正在加载视频...

视频加载失败

返回首页

We aren't ready for this next generation of agentic engineers. 100k Github stars in 24 hours (claw-code), Yeachan Heo (Bellman) has 3 to 5 pro accounts and ships software from telegram and discord. Those who accuse these guys of AI slop haven't done their homework because the real story...

RayFernando1337's profile picture

Ray Fernando

37,081 subscribers

59,092 次观看 • 3 个月前 •via X (Twitter)

教育新闻政治科学技术
LIVE

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Chief Strategy Officer at Circle (Circle $CRCL) Dante Disparte (Dante Disparte) says stablecoins will play a critical role in the developing agentic economy: "The next big frontier breakthrough for stablecoins is going to be agentic commerce and economic activity." "At [the] core it's software, and software will invariably speak to software..." "We ran the world's first AI-led, AI-judged, and AI-only hackathon with Claude bots last month". "Once the agents literally got going, there was an economic flywheel of activity. The agents competed like they would in a traditional hackathon and the best idea won and the entire economy of this project was paid for in USDC."
1:30

Chief Strategy Officer at Circle (Circle $CRCL) Dante Disparte (Dante Disparte) says stablecoins will play a critical role in the developing agentic economy: "The next big frontier breakthrough for stablecoins is going to be agentic commerce and economic activity." "At [the] core it's software, and software will invariably speak to software..." "We ran the world's first AI-led, AI-judged, and AI-only hackathon with Claude bots last month". "Once the agents literally got going, there was an economic flywheel of activity. The agents competed like they would in a traditional hackathon and the best idea won and the entire economy of this project was paid for in USDC."

etn.

11,791 次观看 • 4 个月前

This is crazy, I can talk to OpenAI's realtime API, and it'll respond back with voice, and then help call Codex to help me code! Got curious about Codex and its realtime integration, and found codex's feature flag `realtime_conversation` integrated for the codex app-server. How it works: - launch codex app-server with realtime - connect a client to realtime through WebRTC voice connection - Codex app-server is also attached on the side - talk to realtime - realtime decides whether coding is needed, and responds back with events - Codex app-server takes these events and runs codex agent turns - codex writes code like your codex cli exp Keep in mind OpenAI hasn't released this officially, they're still actively working on it, I just created a fork. This is a completely new UX than the usual chat interface for agentic coding. For example, when the agent responds back in voice, it's actually faster for me to read the response, and I don't actually find voice response that useful unless it does so in the background. But image realtime working in the background, you can talk to it, realtime keeps track of the different agents working on your tasks and your status. More to come on demo side, i'll make a more polished version and include voice, but thought this was cool to share. You can see in the responses the distinction between my voice input, realtime response, and realtime calling Codex to do work!
0:28

This is crazy, I can talk to OpenAI's realtime API, and it'll respond back with voice, and then help call Codex to help me code! Got curious about Codex and its realtime integration, and found codex's feature flag `realtime_conversation` integrated for the codex app-server. How it works: - launch codex app-server with realtime - connect a client to realtime through WebRTC voice connection - Codex app-server is also attached on the side - talk to realtime - realtime decides whether coding is needed, and responds back with events - Codex app-server takes these events and runs codex agent turns - codex writes code like your codex cli exp Keep in mind OpenAI hasn't released this officially, they're still actively working on it, I just created a fork. This is a completely new UX than the usual chat interface for agentic coding. For example, when the agent responds back in voice, it's actually faster for me to read the response, and I don't actually find voice response that useful unless it does so in the background. But image realtime working in the background, you can talk to it, realtime keeps track of the different agents working on your tasks and your status. More to come on demo side, i'll make a more polished version and include voice, but thought this was cool to share. You can see in the responses the distinction between my voice input, realtime response, and realtime calling Codex to do work!

Matthew Lam

17,674 次观看 • 2 个月前

Claude Code + Composio Plugin -> DevOps Automation Our engineering team regularly uses Claude Code for: - Fetching logs from Datadog and ClickHouse - Analyzing failures and fixing the codebase - Creating and updating Linear tickets but setting up and configuring each of these mcp servers takes hours We made a connect-apps plugin that uses Composio for instant connection to 500+ apps, enabling you to start using them in minutes. link to the plugin below:
0:59

Claude Code + Composio Plugin -> DevOps Automation Our engineering team regularly uses Claude Code for: - Fetching logs from Datadog and ClickHouse - Analyzing failures and fixing the codebase - Creating and updating Linear tickets but setting up and configuring each of these mcp servers takes hours We made a connect-apps plugin that uses Composio for instant connection to 500+ apps, enabling you to start using them in minutes. link to the plugin below:

