Santiago's banner

Santiago

@svpino • 452,849 subscribers

Computer scientist. I teach hard-core AI/ML Engineering at https://t.co/THCAAZcBMu. YouTube: https://t.co/pROi08OZYJ

Shorts

DeepSeek R1 is *the* best model available right now. It's at the level of o1, but you can use it for free, and it's much faster. A huge leap forward that nobody saw coming. No wonder so many people are throwing tantrums online trying to discredit the Chinese students who built this. You can use DeepSeek in Visual Studio Code right now: 1. Install the Qodo Gen AI extension 2. Select DeepSeek R1 from their list of models The Qodo team is hosting DeepSeek on their servers, so none of your data will go to China. I've been building a Tetris game using DeepSeek, and this is the most impressive model I've seen so far.

DeepSeek R1 is the best model available right now. It's at the level of o1, but you can use it for free, and it's much faster. A huge leap forward that nobody saw coming. No wonder so many people are throwing tantrums online trying to discredit the Chinese students who built this. You can use DeepSeek in Visual Studio Code right now: 1. Install the Qodo Gen AI extension 2. Select DeepSeek R1 from their list of models The Qodo team is hosting DeepSeek on their servers, so none of your data will go to China. I've been building a Tetris game using DeepSeek, and this is the most impressive model I've seen so far.

1,224,059 Aufrufe

Look at the speed at which this model generates video! Imagine a chat interface that uses real-time video streaming to talk to us instead of text. We are getting close!

Look at the speed at which this model generates video! Imagine a chat interface that uses real-time video streaming to talk to us instead of text. We are getting close!

38,610 Aufrufe

The architecture of this new world model is one of the most interesting things I've seen lately: Let me first explain how most world models work: They predict and render one frame at a time. If you are navigating in one of these worlds, and you look left, the model draws whatever looks right in the moment. Every time you change your viewpoint, the model has to imagine what should be there again, so it's very common for these models to "forget" what's in the world. For example, if you put a toy on the table, look away, then look back, the toy might not be there anymore. Tripo AI is releasing its Project Eden model, which works very differently: The model builds the world first, and then renders it based on that map. That map holds the real state of the world: the geometry, every object, where things are, what's already happened. The picture you see on screen gets generated from the map. This architecture flips the whole thing. Now, you get the following: 1. The world stops forgetting. Leave, come back, and the toy is still on the table because it lives in the map, not in the last frame you saw. 2. You can edit the world, and those changes persist for anyone who enters later. 3. Multiple people and AI agents can coexist in the world and see it from different perspectives. This is early research, but it's looking really promising. They just raised nearly $200M across two rounds to build it out. Tripo will be at SIGGRAPH 2026 (July 19–23, Los Angeles Convention Center). If you work in 3D, embodied AI, simulation, or anything spatial, go connect with them there.

The architecture of this new world model is one of the most interesting things I've seen lately: Let me first explain how most world models work: They predict and render one frame at a time. If you are navigating in one of these worlds, and you look left, the model draws whatever looks right in the moment. Every time you change your viewpoint, the model has to imagine what should be there again, so it's very common for these models to "forget" what's in the world. For example, if you put a toy on the table, look away, then look back, the toy might not be there anymore. Tripo AI is releasing its Project Eden model, which works very differently: The model builds the world first, and then renders it based on that map. That map holds the real state of the world: the geometry, every object, where things are, what's already happened. The picture you see on screen gets generated from the map. This architecture flips the whole thing. Now, you get the following: 1. The world stops forgetting. Leave, come back, and the toy is still on the table because it lives in the map, not in the last frame you saw. 2. You can edit the world, and those changes persist for anyone who enters later. 3. Multiple people and AI agents can coexist in the world and see it from different perspectives. This is early research, but it's looking really promising. They just raised nearly $200M across two rounds to build it out. Tripo will be at SIGGRAPH 2026 (July 19–23, Los Angeles Convention Center). If you work in 3D, embodied AI, simulation, or anything spatial, go connect with them there.

