Mithilesh Said

Good tip for avoiding cognitive debt in codebases where AI has run wild: Design the interface, delegate the implementation

Claude Code (or Opus 4.6) feels like it asks you far fewer questions during plan mode Try: "Interview me relentlessly about every aspect of this plan until we reach a shared understanding. Walk down each branch of the design tree, resolving dependencies between decisions one-by-one."

Bought a new Mac mini to properly tinker with claws over the weekend. The apple store person told me they are selling like hotcakes and everyone is confused :) I'm definitely a bit sus'd to run OpenClaw specifically - giving my private data/keys to 400K lines of vibe coded monster that is being actively attacked at scale is not very appealing at all. Already seeing reports of exposed instances, RCE vulnerabilities, supply chain poisoning, malicious or compromised skills in the registry, it feels like a complete wild west and a security nightmare. But I do love the concept and I think that just like LLM agents were a new layer on top of LLMs, Claws are now a new layer on top of LLM agents, taking the orchestration, scheduling, context, tool calls and a kind of persistence to a next level. Looking around, and given that the high level idea is clear, there are a lot of smaller Claws starting to pop out. For example, on a quick skim NanoClaw looks really interesting in that the core engine is ~4000 lines of code (fits into both my head and that of AI agents, so it feels manageable, auditable, flexible, etc.) and runs everything in containers by default. I also love their approach to configurability - it's not done via config files it's done via skills! For example, /add-telegram instructs your AI agent how to modify the actual code to integrate Telegram. I haven't come across this yet and it slightly blew my mind earlier today as a new, AI-enabled approach to preventing config mess and if-then-else monsters. Basically - the implied new meta is to write the most maximally forkable repo and then have skills that fork it into any desired more exotic configuration. Very cool. Anyway there are many others - e.g. nanobot, zeroclaw, ironclaw, picoclaw (lol @ prefixes). There are also cloud-hosted alternatives but tbh I don't love these because it feels much harder to tinker with. In particular, local setup allows easy connection to home automation gadgets on the local network. And I don't know, there is something aesthetically pleasing about there being a physical device 'possessed' by a little ghost of a personal digital house elf. Not 100% sure what my setup ends up looking like just yet but Claws are an awesome, exciting new layer of the AI stack.

A super interesting new study from Harvard Business Review. A 8-month field study at a US tech company with about 200 employees found that AI use did not shrink work, it intensified it, and made employees busier. Task expansion happened because AI filled in gaps in knowledge, so people started doing work that used to belong to other roles or would have been outsourced or deferred. That shift created extra coordination and review work for specialists, including fixing AI-assisted drafts and coaching colleagues whose work was only partly correct or complete. Boundaries blurred because starting became as easy as writing a prompt, so work slipped into lunch, meetings, and the minutes right before stepping away. Multitasking rose because people ran multiple AI threads at once and kept checking outputs, which increased attention switching and mental load. Over time, this faster rhythm raised expectations for speed through what became visible and normal, even without explicit pressure from managers.

On the one hand, AI influencers are breathlessly raving about Claude Code, Clawdbot, and Cowork. And on the other hand, most people I know—even software engineers—are despondent, overwhelmed about how everything is changing so quickly. I hear this from people early in their careers especially, a fear that everything they've learned and the skills they've gained are rapidly being devalued. This is a mental trap. Don't fall for it. You should not just be watching from the sidelines or reading articles about "how software engineering is changing." Imagine it was 1993 and the personal computer revolution was kicking off. If you could go back in time to then, what should you have done? The answer: try everything. Buy a PC. Learn how to touch type. Figure out what the Internet is. Imbibe it all. Don't wait until it becomes a job requirement. That's exactly what you should do with AI. Try everything. Try Claude Code, try Clawdbot, try the Excel integrations, Veo, everything you can get your hands on. Learn what it's doing. Build your intuitions. Be one step ahead of it. Evolve alongside it. Don't lose your curiosity or get swallowed by anxiety or let yourself be convinced that you'll learn it when you have to. Think deeply about how AI will change the things around you—not society, that's too hard to project—but how it will change your job, your personal life, your immediate environment. No matter how old you are or young you are, no matter what stage of your career you are in, we are all going through the biggest technological change of the last 100 years, and we're going through it together. Nobody has the answers. It's obvious that so much is going to change, but nobody is going to figure it out before you do if you choose to stay at the frontier. So don't hide from it. Sit at the front of the class. Pay close attention. And be grateful that it's never been easier to stay at the frontier of the most important technology change of our lifetimes.

I work with multiple companies where nearly all code is AI generated now. However, the productivity probably has only increased 20-30%. Why? I suspect because writing code is really running code. Changes are the result of a business learnings. Or an operational learnings. For mature companies, the majority of PRs are sub 10 lines codifying these learnings. AI clearly helps here (e.g. debugging, running tests, building tools) but less so. Operations and business learnings are workload and company specific. Until AI can perfectly predict what the market needs, or how a system will be used this bottleneck will exist.

We built a browser with GPT-5.2 in Cursor. It ran uninterrupted for one week. It's 3M+ lines of code across thousands of files. The rendering engine is from-scratch in Rust with HTML parsing, CSS cascade, layout, text shaping, paint, and a custom JS VM. It *kind of* works! It still has issues and is of course very far from Webkit/Chromium parity, but we were astonished that simple websites render quickly and largely correctly.