Karan Vaidya

207,872 次观看 • 6 个月前

Three skills I use every day in Claude Code and Codex to solve my hardest problems: 1️⃣ /agent-watchdog When I have one agent like Codex working on a task and I don't fully trust it's going to do everything right, I'll open up another one like Claude Code and tell it to watchdog the Codex thread. You can copy the Codex deep link into Claude Code and it'll look at the prompt you sent, watch the Codex thread until it's done, then compare the Codex solution to how it was planning to solve it and automatically fix anything that Codex missed. It can also test the work of the other agent end-to-end. Similar to the idea of OpenRouter's new Fusion feature, I've definitely found that two models thinking through a problem and checking each other's work can be wildly more impactful than just one. 2️⃣ /plan-arbiter Similar ideas as /agent-watchdog - but with this one you have both make plans, compare plans, negotiate the differences, and make a final plan to execute. I find Claude Code is better at writing plans, but Codex is faster and cheaper to execute on them. Then I usually have Claude Code watchdog the Codex work and fix anything that was missed. 3️⃣ /read-the-damn-docs One thing that drives me crazy with coding agents is they're so reluctant to look up docs. They'll just guess and guess and guess at the right API surface for things, or the right solution to an integration of two things. Once I explicitly tell it to look up the docs, it says "Oh, I see the answer," and it fixes the problem. So I made the /read-the-damn-docs skill. Add it and your agents will know when and how to do efficient web searches to look up docs for the types of problems you really should look up docs for. All of these are totally open source over on my GitHub. If you try them, let me know your feedback. Will link to them below:
1:21

Three skills I use every day in Claude Code and Codex to solve my hardest problems: 1️⃣ /agent-watchdog When I have one agent like Codex working on a task and I don't fully trust it's going to do everything right, I'll open up another one like Claude Code and tell it to watchdog the Codex thread. You can copy the Codex deep link into Claude Code and it'll look at the prompt you sent, watch the Codex thread until it's done, then compare the Codex solution to how it was planning to solve it and automatically fix anything that Codex missed. It can also test the work of the other agent end-to-end. Similar to the idea of OpenRouter's new Fusion feature, I've definitely found that two models thinking through a problem and checking each other's work can be wildly more impactful than just one. 2️⃣ /plan-arbiter Similar ideas as /agent-watchdog - but with this one you have both make plans, compare plans, negotiate the differences, and make a final plan to execute. I find Claude Code is better at writing plans, but Codex is faster and cheaper to execute on them. Then I usually have Claude Code watchdog the Codex work and fix anything that was missed. 3️⃣ /read-the-damn-docs One thing that drives me crazy with coding agents is they're so reluctant to look up docs. They'll just guess and guess and guess at the right API surface for things, or the right solution to an integration of two things. Once I explicitly tell it to look up the docs, it says "Oh, I see the answer," and it fixes the problem. So I made the /read-the-damn-docs skill. Add it and your agents will know when and how to do efficient web searches to look up docs for the types of problems you really should look up docs for. All of these are totally open source over on my GitHub. If you try them, let me know your feedback. Will link to them below:

Steve (Builder.io)

43,089 次观看 • 1 个月前

🚨 OpenAI just launched Codex, a brand-new autonomous coding agent that can build features and fix bugs on its own. We’ve been using it Every 📧 for a few days, and I’m impressed. I invited Alexander Embiricos (ben davies), a member of the product staff responsible for Codex, to demo Codex and talk about it live on a special edition of AI & I: What Codex is and how it works Codex is designed to be used by senior engineers—it performs coding tasks like adding features or fixing bugs autonomously. It's built to allow you to start many sessions at once, so you can have multiple agents working in parallel. Codex is built to have "taste" OpenAI trained Codex to have the taste of a senior software engineer. It knows how big codebases work, how to write a good PR, and uses clean, minimal code. Why an “abundance mindset” is best for interacting with agents Codex is designed to allow users to delegate many tasks at once without getting caught up in the details. This lets you point an abundance of agents at a specific task like a difficult bug—it’s worth it even if only one of them succeeds. How OpenAI is thinking about agents Codex is one piece of a unified super-assistant OpenAI wants to eventually build—an agent that helps users easily get things done by selecting the right tools for them behind the scenes. OpenAI’s vision for the future of programming In the future developers will probably spend less time writing routine code and more time guiding agents, reviewing their work, and making strategy decisions. Programming will become more social, letting teams easily delegate multiple tasks at once, allowing people to focus on ideas and collaboration instead of routine coding. Watch below!
44:33

🚨 OpenAI just launched Codex, a brand-new autonomous coding agent that can build features and fix bugs on its own. We’ve been using it Every 📧 for a few days, and I’m impressed. I invited Alexander Embiricos (ben davies), a member of the product staff responsible for Codex, to demo Codex and talk about it live on a special edition of AI & I: What Codex is and how it works Codex is designed to be used by senior engineers—it performs coding tasks like adding features or fixing bugs autonomously. It's built to allow you to start many sessions at once, so you can have multiple agents working in parallel. Codex is built to have "taste" OpenAI trained Codex to have the taste of a senior software engineer. It knows how big codebases work, how to write a good PR, and uses clean, minimal code. Why an “abundance mindset” is best for interacting with agents Codex is designed to allow users to delegate many tasks at once without getting caught up in the details. This lets you point an abundance of agents at a specific task like a difficult bug—it’s worth it even if only one of them succeeds. How OpenAI is thinking about agents Codex is one piece of a unified super-assistant OpenAI wants to eventually build—an agent that helps users easily get things done by selecting the right tools for them behind the scenes. OpenAI’s vision for the future of programming In the future developers will probably spend less time writing routine code and more time guiding agents, reviewing their work, and making strategy decisions. Programming will become more social, letting teams easily delegate multiple tasks at once, allowing people to focus on ideas and collaboration instead of routine coding. Watch below!

