ראיון הקבלה ל-yc אורך רק 10 דקות, ובו 3 פרטנרים צולבים אתכם בשאלות על המוצר שלכם. 7 וחצי בערב, 24 שעות אחרי שקיבלתי מייל וזמנו אותי לראיון. אני בתל אביב, גל באיזו חווה בויאטנם. /1

שומע את השיחה של @naftalibennett אצל @NadavPerry והרבע שעה הראשונה על AI פשוט מביכה. רק הוכחה למה אסור למדינה להתערב בתחום הזה עם כל מיני הזיות של ״מודל כחול לבן״

כתבות שהמילה לא היא המילה היחידה שצריכה להיות בהם

התארחתי אצל @OmriBarak ו @Tsuker לדבר על מודלי קוד פתוח ולמה (כרגיל) ההייפ קצת מוגזם. היה כיף youtu.be/8tkfh36yaBc?is=l3JQ…

INSANE Vercel just invented….. Cloud Computing?

In what world does more lines of code == more developer productivity?

היי טוויטר! מלחמה בחוץ אז חשבתי שזה זמן טוב לספר לכם ש-@traceloopdev, החברה ש-@GalKlm ואני הקמנו, נרכשה על-ידי ServiceNow! איכשהו בין טיל לאזעקה נחתם היום הסכם הרכישה (סיפור משוגע בפני עצמו, שנשמור לימים רגועים יותר)

This video was uploaded by OpenClaw. I didn't do anything. I just told @OmriBarak to send the video to my OpenClaw bot, and then it just uploaded it to my LinkedIn profile (hopefully!). This is what the future looks like. A lot of people have been asking me lately - what's the big deal with OpenClaw? Why is everyone talking about it? In my opinion, it comes down to 3 things: 1. Cron Jobs. Not a new concept - they've been around since the early days of Linux. Schedule something, and it happens. Simple. With OpenClaw, I've been using one to scrape Tel Aviv apartment listings and get a WhatsApp message every day at 7pm with the results. Old idea, powerful new use case. 2. Messaging channels. OpenClaw plugged into WhatsApp, Telegram, and more. And this matters more than people think. When I interact with it over WhatsApp, it genuinely feels like texting a person. The interface isn't an app or a dashboard - it's a conversation. That changes everything about how you think about automation. 3. It has its own computer. It can browse the web, read and create files, check my LinkedIn, install packages - basically anything you'd do on a machine. It's not just answering questions. It's actually doing things. Take those 3 ingredients - scheduled tasks, natural messaging channels, and a computer of its own - and you get something that feels less like a chatbot and more like a digital employee. Are we one step closer to AGI? Maybe. But we're definitely one step closer to a world where agents just... handle things for you. What would you automate first?

React is the worst framework for coding agents. Here's why Ruby on Rails might be making a comeback. When you use Claude Code or any other coding agent to work on a React codebase, the agent has no idea where anything is. Your DB models, your API calls, your business logic - they can sit literally anywhere. In a large codebase, this is a massive problem. The agent ends up spending a huge chunk of its context window just searching for the right files. And the more context it burns on navigation, the less it has for actually writing good code. Now think about the opposite scenario. What if the agent knew exactly where everything was from the moment it touched your codebase? That's Ruby on Rails. And yes, I know - we're talking about a framework from 2010. But hear me out. Rails has a strict convention: models go here, controllers go there, API calls live in this folder. Every Rails app follows the same structure. GitHub was built on it. Shopify still runs on it. Twitter started on it. That convention, which developers used to find restrictive, is exactly what makes coding agents 10x (maybe even 30x) more productive. The agent doesn't need to explore. It just starts working. React gave us flexibility. But flexibility has a cost when you're working with AI agents that rely on understanding your codebase structure to do their job well. Next time you're starting a weekend project and plan to use a coding agent heavily - consider Rails over React. The performance difference might surprise you. What framework are you using with your coding agents? Have you noticed the same issue?

We all saw the demos of Claude Cowork last month. They looked incredible. But honestly? I think we’re getting a little ahead of ourselves. Anthropic isn't quite solving the real problem yet. If you’ve ever tried to build a genuine AI copilot, you know there are two massive headaches you have to deal with: 1. Context Engineering: How do you engineer and build the right context so that the AI can actually answer your questions or solve your problem? For that, you can either use chunking (so you build a context that is right for answering a specific question), or using an agent. Then, you just give the agent the entire directory of data that you have, and then the agent can selectively choose the data that it needs to actually answer or solve the problem. 2. Integrations: This is much bigger, because you need to actually connect different data sources to your AI copilot or agent. All of this is largely solved for code just because code is basically text files in your computer. So you can give Claude Code access to your desktop directories and it just works. When thinking about productivity or an AI copilot for everything else, you need to connect to a lot of different tools. Think Gmail, Zoom, Calendar, and Notion, and many, many others. We tried to solve it with MCP, but it didn't really work. So, here is a wild thought. Maybe the solution isn't better APIs. Maybe the solution is just… files. Imagine if your Notion workspace was just a folder of markdown files on your desktop. Imagine if your Zoom calls were just text files sitting in a directory. Suddenly, you don’t need complex integrations. Claude Code could just read your "productivity stack" the exact same way it reads a Python script. I’m seriously thinking about testing this workflow. Has anyone else tried treating their entire work life as local files?

We're releasing today a cool new open source (link in the comments!) Over the past 2 years, we've helped teams debug everything from prompt issues to production outages. We kept running into the same problem: Jumping between our IDEs and our observability dashboards. So, we built an open-source MCP server that connects any OpenTelemetry backend (Grafana, Jaeger, Datadog, Dynatrace, Traceloop) to our dev environment using an MCP. While there are many MCP servers built for specific providers (like Datadog and others), they’re closed source (so we can’t easily extend them), and they’re locked to a single platform, so organizations that leverage multiple platforms, where data is scattered in between them, can’t really use them. We’re adding support for more providers every day - feel free to contribute your own. We would love your feedback and opinions - feel free to connect it to Claude or ChatGPT and try to investigate your own production data. What do you think about the set of tools that we currently expose? Do you think we should expose more or others?

אבל כבר יש אפליקציה שמציגה רק יצירות AI קצרות וחסרות משמעות לחלוטין היא נקראת לינקדאין

Yesterday, Claude betrayed me. He pushed some code he’d written straight into production. I just asked him to fix a bug and then to create a pull request, and instead, he decided to directly push his code to main, and from there it went straight to our production system. So then I see people on the Internet writing, "oh, so we just add some instructions on our Claude MD file - like "don’t push something directly to main" or "don’t delete my database". But that's wrong - Claude may or may not listen to my nice Claude MD file. When you think about it, the problem isn't Claude, it was me. I didn’t put the right guardrails in my system so that he couldn’t push something directly to production. When I used to work at Google, I could never just push some code straight to prod. Someone has to approve all my PRs, I needed to roll out new features with a feature flags, and so on. There were a lot of systems and guardrails in place preventing me from doing harm to the YouTube system I was working on. Even if I really wanted to, I couldn’t take YouTube down. Good systems prevent you from destroying themselves, even if you didn't mean to do that. So when you're thinking to yourself how do I prevent Claude from making mistakes - think about building the right guardrails so that Claude cannot push code to main, or cannot access your production databases etc. Otherwise, if you allow Claude to take your own system down, you’re at fault, not Claude.

אז אחרי שגוגל הכריזו שהם קונים את היזמים של windsurf, דווין החליטו לקנות את מה שנשאר cognition.ai/blog/windsurf