't need to do any setup to get this working. The way ranking agents in the marketplace works is pretty cool: Fetch.ai, the company behind it, created an AgentRank algorithm that works much like Google's PageRank. Every time an agent calls another, it forms a connection. Over time, these connections build into a graph of who relies on whom. An agent that is frequently called by other reputable agents scores higher and surfaces higher in results. The end result here is that your agent will consistently use the best agents in the marketplace to accomplish a goal. You should give this a try: You don't need to pay or even register to try these agents. Thanks to the team for partnering with me on this post.

Santiago

18,715 просмотров • 2 месяцев назад

here's a hands on guide to setup multi-agent autoresearch by Andrej Karpathy. uses open models. works with codex, claude, open code. - uses 5 agents each with a configuration, specific tools, roles, and permission (see repo) - a researcher agent searches papers on hf papers and creates hypotheses - a planner agent maintains an experiment plan and log - workers take the hypotheses and updates the scripts, then it starts a hf job with a gpu to run the script - a reporter agent monitors these jobs and reports events and metrics to a TrackioApp dashboard I ran this for 4 hours and the agents ran 32 jobs, they improved on the baseline by a small margin. check out everything I learnt in thread.

here's a hands on guide to setup multi-agent autoresearch by Andrej Karpathy. uses open models. works with codex, claude, open code. - uses 5 agents each with a configuration, specific tools, roles, and permission (see repo) - a researcher agent searches papers on hf papers and creates hypotheses - a planner agent maintains an experiment plan and log - workers take the hypotheses and updates the scripts, then it starts a hf job with a gpu to run the script - a reporter agent monitors these jobs and reports events and metrics to a TrackioApp dashboard I ran this for 4 hours and the agents ran 32 jobs, they improved on the baseline by a small margin. check out everything I learnt in thread.

Ben Burtenshaw

90,760 просмотров • 4 месяцев назад

Right now, I have a few dozen tools to automate my life. Every single thing that I do more than once every week is now a tool: either a Claude Code skill, a scheduled workflow, or an application. • I spend the time doing this once. • I schedule it. • I forget about it (or at least, try to) CREAO is one of the platforms I've used extensively for building some of these automations. They are partnering with me on this post. They are one of the only platforms where you can go from a conversation to a scheduled agent that quickly. This is how it works: 1. You describe the problem you want to solve 2. CREAO's agent builds the logic and executes it 3. You can iterate with the agent to improve the solution 4. When you are done, you turn that solution into a mini app 5. You can schedule that app to run any time you need it Something important: These agents are deterministic. They don't use an LLM to generate answers, so they will always return the same output given the same input. This is critical: when you're automating something that runs every Monday at 9 am, you need it to return the same result every time, not a "creative" answer.

Right now, I have a few dozen tools to automate my life. Every single thing that I do more than once every week is now a tool: either a Claude Code skill, a scheduled workflow, or an application. • I spend the time doing this once. • I schedule it. • I forget about it (or at least, try to) CREAO is one of the platforms I've used extensively for building some of these automations. They are partnering with me on this post. They are one of the only platforms where you can go from a conversation to a scheduled agent that quickly. This is how it works: 1. You describe the problem you want to solve 2. CREAO's agent builds the logic and executes it 3. You can iterate with the agent to improve the solution 4. When you are done, you turn that solution into a mini app 5. You can schedule that app to run any time you need it Something important: These agents are deterministic. They don't use an LLM to generate answers, so they will always return the same output given the same input. This is critical: when you're automating something that runs every Monday at 9 am, you need it to return the same result every time, not a "creative" answer.

Santiago

13,727 просмотров • 5 месяцев назад