Dan Shipper 📧

145,487 次观看 • 1 年前

Claude Code Artifacts are out of control amazing. Make changes in your session, and those changes are reflected in the artifact instantly. For *everyone* on your team who has the artifact. This is the first real multi-player agentic engineering workflow. Only available for Enterprise and Teams plans at the moment, but coming to Max and Pro soon I'm sure.
0:21

Claude Code Artifacts are out of control amazing. Make changes in your session, and those changes are reflected in the artifact instantly. For *everyone* on your team who has the artifact. This is the first real multi-player agentic engineering workflow. Only available for Enterprise and Teams plans at the moment, but coming to Max and Pro soon I'm sure.

Dan McAteer

32,005 次观看 • 2 个月前

Jensen Huang just said this is the greatest era in history to build software. AI agents will not kill software. They will do the exact opposite: create a massive new wave of software demand. at NVIDIA GTC Taipei 2026 "Click and type. We now replace that with explaining to the AI what we want, our intent, and the AI generates the code or uses tools to produce the necessary output. This is how computers are going to work in the future. This is Agentic AI. For two years, we've been building toward this, and now it has arrived. One of the big breakthroughs, of course, is tool use. A lot of people have said, “Jensen, AI is coming. Agentic AI is coming. Therefore, all the software companies are going to go out of business.” This is exactly the opposite. Because there are going to be so many agents, the world is no longer limited by the number of people. Therefore, those agents are going to use more tools than ever. This is actually an incredible time to be a software company. But the software has to be presented to the agent in a way that the agent can use it. This is a big breakthrough. And in fact, what we have done, as you know, what Nvidia’s treasure..." ---- From 'NVIDIA' YT channel (link in comment)
0:59

Jensen Huang just said this is the greatest era in history to build software. AI agents will not kill software. They will do the exact opposite: create a massive new wave of software demand. at NVIDIA GTC Taipei 2026 "Click and type. We now replace that with explaining to the AI what we want, our intent, and the AI generates the code or uses tools to produce the necessary output. This is how computers are going to work in the future. This is Agentic AI. For two years, we've been building toward this, and now it has arrived. One of the big breakthroughs, of course, is tool use. A lot of people have said, “Jensen, AI is coming. Agentic AI is coming. Therefore, all the software companies are going to go out of business.” This is exactly the opposite. Because there are going to be so many agents, the world is no longer limited by the number of people. Therefore, those agents are going to use more tools than ever. This is actually an incredible time to be a software company. But the software has to be presented to the agent in a way that the agent can use it. This is a big breakthrough. And in fact, what we have done, as you know, what Nvidia’s treasure..." ---- From 'NVIDIA' YT channel (link in comment)

Rohan Paul

16,584 次观看 • 2 个月前

Jensen Huang says agentic AI is not a chatbot. It is a "digital robot" -- and the next bottleneck is not the model. It is first-person data. "Agentic AI is just a digital robot. It understands, it reasons, it plans, and it acts and uses tools." Then he makes the bigger jump: "The world's video data is from a third person, not first person. And so agentic systems, robotic systems, physical AI -- the data is the hardest problem." That is the hidden constraint in robotics. LLMs got the internet. Physical AI needs demonstrations, synthetic worlds, reinforcement learning, and first-person experience. This is why Jensen keeps calling it a stack: robots are not waiting for one magical model. They need the data engine, the simulator, the reward system, the runtime, and the computer. The next wave of AI is not just software that talks. It is software that sees, plans, acts, and eventually moves through the world.
2:32

Jensen Huang says agentic AI is not a chatbot. It is a "digital robot" -- and the next bottleneck is not the model. It is first-person data. "Agentic AI is just a digital robot. It understands, it reasons, it plans, and it acts and uses tools." Then he makes the bigger jump: "The world's video data is from a third person, not first person. And so agentic systems, robotic systems, physical AI -- the data is the hardest problem." That is the hidden constraint in robotics. LLMs got the internet. Physical AI needs demonstrations, synthetic worlds, reinforcement learning, and first-person experience. This is why Jensen keeps calling it a stack: robots are not waiting for one magical model. They need the data engine, the simulator, the reward system, the runtime, and the computer. The next wave of AI is not just software that talks. It is software that sees, plans, acts, and eventually moves through the world.