30,189 Aufrufe

The first design agent ever released is pretty incredible! Human + AI working on the same canvas. I wrote a prompt, and 5 minutes later, I had $5,000-worth of design posters waiting for me. I think I'm never hiring a designer ever again.

The first design agent ever released is pretty incredible! Human + AI working on the same canvas. I wrote a prompt, and 5 minutes later, I had $5,000-worth of design posters waiting for me. I think I'm never hiring a designer ever again.

333,649 Aufrufe

This is how you unlock the next billion software developers. The new Replit ⠕ Agent 3 (they just launched) is the most advanced vibe-coding agent in the world. 1. Smarter than any other vibe-coding model (10x more autonomous than the previous version). 2. It thinks harder and lasts longer than any other model (up to 200 minutes running fully autonomously). 3. The agent can now use an actual browser to test and fix its own code. 4. 3x faster and 10x more cost-effective than any other "Computer Use" for testing. 5. It can build other agents and automations to take care of repetitive tasks. Seeing the agent test the application autonomously is science fiction!

This is how you unlock the next billion software developers. The new Replit ⠕ Agent 3 (they just launched) is the most advanced vibe-coding agent in the world. 1. Smarter than any other vibe-coding model (10x more autonomous than the previous version). 2. It thinks harder and lasts longer than any other model (up to 200 minutes running fully autonomously). 3. The agent can now use an actual browser to test and fix its own code. 4. 3x faster and 10x more cost-effective than any other "Computer Use" for testing. 5. It can build other agents and automations to take care of repetitive tasks. Seeing the agent test the application autonomously is science fiction!

167,056 Aufrufe

My project has 39,205 lines of code, and Cursor can't answer questions about it. Cursor's context seems to be capped at around 10,000 tokens. Unfortunately, this is not enough for any decent-sized project. If you have a large codebase, check out Augment Code. This thing is faaaast! I'm currently using their Visual Studio Code plugin, but you can also use them on JetBrains, Neovim, and even Vim. (I'm a Neovim fan, but Copilot's implementation for Neovim is nowhere as good as Augment Code.) Augment Code was gracious enough to sponsor this post. After you install their extension and run it for the first time, it will index your entire codebase. This is why it can answer questions as fast as it does, regardless of the size of your codebase. Augment Code supports chat and completions like every other AI coding assistant, but its killer feature is "Next Edit." When you make a change, two things happen: 1. The model analyzes the change to determine the ripple effects across your *entire* codebase. 2. The model suggests everything you need to update to ensure everything works correctly. This is pretty wild!

My project has 39,205 lines of code, and Cursor can't answer questions about it. Cursor's context seems to be capped at around 10,000 tokens. Unfortunately, this is not enough for any decent-sized project. If you have a large codebase, check out Augment Code. This thing is faaaast! I'm currently using their Visual Studio Code plugin, but you can also use them on JetBrains, Neovim, and even Vim. (I'm a Neovim fan, but Copilot's implementation for Neovim is nowhere as good as Augment Code.) Augment Code was gracious enough to sponsor this post. After you install their extension and run it for the first time, it will index your entire codebase. This is why it can answer questions as fast as it does, regardless of the size of your codebase. Augment Code supports chat and completions like every other AI coding assistant, but its killer feature is "Next Edit." When you make a change, two things happen: 1. The model analyzes the change to determine the ripple effects across your entire codebase. 2. The model suggests everything you need to update to ensure everything works correctly. This is pretty wild!

