Future-of-Tech

I have not been “AI pilled” yet. (Also, what a stupid term.) While AI has become deeply integrated into my workflow, and I genuinely love having agents run things for me in the background while I focus on other things, I wouldn’t say I’ve had some red pill moment where “I see the truth now” and AI became an essential and daily thing… You see, my morning routine when I start work is the same: I open my terminal of choice (Warp), and I open my IDE of choice (whichever JetBrains one is applicable). And then if the task deems it, I’ll open Junie or Claude inside my IDE. ...

Do trust and accountability go hand in hand? This is something I’ve been chewing on over the weekend. And I don’t know really, but here’s where I’m coming from. One of my side projects at PiForge at the moment is building a system around Agentic Engineering using team lead principles I’ve honed over years, and applying how human teams communicate and organize over the SDLC to agents (i.e. start with a spec, write tickets on a kanban board, grab the next highest priority, work till done, test, PR, release, document). ...

Trigger warning: this is part rant, part genuine exploration, and entirely my opinion. As usual. Also; research heavy. I wanted this to be informed. I’ve been thinking about this one for a while. In a previous post I argued that not everyone who writes code is an engineer, and that the title carries expectations. In another I complained about the lack of standards in an industry that rewards speed and hype over depth. And more recently I got on my soapbox about fundamentals mattering — about how the people who actually understood the machines they worked on are slowly dying off, and what we’re being left with instead. ...

Just because your fancy new Claude Code plugin prints out “50% tokens saved” in the logs doesn’t mean you actually got them. I was playing around with Caveman Compression last week and tried to get the UserPromptSubmit hook to rewrite prompts using the tool for savings across the board. Turns out? The hook doesn’t allow it. Probably for security reasons; can you imagine the injection attacks if any random plugin could hook into and replace your prompts? ...

Previous post for context: Two AI Agents Walk Into a Codebase If you look at social media, everyone will tell you that most people are still using AI like a very fast keyboard. You write what you want, it writes the code, you review it, you move on. Faster, sure. But you’re still in the driver’s seat for every line, every file, every decision. They will also tell you that the future is not that. The future is swarms of AI agents doing the work of 100s of people. And I mostly agree. The shift that’s actually happening — and I say this as someone who’s spent the last month living inside it — is from writing code to directing agents. ...

🤔 The thing about how much AI agents and tools have improved is that I’m finding myself in a weird spot. I’m always working. Even when I’m not working, I’m planning and brainstorming in Claude Projects so I can use the spec and plan files later in Claude Code. In a recent interview with The Pragmatic Engineer, Mitchell Hashimoto, the founder of HashiCorp said his “new rule for building software: always have an agent running in the background doing something.” (link) ...

One of the reasons I’m saddened that formal debate isn’t taught in schools anymore is that we’ve lost a key skill in not only communicating, but also in critical thinking and research. In debate, you’d often have to argue for the side that doesn’t match your own personal view. You’d be forced to research, refine your understanding, and in some cases actually change your opinion because you realized you were wrong. Because that’s the thing about an opinion, right? Despite what the internet and social media will have you believe, it’s not fact. It’s not the whole truth. It’s your perspective on something. ...

Around a year ago I started one of my blog posts with this musing on “The Promise vs. Reality of AI in Tech”: I’m concerned about the industry’s direction with these [improvements in AI]. Instead of creating better developers, we’re often replacing them. Rather than building amazing accessibility tools, we’re creating deep fakes and virtual companions. Instead of developing better MVPs for real problems faster, we’re seeing low-quality products marketed as revolutionary simply because they were built without coding experience, for no purpose other than a quick cash-grab. ...

🚨 The guy who built Clawbot/Moltbot/OpenClaw just got hired by OpenAI. Let that sink in for a moment. This project is one of the biggest security nightmares of recent memory. Every day there are more stories of problems, exploits, vulnerabilities. Yet the project has gone viral in ways that few open source projects do, and people are eating it up. Meanwhile, I know developers who started similar projects and abandoned them specifically because of the security risks. They made the responsible choice. They understood the implications. They walked away. ...

We spend more effort learning how to prompt LLMs than we do communicating with other humans. People complain that AI is bad at understanding humans, but in truth, humans are rediscovering how bad we are at explaining ourselves. Prompting works because you’re forced to do interface discovery consciously. You test phrasing, observe outputs, refine assumptions. With humans, we think discovery is rude or inefficient, so we skip it. Then we’re shocked when the call fails. ...