Karl Mehta

14,140 次观看 • 1 个月前

“The only job left is to understand what you don't like, put it into words, and tell the AI.” Here’s my new episode with jason (DevEx at OpenAI) where he showed me how he uses Codex throughout his workday, including how to: → Set up a chief of staff for Slack and email → Turn past sessions into new AI skills → Give long-running projects verifiable goals Some example Codex use cases from Jason: “I want you to read the past week of Slack messages I’ve written and make a skill to figure out how to talk like me.” “Turn this thread into a heartbeat. I want you to check my emails, my Slack, my Linear, and tell me what I need to prioritize.” “Codex can find a booking ticket and check into the flight for me and text me the boarding pass to my phone.” Jason wrote the official OpenAI handbook on how to get the most out of Codex, so don’t miss this episode. 📌 Watch now: Thanks to our sponsors: Riverside: All-in-one AI studio for podcasts and video Google AI Studio: Build apps with Nano Banana, and more
0:30

“The only job left is to understand what you don't like, put it into words, and tell the AI.” Here’s my new episode with jason (DevEx at OpenAI) where he showed me how he uses Codex throughout his workday, including how to: → Set up a chief of staff for Slack and email → Turn past sessions into new AI skills → Give long-running projects verifiable goals Some example Codex use cases from Jason: “I want you to read the past week of Slack messages I’ve written and make a skill to figure out how to talk like me.” “Turn this thread into a heartbeat. I want you to check my emails, my Slack, my Linear, and tell me what I need to prioritize.” “Codex can find a booking ticket and check into the flight for me and text me the boarding pass to my phone.” Jason wrote the official OpenAI handbook on how to get the most out of Codex, so don’t miss this episode. 📌 Watch now: Thanks to our sponsors: Riverside: All-in-one AI studio for podcasts and video Google AI Studio: Build apps with Nano Banana, and more

Peter Yang

217,376 次观看 • 25 天前

We just launched Sites into Codex! Software creation was always about more than writing code. Sites in Codex fundamentally gives the power of end-to-end software creation to every user, no matter their technical fluency. These Sites are fully deployed to a URL, private to workspaces, come with authentication, can have static files, and can store dynamic data in databases. It is in preview for business and enterprise teams and will be rolling out to all workspaces over the next day. Give it a try by typing @ Sites into Codex and ask it to build anything! This project took a massive amount of effort across hundreds of people at OpenAI - proud that we were able to get this out and excited to see what you all build with it!
0:46

We just launched Sites into Codex! Software creation was always about more than writing code. Sites in Codex fundamentally gives the power of end-to-end software creation to every user, no matter their technical fluency. These Sites are fully deployed to a URL, private to workspaces, come with authentication, can have static files, and can store dynamic data in databases. It is in preview for business and enterprise teams and will be rolling out to all workspaces over the next day. Give it a try by typing @ Sites into Codex and ask it to build anything! This project took a massive amount of effort across hundreds of people at OpenAI - proud that we were able to get this out and excited to see what you all build with it!

Rohan Varma

1,035,032 次观看 • 2 个月前

Sam Altman reveals building Codex was a "crazy kamikaze mission" to beat Claude Code and that most of the best coders he knows now use Codex. "We were way behind Claude Code, and it seemed like a kind of crazy kamikaze mission to try to beat them with a coding app." "The consensus is that this kind of thing never works, and you just move on to the next one. It's a fool's errand to try to win when someone else already has momentum in a particular product category." "But we decided we thought it was really important. We asked a team to do it, and they performed a legitimate, unbelievable, very rare in the history of business thing." "Now it is the product that most of the best coders I know use." "That felt like an impossible thing, but if we hadn't asked the team, hey, we have a really important but extremely hard mission for you, it just wouldn't have happened."
0:58

Sam Altman reveals building Codex was a "crazy kamikaze mission" to beat Claude Code and that most of the best coders he knows now use Codex. "We were way behind Claude Code, and it seemed like a kind of crazy kamikaze mission to try to beat them with a coding app." "The consensus is that this kind of thing never works, and you just move on to the next one. It's a fool's errand to try to win when someone else already has momentum in a particular product category." "But we decided we thought it was really important. We asked a team to do it, and they performed a legitimate, unbelievable, very rare in the history of business thing." "Now it is the product that most of the best coders I know use." "That felt like an impossible thing, but if we hadn't asked the team, hey, we have a really important but extremely hard mission for you, it just wouldn't have happened."

Fireside Alpha

1,261,432 次观看 • 26 天前

The trades can build anything... except the software they run on. That changes today. We've raised $9.2M to build Dalton Mills. Software has spent its whole history getting closer to the people who do the work. First, the system of record. Software you stored your business in. Then, the agentic era. Software that did the work for you. Now, the bespoke era. Agentic software you build yourself, without code. Each era closed the gap and this one closes it for good. Software can finally work around your business, instead of you bending your business to make it fit. You ran on software made for everyone… never for you. That's over. Welcome to Dalton Mills. Let the builders build!
2:14

The trades can build anything... except the software they run on. That changes today. We've raised $9.2M to build Dalton Mills. Software has spent its whole history getting closer to the people who do the work. First, the system of record. Software you stored your business in. Then, the agentic era. Software that did the work for you. Now, the bespoke era. Agentic software you build yourself, without code. Each era closed the gap and this one closes it for good. Software can finally work around your business, instead of you bending your business to make it fit. You ran on software made for everyone… never for you. That's over. Welcome to Dalton Mills. Let the builders build!