247,817 Aufrufe

OpenAI's Deep Research is getting a run for its money. Deep Lake was just released, and it's a different take on an AI system that can do deep research on your own data. You can use Deep Lake to build AI search with reasoning on your private and public data. (Look at the attached videos to get an idea of how it works.) If you want to research proprietary and sensitive data, Deep Research won't help you because it's limited to public data. Deep Lake, however, will allow you to use your private data. On top of that, Deep Lake supports multi-modal retrieval from the ground up. It uses vision language models for data ingestion and retrieval so that you can connect any data (PDFs, images, videos, structured data, etc.) You can even use mixed-data queries! Deep Lake can search your data from S3, Dropbox, and GCP. It learns from your queries over time, making the results as relevant to your work as possible!

OpenAI's Deep Research is getting a run for its money. Deep Lake was just released, and it's a different take on an AI system that can do deep research on your own data. You can use Deep Lake to build AI search with reasoning on your private and public data. (Look at the attached videos to get an idea of how it works.) If you want to research proprietary and sensitive data, Deep Research won't help you because it's limited to public data. Deep Lake, however, will allow you to use your private data. On top of that, Deep Lake supports multi-modal retrieval from the ground up. It uses vision language models for data ingestion and retrieval so that you can connect any data (PDFs, images, videos, structured data, etc.) You can even use mixed-data queries! Deep Lake can search your data from S3, Dropbox, and GCP. It learns from your queries over time, making the results as relevant to your work as possible!

171,340 Aufrufe

A massive repository with end-to-end examples of AI applications with React! Together with MCP and A2A, the Agent-User Interaction Protocol (AG-UI) is the third piece that will help you build user-facing AI agents. This GitHub repository will give you access to a bunch of examples showing you how to build the following: • Real-time updates between AI and users • Shared mutable state between agents and users • Tool orchestration • Security boundaries • UI synchronization In every one of these examples, you'll get the following: • Client sends a POST request to the agent endpoint • Then listens to a unified event stream over HTTP • Each event includes a type and a minimal payload • Agents emit events in real-time • The frontend can react immediately to these events • The frontend emits events and context back to the agent Check the link in the next post:

A massive repository with end-to-end examples of AI applications with React! Together with MCP and A2A, the Agent-User Interaction Protocol (AG-UI) is the third piece that will help you build user-facing AI agents. This GitHub repository will give you access to a bunch of examples showing you how to build the following: • Real-time updates between AI and users • Shared mutable state between agents and users • Tool orchestration • Security boundaries • UI synchronization In every one of these examples, you'll get the following: • Client sends a POST request to the agent endpoint • Then listens to a unified event stream over HTTP • Each event includes a type and a minimal payload • Agents emit events in real-time • The frontend can react immediately to these events • The frontend emits events and context back to the agent Check the link in the next post:

78,271 Aufrufe

Here is an AI-native browser. You gotta see how this works! Honestly, I'm still wrapping my head around this. This web browser: • Integrates an AI agent on every page • Can navigate on autopilot • It can even use web apps for you! Check out this video:

Here is an AI-native browser. You gotta see how this works! Honestly, I'm still wrapping my head around this. This web browser: • Integrates an AI agent on every page • Can navigate on autopilot • It can even use web apps for you! Check out this video:

96,109 Aufrufe

AI will not leave software engineers homeless any time soon. Google CEO says quiet part out loud: “Yeah… we need all of those software engineers…” Who would have known that!

AI will not leave software engineers homeless any time soon. Google CEO says quiet part out loud: “Yeah… we need all of those software engineers…” Who would have known that!

74,985 Aufrufe

MiniMax is the James Bond of AI agents. It uses the world's first open-weight model (MiniMax-M1), and it squeezes every bit of power from it. The agent takes a prompt and does more than any other agent in the market right now: 1. It can do Deep Research 2. It can write code 3. It can design web pages 4. It can build 3D models I built 5 different experiences using MiniMax and recorded them for you:

MiniMax is the James Bond of AI agents. It uses the world's first open-weight model (MiniMax-M1), and it squeezes every bit of power from it. The agent takes a prompt and does more than any other agent in the market right now: 1. It can do Deep Research 2. It can write code 3. It can design web pages 4. It can build 3D models I built 5 different experiences using MiniMax and recorded them for you:

