In some of my previous posts I’ve talked about playing around with “vibe coding” tools, more specifically the more hands-on ones like Cursor and Windsurf where I can still jump in if needed. Every time I have an idea for a silly or stupid app just for myself, I tend to gravitate towards these tools, not because I can’t be arsed to do it myself, but because I’m genuinely curious about how well these perform and how much they improve over time. ...
The Gell-Mann Amnesia Effect It describes how someone reads an article in their area of expertise, finds it full of errors and oversimplifications, but then turns the page and takes the next article, on a subject they know nothing about, at face value. I only learned this term recently, although I’ve always kinda knew and understood the concept. And with all the content LinkedIn and YouTube have been force feeding me, I’ve been thinking about how this idea extends beyond just “reading the news” to our skills and expertise. ...
I’ve been playing around with Cursor and Windsurf, because I keep seeing on social media how great these tools are and how easy it is to build things. And you know what? It’s…. ummm… better than before? Okay, look, it’s impressive. If I compare it so some earlier versions of the IDEs and other tools like Bolt.new, sure, it’s improved. But sheesh, does it take poking and prodding and coddling to get somewhere. Maybe I’m using it wrong, I don’t know, but I wish I could share the transcripts of my chats with these tools so you’ll understand… (can I export those? am I missing a feature somewhere?) ...
Wow, the new Mac Studios look really impressive. I can’t find the post that I saw last night about it, so I can’t share that author’s thoughts (I thought I commented or reacted at least, apparently not…), but what was interesting is the M3 Ultra goes up to 512GB of unified memory. 512GB… Of unified memory… If you’ve been playing with LLMs locally, and you have Apple Silicon, you’ll know that Apple’s unified memory is pretty performant, and it’s great for running local LLMs because the GPU uses the same system memory as the CPU, which means it can access most if not all of the RAM. ...
🎯 This morning’s YouTube recommendation: someone coding purely by voice using Cursor agents and Windows dictation tools. My first thought? Not “wow, how cool!” but “seriously, is typing that hard now!?” 🙄 My second thought: “Good luck remote debugging a Linux server at 1am to fix what your AI buddy broke…” First we outsource thinking to AI, now the typing… it’s like nobody wants to actually do this job anymore! 🤦 But here’s the thing - after my initial skepticism, I realized this IS actually pretty cool. Just not for the reasons filling up your social media feed. ...
🤖 I love how every new LLM release triggers a wave of “AI is coming for your job!” posts, only for people to realize a few weeks later “oh, nope, sorry, not this yet” 😏 💡 While AI tools are certainly force multipliers for productivity, even with agents, they’re not replacing humans yet. Even the best apps I’ve generated with Bolt or Replit eventually need human intervention and fixing. 🎯 Hot take incoming: I find it amusing when people consider these simplistic example AI-generated “apps” as “real development”. Most modern webapps are already essentially just careful combinations of frameworks and styling, using existing tools that solve problems in generic ways. That’s not novel software development. ...
🌱 As 2024 enters the rear-view mirror and we look forward to 2025, this is usually an opportune time to reflect and plan. Those who know me personally are aware that 2024 was a challenging year with personal loss and challenges in the extended family, as well as some health issues, but it was also one with opportunity and challenges (some I chose for myself). 💼 I’m extremely grateful for the support I’ve received after starting PiForge. It’s been an amazing start for a new company, and while the last few months have been challenging with deadlines and extra hours, I look forward to what that means for the future. ...