Todd Saunders

96,045 次观看 • 2 个月前

I have built a Windows x64 sampling profiler for native code+C# to be used by coding agents. Why? Because it is irresponsible to let computers write code but give them no tools to evaluate the performance of their code. Stop guessing, start measuring. -> How does it work? Just point your agent to the profiler and let them measure and optimize. Or record a trace yourself and let the agent interpret the results for you. Works with Claude Code, Codex, pi, etc. The profiler also has a couple of neat features by itself like giving you estimates for how much time your code is spending on memory stalls and annotating disassembly with inlining information. Take a look and try it for free!
12:40

I have built a Windows x64 sampling profiler for native code+C# to be used by coding agents. Why? Because it is irresponsible to let computers write code but give them no tools to evaluate the performance of their code. Stop guessing, start measuring. -> How does it work? Just point your agent to the profiler and let them measure and optimize. Or record a trace yourself and let the agent interpret the results for you. Works with Claude Code, Codex, pi, etc. The profiler also has a couple of neat features by itself like giving you estimates for how much time your code is spending on memory stalls and annotating disassembly with inlining information. Take a look and try it for free!

Sebastian Schöner

13,064 次观看 • 3 个月前

Text-to-SQL is dead 💀 The next generation of querying is agentic - and it’s already here. This paper ( introduces a type of agentic querying called 𝗙𝘂𝗻𝗰𝘁𝗶𝗼𝗻 𝗖𝗮𝗹𝗹𝗶𝗻𝗴 that uses an LLM to structure queries using predefined function calls in JSON format, with optional arguments for search, filters, aggregation, and grouping. Along with that, it also tests out a bunch of different models with a new dataset, DBGorilla, designed to evaluate agentic querying techniques on real-world use cases. Weaviate AI Database also just released a 𝗤𝘂𝗲𝗿𝘆 𝗔𝗴𝗲𝗻𝘁, designed based on some of the work in this paper, to handle advanced agentic querying out of the box, find out more here:
3:32

Text-to-SQL is dead 💀 The next generation of querying is agentic - and it’s already here. This paper ( introduces a type of agentic querying called 𝗙𝘂𝗻𝗰𝘁𝗶𝗼𝗻 𝗖𝗮𝗹𝗹𝗶𝗻𝗴 that uses an LLM to structure queries using predefined function calls in JSON format, with optional arguments for search, filters, aggregation, and grouping. Along with that, it also tests out a bunch of different models with a new dataset, DBGorilla, designed to evaluate agentic querying techniques on real-world use cases. Weaviate AI Database also just released a 𝗤𝘂𝗲𝗿𝘆 𝗔𝗴𝗲𝗻𝘁, designed based on some of the work in this paper, to handle advanced agentic querying out of the box, find out more here:

Victoria Slocum

189,281 次观看 • 1 年前

If your MCP server has dozens of tools, it’s probably built wrong. You need tools that are specific and clear for each use case—but you also can’t have too many. This creates an almost impossible tradeoff that most companies don’t know how to solve. That’s why I interviewed my friend Alex Rattray (Alex Rattray), the founder and CEO of Stainless. Stainless builds APIs, SDKs, and MCP servers for companies like OpenAI and Anthropic. Alex has spent years mastering how to make software talk to software, and he came on the show to share what he knows. I had him on Every 📧’s AI & I to talk about MCP and the future of the AI-native internet. We get into: • Design MCP servers to be lean and precise. Alex’s best practices for building reliable MCP servers start with keeping the toolset small, giving each tool a precise name and description, and minimizing the inputs and outputs the model has to handle. At Stainless, they also often add a JSON filter on top to strip out unnecessary data. • Make complex APIs manageable with dynamic mode. To solve the problem of how an AI figures out which tool to use in larger APIs, Stainless switches to “dynamic mode,” where the model gets only three tools: List the endpoints, pick one and learn about it, and then execute it. • MCP servers as business copilots. At Stainless, Alex uses MCP servers to connect tools like Notion and HubSpot, so he can ask questions like, “Which customers signed up last week?” The system queries multiple databases and returns a summary that would’ve otherwise taken multiple logins and searches. • Create a “brain” for your company with Claude Code. Alex built a shared company brain at Stainless by keeping Claude Code running on his system and asking it to save useful inputs—like customer feedback and SQL queries—into GitHub. Over time, this creates a curated archive his team can query easily. • The future of MCP is code execution. Instead of giving models hundreds of tools, Alex believes the most powerful setup will be a simple code execution tool and a doc search tool. The AI writes code against an API’s SDK, runs it on a server, and checks the docs when it gets stuck. This is a must-watch for anyone who wants to understand MCP—and learn how to use them as a competitive edge. Watch below! Timestamps: Introduction: 00:01:14 Why Alex likes running barefoot: 00:02:54 APIs and MCP, the connectors of the new internet: 00:05:09 Why MCP servers are hard to get right: 00:10:53 Design principles for reliable MCP servers: 00:20:07 Scaling MCP servers for large APIs: 00:23:50 Using MCP for business ops at Stainless: 00:25:14 Building a company brain with Claude Code: 00:28:12 Where MCP goes from here: 00:33:59 Alex’s take on the security model for MCP: 00:41:10
51:39