44,730 Aufrufe

Replit, Vercel, and OpenAI have built very cool agent-native applications, but nobody else has passed the demo stage. Building agents that work is complex. Teams aren't shipping agents because we don't have good tooling yet (and most of us don't know how to do this well.) A couple of days ago, the CopilotKit🪁 team announced a collaboration with . You can now use LangGraph with CoAgents to build agent-native applications, and here is everything you need to know about that: CoAgents is fully open-source, and you can use it to do the following: • 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 Start this GitHub Repository: Thanks to the team for giving me early access and collaborating with me on this post.

Replit, Vercel, and OpenAI have built very cool agent-native applications, but nobody else has passed the demo stage. Building agents that work is complex. Teams aren't shipping agents because we don't have good tooling yet (and most of us don't know how to do this well.) A couple of days ago, the CopilotKit🪁 team announced a collaboration with . You can now use LangGraph with CoAgents to build agent-native applications, and here is everything you need to know about that: CoAgents is fully open-source, and you can use it to do the following: • 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 Start this GitHub Repository: Thanks to the team for giving me early access and collaborating with me on this post.

63,073 Aufrufe

Huge step for people who want to integrate video production as part of a workflow: $ pixverse create video --prompt "a parisian scene during a rainy day." You can now run the PixVerse CLI or integrate with their API: • JSON outputs • Asynchronous generation • Really easy debugging and task tracking • Deterministic exit codes The terminal changes how you use the product entirely.

Huge step for people who want to integrate video production as part of a workflow: $ pixverse create video --prompt "a parisian scene during a rainy day." You can now run the PixVerse CLI or integrate with their API: • JSON outputs • Asynchronous generation • Really easy debugging and task tracking • Deterministic exit codes The terminal changes how you use the product entirely.

14,237 Aufrufe

My kid is learning how to program. He is not using AI.

My kid is learning how to program. He is not using AI.

32,504 Aufrufe

In a year or two, every ad you see will be AI-generated. If you're selling a product, you should check this out. Here is how you can generate hundreds of ads while you sleep:

In a year or two, every ad you see will be AI-generated. If you're selling a product, you should check this out. Here is how you can generate hundreds of ads while you sleep:

26,017 Aufrufe

You can integrate uv with your shell to enable autocompletion on the terminal! The good stuff keeps getting better! Take 5 minutes and look into uv. I'm willing to bet you'll like it a lot.

You can integrate uv with your shell to enable autocompletion on the terminal! The good stuff keeps getting better! Take 5 minutes and look into uv. I'm willing to bet you'll like it a lot.

22,174 Aufrufe

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

Apple will blow everyone out of the water.

Apple will blow everyone out of the water.

49,347,388 Aufrufe • vor 2 Jahren

People are lying to you. These agents don't work as they promised.

People are lying to you. These agents don't work as they promised.

854,894 Aufrufe • vor 4 Monaten

Some of the stories they aren't telling you: • Chevrolet's chatbot sold a car for $1 • Air Canada had to honor a refund policy that its chatbot made up • A pipeline ran 20x over cost for 6 days without anyone noticing People didn't realize because nothing broke. There were no crashes and no alerts. That's the issue with agentic applications. They always generate something that looks coherent and don't raise any suspicion unless it's too late. There's an amazing free YouTube lecture and blog post from Arsh Shah Dilbagi that will help you fix this with a practical framework. Here is what you'll learn: • How to set up end-to-end trace instrumentation • How to build alerts around a silent failure taxonomy • An eval system built from production data • Complete and concrete implementation steps Every section of the blog ends with exactly what to do next.

