Roger Kitain

Anthropic, the company best know for being compelled to pay a $1.5B settlement for its massive theft of copyrighted texts, issued a C&D against "clawdbot" for resembling its trademarked model name. #so #Claude #clawdbot #copyright #trademark

24

9 Comments

Anthropic just dropped Claude Code Review → multi-agent swarm auto-scans every PR for bugs, verifies findings, ranks severity. Internal stat: substantive reviews jumped 16% → 54%, catches ~7.5 real issues on big PRs. $15–25/review beta for Team/Ent. Game changer or expensive lint? 👀 https://lnkd.in/eVpR_vyD

8

Here's a simple framework to build systems that scale. Track: Notice what you're doing repeatedly Note: Add to your automation wishlist Just Do It: Start your day with twenty minutes of system building Today I built a UI testing loop in Claude Code that runs iterations automatically. No more sitting there, running the same tests manually, waiting for results. Five minutes saved per test. Twenty tests a day. That's 100 minutes back. But here's what most founders miss about systems: They wait for the "right time" to build them. When things calm down. When they have bandwidth. When the crisis passes. They're still waiting. I keep a simple list in my notes app. Every time I catch myself doing something twice, it goes on the list: "Manually copying customer data between systems" "Rewriting the same email response" "Running the same code tests" Then every morning, before the chaos starts, I pick one thing. Twenty minutes. That's it. This morning's automation will save me hours this week. Last week's Gemini CLI setup now transcribes thousands of calls while I sleep. Monday's Superwhisper setup means I speak emails instead of typing them. Small wins compound. Six months ago, I was manually formatting every email. Now Superwhisper handles it while I talk. A year ago, I was copying data between systems. Now APIs do it while I sleep. The compound effect is real. But it only works if you start. What's one thing you'll automate in the next 20 minutes?

4

2 Comments

If you're unfamiliar with the practice of software engineering, building a compiler seems like the Manhattan project. From scratch? You'd be right. Just their input, the specification for the programming languages that feed them, are the most detailed and precise standards, honed by committees and practice, the last bastion of waterfall in a predominately agile environment. Implementation over decades, closing edge cases, resolving spec ambiguity, a slow pursuit of necessary perfection refining the very definition of correct. The code part though? Implementation? Fairly trivial. An undergraduate assignment to build a simple compiler. Anthropic steps up to one of the most precise specifications you could ask for, the most unrealistic and ideal situation to test their agent. It has a model trained on a corpus containing all kinds of practical compiler implementations and their test cases. Billions of lines of compliable code with their own test cases. Fifty years of textbooks, courses, assignments, to tie higher level concepts together. Zero ambiguity in spec. The result? Failure spun as a revolution. Marketing for those who think the value in GCC's 37 years of development is the lines of code delivered. No assembler, no linker. 100kloc of poor quality parser/transformer that barely scrapes through test suites. "Engineering jobs obsolete as primary school class builds a bridge from spaghetti". This is the current limit of agentic coding: Loosely constrained mad-libs for when you don't care about or understand the problem space. Prototypes. Glue. The new spreadsheets of integration. "Haha now make the bear have a beer", but for code. "Yes I'm an excellent programmer / artist / communicator".

61

18 Comments

Something I said in a thread elsewhere, which bears repeating here: I think the reason the C programming language excited people back around 1980-85 is that, for the first time, we had a programming language that really did replace assembler -- it gave you an efficient way to do basically anything the computer could do. Previous programming languages, especially FORTRAN and BASIC, didn't give you the full capabilities of the computer directly. They were designed to put a layer of separation between the programmer and the CPU, the way R, for instance, does today. FORTRAN in particular had a strong emphasis on portability. BASIC had a strong emphasis on the things a beginner would want to do. C made it easy to program down to the bare metal, so to speak.

43

16 Comments

The next programming language could very well be called 'English'. Many programmers today have no clue how a transistor or gate works. Even many comp sci grads don't understand how modern operating systems work -- the very ones they are writing software for! For many, things like assembler or lower level languages like C aren't used anymore in favor of higher level languages like Python or PHP. But the next generational development seems to push even these 'easier' languages aside in favor of... well written prompts in English... or whatever language you speak the best ;)

17

4 Comments

"Angular is becoming Razor Pages." That’s what my teammate told me today. He was referencing Angular’s new @if control flow syntax and jokingly predicted the death of *ngIf by Angular 21. He ended his argument with the classic hot take: "Dotnet >>> Angular." I had to remind him why we chose Angular for our frontend. While the syntax might look familiarly chaotic to backend developers right now, the behavior is strictly next-gen frontend architecture. We aren't dealing with server-side rendering that requires a clunky full page reload every time a user submits a form. Angular provides an ecosystem that delivers a seamless feel that older backend technologies struggled to achieve on their own: ✅ True SPA Experience: No flickering reloads. The app feels native and fluid. ✅ Signals & Zoneless: We are rapidly moving toward a world where change detection is surgical and incredibly performant. ✅ Enterprise Dependency Injection: A structured way to manage code that other frameworks are still trying to bolt on via third-party libraries. ✅ Deferrable Views: The built-in ability to prioritize exactly what loads when (@defer) is a massive win for Core Web Vitals. We can borrow helpful syntax ideas from the backend, but the User Experience is pure frontend magic. ✨ Are you Team Angular or Team .NET for modern web apps? #Angular #WebDevelopment #RazorPages #UI #SoftwareEngineering #DotNet #Frontend #TechDebate #JavaScript #TypeScript

36

5 Comments