If your MCP server has dozens of tools, it’s probably built wrong. You need tools that are specific and clear for each use case—but you also can’t have too many. This creates an almost impossible tradeoff that most companies don’t know how to solve. That’s why I interviewed my friend Alex Rattray (Alex Rattray), the founder and CEO of Stainless. Stainless builds APIs, SDKs, and MCP servers for companies like OpenAI and Anthropic. Alex has spent years mastering how to make software talk to software, and he came on the show to share what he knows. I had him on Every 📧’s AI & I to talk about MCP and the future of the AI-native internet. We get into: • Design MCP servers to be lean and precise. Alex’s best practices for building reliable MCP servers start with keeping the toolset small, giving each tool a precise name and description, and minimizing the inputs and outputs the model has to handle. At Stainless, they also often add a JSON filter on top to strip out unnecessary data. • Make complex APIs manageable with dynamic mode. To solve the problem of how an AI figures out which tool to use in larger APIs, Stainless switches to “dynamic mode,” where the model gets only three tools: List the endpoints, pick one and learn about it, and then execute it. • MCP servers as business copilots. At Stainless, Alex uses MCP servers to connect tools like Notion and HubSpot, so he can ask questions like, “Which customers signed up last week?” The system queries multiple databases and returns a summary that would’ve otherwise taken multiple logins and searches. • Create a “brain” for your company with Claude Code. Alex built a shared company brain at Stainless by keeping Claude Code running on his system and asking it to save useful inputs—like customer feedback and SQL queries—into GitHub. Over time, this creates a curated archive his team can query easily. • The future of MCP is code execution. Instead of giving models hundreds of tools, Alex believes the most powerful setup will be a simple code execution tool and a doc search tool. The AI writes code against an API’s SDK, runs it on a server, and checks the docs when it gets stuck. This is a must-watch for anyone who wants to understand MCP—and learn how to use them as a competitive edge. Watch below! Timestamps: Introduction: 00:01:14 Why Alex likes running barefoot: 00:02:54 APIs and MCP, the connectors of the new internet: 00:05:09 Why MCP servers are hard to get right: 00:10:53 Design principles for reliable MCP servers: 00:20:07 Scaling MCP servers for large APIs: 00:23:50 Using MCP for business ops at Stainless: 00:25:14 Building a company brain with Claude Code: 00:28:12 Where MCP goes from here: 00:33:59 Alex’s take on the security model for MCP: 00:41:10

Dan Shipper 📧

15,645 次观看 • 10 个月前

OpenAI’s hottest app isn’t ChatGPT—it’s Codex. In the last few weeks alone, the Codex team shipped a desktop app, GPT-5.3 Codex (a new flagship model), and Spark, the fastest coding model I’ve ever used. Usage has grown fivefold since January and over a million people now use Codex weekly. Codex was also the app that OpenAI chose to run an ad for in the Super Bowl. I talked to Thibault (Tibo), head of Codex, and Andrew (Andrew Ambrosino), a member of technical staff who built the Codex app, for Every 📧’s AI & I about what OpenAI is building and how they’re using it internally. We get into: - Why they built a GUI instead of a terminal. Terminals work for quick tasks, they say, but feel limiting when you’re running multiple agents in parallel. The IDE, meanwhile, overwhelms users—and the Codex team wants the AI to dynamically decide which tools to show you for a given task. - How they’re teaching the model to read between the lines. Codex is great at following instructions, but optimize too hard in that direction, and it starts taking you literally—like copying a typo directly into the code. The team obsesses over this tradeoff, and is also introducing “personalities,” modes users can toggle between that control how blunt or supportive the model feels. - How OpenAI uses its own coding agent. Codex lets you schedule prompts to run on a recurring basis, and the team has dozens of automations running at all times. For example, one scans for merge conflicts every couple of hours so code is always ready to ship, and another picks a random file from the codebase multiple times a day and hunts for bugs no one would've gone looking for. - Why speed is a dimension of intelligence. OpenAI’s newest model (Spark) is so fast that they actually slow it down so you can read the output. They see the speed enabling three things: staying super in the flow, replacing brittle developer tools with intelligent ones that can adapt on the fly, and redirecting the model mid-task— especially with voice—so coding starts to feel more and more like a conversation. - Code review is the next bottleneck. Models can generate code faster than ever, but someone still has to verify that it works. The team is exploring a future where the model proves its own fix works—retracing the click path a user would take, screenshotting the results, and attaching the evidence to a pull request. This is a must-watch for anyone who uses AI coding agents—and is curious about the future of programming. Watch below! Timestamps: Introduction: 00:01:27 OpenAI’s evolving bet on its coding agent: 00:05:27 The choice to invest in a GUI (over a terminal): 00:09:42 The AI workflows that the Codex team relies on to ship: 00:20:38 Teaching Codex how to read between the lines: 00:26:45 Building affordances for a lightening fast model: 00:28:45 Why speed is a dimension of intelligence: 00:33:15 Code review is the next bottleneck for coding agents: 00:36:30 How the Codex team positions against the competition: 00:41:24
46:40