Some of the stories they aren't telling you: • Chevrolet's chatbot sold a car for $1 • Air Canada had to honor a refund policy that its chatbot made up • A pipeline ran 20x over cost for 6 days without anyone noticing People didn't realize because nothing broke. There were no crashes and no alerts. That's the issue with agentic applications. They always generate something that looks coherent and don't raise any suspicion unless it's too late. There's an amazing free YouTube lecture and blog post from Arsh Shah Dilbagi that will help you fix this with a practical framework. Here is what you'll learn: • How to set up end-to-end trace instrumentation • How to build alerts around a silent failure taxonomy • An eval system built from production data • Complete and concrete implementation steps Every section of the blog ends with exactly what to do next.

609,504 Aufrufe • vor 4 Monaten

How to monitor the web and research what comes back in 300 lines of code. I want to buy some cheap products on Amazon, but I want to grab them when prices drop. I'm using Parallel Parallel Web Systems here, which is a really easy way to ground your agentic code. Here is how this works: 1. Set up a monitoring event with Parallel for the products 2. If there's a hit, I get a webhook event with the details 3. My script immediately kicks off a Deep Research task 4. The final result tells me whether the product is worth buying I probably spent 1 hour building all of this with Claude Code + the Parallel Agent Skills. I'm linking to the GitHub repo below. Just think about what you could do with this. Here is an easy example (I also set this up): • Monitor news for public tech companies • Analyze the news + price • Assess whether it's worth investing You can do this, put it on autopilot, and get an email anytime there's something worth your time. Here is the video I recorded.

How to monitor the web and research what comes back in 300 lines of code. I want to buy some cheap products on Amazon, but I want to grab them when prices drop. I'm using Parallel Parallel Web Systems here, which is a really easy way to ground your agentic code. Here is how this works: 1. Set up a monitoring event with Parallel for the products 2. If there's a hit, I get a webhook event with the details 3. My script immediately kicks off a Deep Research task 4. The final result tells me whether the product is worth buying I probably spent 1 hour building all of this with Claude Code + the Parallel Agent Skills. I'm linking to the GitHub repo below. Just think about what you could do with this. Here is an easy example (I also set this up): • Monitor news for public tech companies • Analyze the news + price • Assess whether it's worth investing You can do this, put it on autopilot, and get an email anytime there's something worth your time. Here is the video I recorded.

14,430 Aufrufe • vor 2 Tagen

This was the peak. We’ll never top this.

This was the peak. We’ll never top this.

1,987,055 Aufrufe • vor 1 Jahr

Google published an entire library of highly sophisticated, end-to-end agent examples. 100% open-source. • Complete documentation • Source code • Ability to one-click deploy In the video, I break down one of the coolest examples in this collection.

Google published an entire library of highly sophisticated, end-to-end agent examples. 100% open-source. • Complete documentation • Source code • Ability to one-click deploy In the video, I break down one of the coolest examples in this collection.

109,892 Aufrufe • vor 2 Monaten

This is literally the fastest way to install OpenClaw (MoltBot). This video will show you how to do it step by step. You don't need to buy a Mac Mini. We'll install it in DigitalOcean. I've installed this 12 different times already, and this is the fastest way I've found.

This is literally the fastest way to install OpenClaw (MoltBot). This video will show you how to do it step by step. You don't need to buy a Mac Mini. We'll install it in DigitalOcean. I've installed this 12 different times already, and this is the fastest way I've found.

241,149 Aufrufe • vor 5 Monaten

My agent is now paying for its own data. No API key. No account. No credit card. Check the video I recorded. This uses the x402 open protocol built by Coinbase, along with a simple skill. This is an open protocol governed by the Linux Foundation. To complete a goal, an agent can now search for an actor on the Apify Store, pay for it, and use it without any human intervention. The way it works is pretty simple: 1. Your agent finds an Actor it wants to use 2. It sends a request 3. The Actor sends back an HTTP 402 "Payment Required" response 4. Agent authorizes payment from a wallet in USDC on Base 5. The Actor runs 6. User receives the result The model is pay-as-you-go: the agent authorizes a spending ceiling, pays only for usage, and the remaining balance is automatically settled. This brings an entire marketplace of AI tools into the agentic economy. Here is the skill you need. Add it to your agent, and it will take care of everything for you: If you want to know how this works, including what you can do with $1, read this post: Thanks to the Apify team for partnering with me on this post.

