It’s like saying you don’t want to exercise because it induces tachycardia and hypertension. The point is that you are training your body to adapt to overstimulation in a context and dose dependent manner.
> Some people never get to the part where they review the code. They go straight to their LinkedIn or blog and start writing (or having ChatGPT write) posts about how manual coding is dead and they’re done writing code by hand forever.
Some people review the code and declare it unusable garbage, then also go to their social media and post how AI coding is completely useless and they’re not going to use it for anything. This blog post shows the journey that anyone not in one of those two vocal minorities is going through right now.
What’s really happening is that you’re all of those people in the beginning. Those people are you as you go through the experience. You’re excited after seeing it do the impossible and in later instances you’re critical of the imperfections. It’s like the stages of grief, a sort of Kübler-Ross model for AI.
OP should expand on #1, why he thinks it’s garbage. Claude Code is the REPL harness Anthropic built, can read, write, edit, bash. Pi, Gemini, Codex do the same, but they are not hinted as garbage. Where’s the beef?
Vendor lock-in is real and it’s scary. You are helpless to the constant price increases and each passing renewal you get deeper and deeper into the lock-in. Here’s to the day when someone clever with AI can disintermediate this situation. You don’t have to vibecode your own CRM but imagine a deterministic harness that lets you lego-block CRM functions like lead management, opportunity tracking, contact list, campaigns. There shouldn’t be a moat anymore.
Not really. Mixture of models and mixture of experts have been around. It’s easy to switch a project harness from Codex to Claude to Gemini and to open models. You’re not locked in to a model, you’re more concerned about competitive token cost.
I still remember in 2016 when Elon Musk made a big announcement about his "acqui-hire" of the Dalhousie University EV battery research team led by Dr Jeff Dahn. There was much fanfare and announcements of million-mile batteries and 3% increase in energy density every year.
Moving on from miracle batteries to Thai rescue to Hyperloop tunnels and presently to data centers in orbit.
Elon is a fraud but Jeff Dahn and Dalhousie are legit.
Lithium batteries have been increasing in density at about twice that rate for the last decade. And million mile LFP batteries are available, NCM is nearing that benchmark.
All credit to the people who actually research and build them which is not Elon, since Tesla don't even produce the majority of their own battery usage.
It’s so exciting to read more and more articles like this, using LLMs to discover clever solutions. I mean how many of us have dreamed of scanning years of receipts, waiting for that moment when you know a DIY solo application is at hand. I’m not being sarcastic, I too have a drawer full of Costco receipts which to me are data waiting for insight, not just crinkly paper. It’s more than being clever, it’s the realization of using a device not as a tool, but an equal partner who can suggest what tools and approaches to do. The end product of the LLM is not the point (although it can produce it better than ever), it’s the way an LLM can elevate messy knowledge work. A single person can now say that analysis knows no bounds.
reply