OpenAI’s hottest app isn’t ChatGPT—it’s Codex. In the last few weeks alone, the Codex team shipped a desktop app, GPT-5.3 Codex (a new flagship model), and Spark, the fastest coding model I’ve ever used. Usage has grown fivefold since January and over a million people now use Codex weekly. Codex was also the app that OpenAI chose to run an ad for in the Super Bowl. I talked to Thibault (Tibo), head of Codex, and Andrew (Andrew Ambrosino), a member of technical staff who built the Codex app, for Every 📧’s AI & I about what OpenAI is building and how they’re using it internally. We get into: - Why they built a GUI instead of a terminal. Terminals work for quick tasks, they say, but feel limiting when you’re running multiple agents in parallel. The IDE, meanwhile, overwhelms users—and the Codex team wants the AI to dynamically decide which tools to show you for a given task. - How they’re teaching the model to read between the lines. Codex is great at following instructions, but optimize too hard in that direction, and it starts taking you literally—like copying a typo directly into the code. The team obsesses over this tradeoff, and is also introducing “personalities,” modes users can toggle between that control how blunt or supportive the model feels. - How OpenAI uses its own coding agent. Codex lets you schedule prompts to run on a recurring basis, and the team has dozens of automations running at all times. For example, one scans for merge conflicts every couple of hours so code is always ready to ship, and another picks a random file from the codebase multiple times a day and hunts for bugs no one would've gone looking for. - Why speed is a dimension of intelligence. OpenAI’s newest model (Spark) is so fast that they actually slow it down so you can read the output. They see the speed enabling three things: staying super in the flow, replacing brittle developer tools with intelligent ones that can adapt on the fly, and redirecting the model mid-task— especially with voice—so coding starts to feel more and more like a conversation. - Code review is the next bottleneck. Models can generate code faster than ever, but someone still has to verify that it works. The team is exploring a future where the model proves its own fix works—retracing the click path a user would take, screenshotting the results, and attaching the evidence to a pull request. This is a must-watch for anyone who uses AI coding agents—and is curious about the future of programming. Watch below! Timestamps: Introduction: 00:01:27 OpenAI’s evolving bet on its coding agent: 00:05:27 The choice to invest in a GUI (over a terminal): 00:09:42 The AI workflows that the Codex team relies on to ship: 00:20:38 Teaching Codex how to read between the lines: 00:26:45 Building affordances for a lightening fast model: 00:28:45 Why speed is a dimension of intelligence: 00:33:15 Code review is the next bottleneck for coding agents: 00:36:30 How the Codex team positions against the competition: 00:41:24

Dan Shipper 📧

15,588 次观看 • 6 个月前

You probably don’t use just one AI agent anymore. Maybe Codex for coding. Claude Code for research. Cursor for quick edits. Hermes for the rest. Each one is great at something different. But every time you switch, you have to start over — re-explaining your project, preferences, and the way you like to work. Your agents know how to help you. They just don’t share a memory of you. memU just shipped an update that fixes this. One personal memory, shared across every agent and device you use. What Codex learned last night, Claude Code can remember this morning. 🧵
0:34

You probably don’t use just one AI agent anymore. Maybe Codex for coding. Claude Code for research. Cursor for quick edits. Hermes for the rest. Each one is great at something different. But every time you switch, you have to start over — re-explaining your project, preferences, and the way you like to work. Your agents know how to help you. They just don’t share a memory of you. memU just shipped an update that fixes this. One personal memory, shared across every agent and device you use. What Codex learned last night, Claude Code can remember this morning. 🧵

Hasan

22,362 次观看 • 23 天前

New short course: LLMs as Operating Systems: Agent Memory, created with Letta, and taught by its founders Charles Packer and Sarah Wooders. An LLM's input context window has limited space. Using a longer input context also costs more and results in slower processing. So, managing what's stored in this context window is important. In the innovative paper MemGPT: Towards LLMs as Operating Systems, its authors (which include the instructors) proposed using an LLM agent to manage this context window. Their system uses a large persistent memory that stores everything that could be included in the input context, and an agent decides what is actually included. Take the example of building a chatbot that needs to remember what's been said earlier in a conversation (perhaps over many days of interaction with a user). As the conversation's length grows, the memory management agent will move information from the input context to a persistent searchable database; summarize information to keep relevant facts in the input context; and restore relevant conversation elements from further back in time. This allows a chatbot to keep what's currently most relevant in its input context memory to generate the next response. When I read the original MemGPT paper, I thought it was an innovative technique for handling memory for LLMs. The open-source Letta framework, which we'll use in this course, makes MemGPT easy to implement. It adds memory to your LLM agents and gives them transparent long-term memory. In detail, you’ll learn: - How to build an agent that can edit its own limited input context memory, using tools and multi-step reasoning - What is a memory hierarchy (an idea from computer operating systems, which use a cache to speed up memory access), and how these ideas apply to managing the LLM input context (where the input context window is a "cache" storing the most relevant information; and an agent decides what to move in and out of this to/from a larger persistent storage system) - How to implement multi-agent collaboration by letting different agents share blocks of memory This course will give you a sophisticated understanding of memory management for LLMs, which is important for chatbots having long conversations, and for complex agentic workflows. Please sign up here!
2:57