My agent is now paying for its own data. No API key. No account. No credit card. Check the video I recorded. This uses the x402 open protocol built by Coinbase, along with a simple skill. This is an open protocol governed by the Linux Foundation. To complete a goal, an agent can now search for an actor on the Apify Store, pay for it, and use it without any human intervention. The way it works is pretty simple: 1. Your agent finds an Actor it wants to use 2. It sends a request 3. The Actor sends back an HTTP 402 "Payment Required" response 4. Agent authorizes payment from a wallet in USDC on Base 5. The Actor runs 6. User receives the result The model is pay-as-you-go: the agent authorizes a spending ceiling, pays only for usage, and the remaining balance is automatically settled. This brings an entire marketplace of AI tools into the agentic economy. Here is the skill you need. Add it to your agent, and it will take care of everything for you: If you want to know how this works, including what you can do with $1, read this post: Thanks to the Apify team for partnering with me on this post.

26,413 Aufrufe • vor 16 Tagen

This little device lets your agents do what they do best, whilst making sure you approve every important action. This is a Ledger Nano Gen5, a hardware signer that keeps your accounts secure. You can install a CLI and a set of skills in your projects. These will enable your agents to send their plan to the signer, so you can approve it. This is awesome: 1. You can have an automated agentic workflow 2. Your agents can't make costly mistakes Check the video I recorded to see how this works. You can run all of this in two commands: 1. Install the CLI 2. Install the skills for your agent From here, the agent can query my Ethereum accounts, check balances, and even initiate transactions as long as my Ledger Nano Gen5 is plugged into the computer. My keys are never stored in my computer and never shared with the agent. This is huge! Also, while the agent can set up transactions, it can't execute them unless a human approves them using the device. Pretty awesome! Thanks to the Ledger team for partnering with me on this post.

This little device lets your agents do what they do best, whilst making sure you approve every important action. This is a Ledger Nano Gen5, a hardware signer that keeps your accounts secure. You can install a CLI and a set of skills in your projects. These will enable your agents to send their plan to the signer, so you can approve it. This is awesome: 1. You can have an automated agentic workflow 2. Your agents can't make costly mistakes Check the video I recorded to see how this works. You can run all of this in two commands: 1. Install the CLI 2. Install the skills for your agent From here, the agent can query my Ethereum accounts, check balances, and even initiate transactions as long as my Ledger Nano Gen5 is plugged into the computer. My keys are never stored in my computer and never shared with the agent. This is huge! Also, while the agent can set up transactions, it can't execute them unless a human approves them using the device. Pretty awesome! Thanks to the Ledger team for partnering with me on this post.

43,749 Aufrufe • vor 29 Tagen

We integrated ChatGPT with our robots. We had a ton of fun building this! Read on for the details:

We integrated ChatGPT with our robots. We had a ton of fun building this! Read on for the details:

1,256,628 Aufrufe • vor 3 Jahren

Markdown was doomed from the start. It's just a format with low information density. HTML is better for humans, and agents can now consume and produce it without issues. But nobody wants to type HTML, so here is an alternative: This is an open-source tool for generating dashboards from data without writing a single HTML tag. You define your dashboard in YAML or TSK, and the tool will serve the HTML file for you. It comes with skills for Claude Code and Codex, so they know how to build these dashboards. And you can connect this to Postgres, MySQL, Snowflake, BigQuery, Redshift, Databricks, and many other databases. Repo link below.

