It’s easy to pump out lots of shitty, insecure software using LLMs. My hope, however, is that in the future good programmers will use AI to create better, more secure software.

First of all, LLMs still suck at software architecture. It’s up to a human to define the overal architecture and structure of a project.

It will also require a human to define the requirements, constraints and tests a module needs to conform to. With sufficiently clear and restrictive requirements and conatraints, the LLM can then generate and modifie the code until it meets all the requirements and produce something acceptable.

I also expect AI will make formal verification, where you mathematically prove your code meets certain criteria, feasible for more than a handful of projects. It doesn’t really matter if a vibe coded formal proof is unreadable and convoluted. If the proof passes verification your code is correct (assuming your assumptions weren’t wrong).

So IMO useful skills for the future include software architecture, compile-time guarantees and advanced type systems, test-driven development (TDD) and possibly formal verification.

Personally I’m trying to learn Lean 4 and formal verification right now, to see how well AI can assist with proofs.

The first two things I remember doing are visiting the official X-Files website, www.trustno1.com, and looking for cool pictures of space ships from Star Trek.

There is a Python library for everything. That’s what makes out so versatile. If performance is not an issue and it doesn’t need to run in the browser, Python is virtually always an option.

I thought A Minecraft Movie was a fun watch and I’d like to see Jason Momoa do more comedy.

I’ll have to try this out. I couldn’t get Microsoft’s ternary bitnets running on llama.cpp or ollama.

Good job, Mozilla! But Edge isn’t the only browser resorting to dark patterns nowadays. Think you might be able to so something about this?