New short course: LLMs as Operating Systems: Agent Memory, created with Letta, and taught by its founders Charles Packer and Sarah Wooders. An LLM's input context window has limited space. Using a longer input context also costs more and results in slower processing. So, managing what's stored in this context window is important. In the innovative paper MemGPT: Towards LLMs as Operating Systems, its authors (which include the instructors) proposed using an LLM agent to manage this context window. Their system uses a large persistent memory that stores everything that could be included in the input context, and an agent decides what is actually included. Take the example of building a chatbot that needs to remember what's been said earlier in a conversation (perhaps over many days of interaction with a user). As the conversation's length grows, the memory management agent will move information from the input context to a persistent searchable database; summarize information to keep relevant facts in the input context; and restore relevant conversation elements from further back in time. This allows a chatbot to keep what's currently most relevant in its input context memory to generate the next response. When I read the original MemGPT paper, I thought it was an innovative technique for handling memory for LLMs. The open-source Letta framework, which we'll use in this course, makes MemGPT easy to implement. It adds memory to your LLM agents and gives them transparent long-term memory. In detail, you’ll learn: - How to build an agent that can edit its own limited input context memory, using tools and multi-step reasoning - What is a memory hierarchy (an idea from computer operating systems, which use a cache to speed up memory access), and how these ideas apply to managing the LLM input context (where the input context window is a "cache" storing the most relevant information; and an agent decides what to move in and out of this to/from a larger persistent storage system) - How to implement multi-agent collaboration by letting different agents share blocks of memory This course will give you a sophisticated understanding of memory management for LLMs, which is important for chatbots having long conversations, and for complex agentic workflows. Please sign up here!

Andrew Ng

200,950 次观看 • 1 年前

After creating Remodex: Codex remote control for iOS I decided to chill a bit by building a browser sidebar inside Theo - t3.gg 's T3 Code You can open it with Cmd+Shift+B This software is so easy to "manipulate" and build upon Congrats to all the guys that put the work in it because it is great I certainly will be building more things with it For this one I decided to switch from the Codex App to the Codex CLI too just to see how it works And boy it was so good
0:20

After creating Remodex: Codex remote control for iOS I decided to chill a bit by building a browser sidebar inside Theo - t3.gg 's T3 Code You can open it with Cmd+Shift+B This software is so easy to "manipulate" and build upon Congrats to all the guys that put the work in it because it is great I certainly will be building more things with it For this one I decided to switch from the Codex App to the Codex CLI too just to see how it works And boy it was so good

Emanuele Di Pietro

38,905 次观看 • 4 个月前

Former Goldman Sachs executive Raoul Pal explains how AI is going to eat traditional software/SAAS. If your product is just software, agentic AI can reproduce it on demand, optimize it, and redeploy it to a better market. "Agentic AI means it’s like having Fiverr, a website of experts you can ask any question. It’ll go away and do the task.... Agentic AI will build, design the website, code it, register the domain name, figure out the branding, figure out the marketing, figure out the email list, figure out the whole thing. So then you and I are in competition. You’ve built this incredible new website. I just go to my AI and say, “Love Steven’s website. Can you just build it better. Boom. 3 minutes. How can we be entrepreneurs in software? Now there’s this theory going around that AI is going to eat software, and I kind of get it." ---- From 'The Diary Of A CEO and Raoul Pal The Journey Man' YT channel. (link in comment)
1:11

Former Goldman Sachs executive Raoul Pal explains how AI is going to eat traditional software/SAAS. If your product is just software, agentic AI can reproduce it on demand, optimize it, and redeploy it to a better market. "Agentic AI means it’s like having Fiverr, a website of experts you can ask any question. It’ll go away and do the task.... Agentic AI will build, design the website, code it, register the domain name, figure out the branding, figure out the marketing, figure out the email list, figure out the whole thing. So then you and I are in competition. You’ve built this incredible new website. I just go to my AI and say, “Love Steven’s website. Can you just build it better. Boom. 3 minutes. How can we be entrepreneurs in software? Now there’s this theory going around that AI is going to eat software, and I kind of get it." ---- From 'The Diary Of A CEO and Raoul Pal The Journey Man' YT channel. (link in comment)

Rohan Paul

48,418 次观看 • 5 个月前