Markdown was doomed from the start. It's just a format with low information density. HTML is better for humans, and agents can now consume and produce it without issues. But nobody wants to type HTML, so here is an alternative: This is an open-source tool for generating dashboards from data without writing a single HTML tag. You define your dashboard in YAML or TSK, and the tool will serve the HTML file for you. It comes with skills for Claude Code and Codex, so they know how to build these dashboards. And you can connect this to Postgres, MySQL, Snowflake, BigQuery, Redshift, Databricks, and many other databases. Repo link below.

86,394 Aufrufe • vor 2 Monaten

The first open-source implementation of the paper that will change automatic test generation is now available! In February, Meta published a paper introducing a tool to automatically increase test coverage, guaranteeing improvements over an existing code base. This is a big deal, but Meta didn't release the code. Fortunately, we now have Cover-Agent, an open-source tool you can install that implements Meta's paper to generate unit tests automatically: I recorded a quick video showing Cover-Agent in action. There are two things I want to mention: 1. Automatically generating unit tests is not new, but doing it right is difficult. If you ask ChatGPT to do it, you'll get duplicate, non-working, and meaningless tests that don't improve your code. Meta's solution only generates unique tests that run and increase code coverage. 2. People who write tests before writing the code (TDD) will find this less helpful. That's okay. Not everyone does TDD, but we all need to improve test coverage. There are many good and bad applications of AI, but this is one I'm looking forward to make part of my life.

The first open-source implementation of the paper that will change automatic test generation is now available! In February, Meta published a paper introducing a tool to automatically increase test coverage, guaranteeing improvements over an existing code base. This is a big deal, but Meta didn't release the code. Fortunately, we now have Cover-Agent, an open-source tool you can install that implements Meta's paper to generate unit tests automatically: I recorded a quick video showing Cover-Agent in action. There are two things I want to mention: 1. Automatically generating unit tests is not new, but doing it right is difficult. If you ask ChatGPT to do it, you'll get duplicate, non-working, and meaningless tests that don't improve your code. Meta's solution only generates unique tests that run and increase code coverage. 2. People who write tests before writing the code (TDD) will find this less helpful. That's okay. Not everyone does TDD, but we all need to improve test coverage. There are many good and bad applications of AI, but this is one I'm looking forward to make part of my life.

774,488 Aufrufe • vor 2 Jahren

Intelligence withdrawal will be brutal. Model tokens are heavily subsidized. Subsidies are disappearing, and with them, so is easy "intelligence". This is the reason for Anthropic and OpenClaw's divorce. This should be a wake-up call for everyone building on top of a single provider. Your AI setup shouldn't depend on someone else's business model.

Intelligence withdrawal will be brutal. Model tokens are heavily subsidized. Subsidies are disappearing, and with them, so is easy "intelligence". This is the reason for Anthropic and OpenClaw's divorce. This should be a wake-up call for everyone building on top of a single provider. Your AI setup shouldn't depend on someone else's business model.

116,165 Aufrufe • vor 3 Monaten

Nobody is writing 90% of their code using AI. Here's the uncomfortable truth: The real productivity gain from using AI to write code is closer to 10%, nowhere near the 90% people claim. Sundar Pichai said in 2024 that 30% of the new code at Google was AI-generated. However, he went on to admit, during Lex Friedman's podcast, that engineering velocity had only increased by about 10%. AI-generated code isn't free code. It still has to be reviewed, tested, and made production-ready. Optimizing a single step (code generation) doesn't boost output if bottlenecks shift elsewhere (code reviews). It doesn't matter how much code you generate if you can't keep up the review process. The solution: Automate as much as you can the review and verification of your code. I'm working with Sonar, who is sponsoring this post, and they will take care of the code quality and security analysis of your code: • They review over 300B lines of code every single day • They cover reliability, security, and maintainability for your code • You can integrate them into your CI/CD pipeline • You can install them in your IDE (I use their VSCode extension) • Support for more than 30 languages Here is a link so you can check them out:

Nobody is writing 90% of their code using AI. Here's the uncomfortable truth: The real productivity gain from using AI to write code is closer to 10%, nowhere near the 90% people claim. Sundar Pichai said in 2024 that 30% of the new code at Google was AI-generated. However, he went on to admit, during Lex Friedman's podcast, that engineering velocity had only increased by about 10%. AI-generated code isn't free code. It still has to be reviewed, tested, and made production-ready. Optimizing a single step (code generation) doesn't boost output if bottlenecks shift elsewhere (code reviews). It doesn't matter how much code you generate if you can't keep up the review process. The solution: Automate as much as you can the review and verification of your code. I'm working with Sonar, who is sponsoring this post, and they will take care of the code quality and security analysis of your code: • They review over 300B lines of code every single day • They cover reliability, security, and maintainability for your code • You can integrate them into your CI/CD pipeline • You can install them in your IDE (I use their VSCode extension) • Support for more than 30 languages Here is a link so you can check them out:

296,363 Aufrufe • vor 9 Monaten

What will happen when OpenAI, Anthropic, and Google raise the price to access their latest models by 10x?

What will happen when OpenAI, Anthropic, and Google raise the price to access their latest models by 10x?

112,265 Aufrufe • vor 3 Monaten

The Framework 13 Pro is the best PC laptop I've ever tried. For the first time in a long time, I'm excited about computers again.

The Framework 13 Pro is the best PC laptop I've ever tried. For the first time in a long time, I'm excited about computers again.

86,423 Aufrufe • vor 2 Monaten

Back in 2010, we could get away with SSH keys and API tokens in .env files. We can't do that anymore. I went down a rabbit hole to understand how identity-based access is much better (and it's replacing) static credentials.

Back in 2010, we could get away with SSH keys and API tokens in .env files. We can't do that anymore. I went down a rabbit hole to understand how identity-based access is much better (and it's replacing) static credentials.

76,378 Aufrufe • vor 2 Monaten

Knowledge graphs are infinitely better than vector search for building the memory of AI agents. With five lines of code, you can build a knowledge graph with your data. When you see the results, you'll never go back to vector-mediocrity-land. Here is a quick video:

Knowledge graphs are infinitely better than vector search for building the memory of AI agents. With five lines of code, you can build a knowledge graph with your data. When you see the results, you'll never go back to vector-mediocrity-land. Here is a quick video:

398,030 Aufrufe • vor 1 Jahr

Here is how you can give Claude Code access to any data that exists online. It's an easy way to make it 10x more powerful than it already is. For example: Use Claude Code to find open LinkedIn jobs in your area, tailor your resume to them, and apply for them automatically.

Here is how you can give Claude Code access to any data that exists online. It's an easy way to make it 10x more powerful than it already is. For example: Use Claude Code to find open LinkedIn jobs in your area, tailor your resume to them, and apply for them automatically.

178,854 Aufrufe • vor 5 Monaten

This is a trillion-dollar industry, and you can't solve it with an LLM: • Forecasting • Fraud detection • Churn prediction Large Language Models are fundamentally bad at solving these problems. When you feed structured data into an LLM, it doesn't see relationships, and it treats every number, date, and foreign key as a token. That's why you always get garbage back. An LLM thinks your database is a Wikipedia article. It doesn't understand its structure or its relationships. GPT-4 scores 63% on relational prediction tasks. That's the best it can do, and that's pretty much useless. You can't expect real-world business value to come from summarizing Wikipedia articles.

This is a trillion-dollar industry, and you can't solve it with an LLM: • Forecasting • Fraud detection • Churn prediction Large Language Models are fundamentally bad at solving these problems. When you feed structured data into an LLM, it doesn't see relationships, and it treats every number, date, and foreign key as a token. That's why you always get garbage back. An LLM thinks your database is a Wikipedia article. It doesn't understand its structure or its relationships. GPT-4 scores 63% on relational prediction tasks. That's the best it can do, and that's pretty much useless. You can't expect real-world business value to come from summarizing Wikipedia articles.

94,701 Aufrufe • vor 3 Monaten