Great message from the Pope (I never thought I'd write those words). I'm glad he recognizes what's going on with AI (LLMs, really) as one of the highest areas of concern for humanity and the Earth and is using his influence to encourage things like renewable energy investment. It's a shame he isn't in a position of "real" power and we're still at the mercy of the worst U.S. president in history.

One thing that isn't talked about enough is how so much is going into AI but not much is coming out of it. The rhetoric from tech bros is still that AI is "going to" change the world. Hasn't really changed the world yet, except driven up everyone's utility bills and put hundreds of thousands of people out of work.

I encourage people, especially software engineers here, to remember the previous "new hotness" tech advancements - blockchain and NoSQL DBs being two recent examples. In both instances there was a flood of VC money into startups that have mostly failed because each was supposed to change the world (or at least change software). I spent a lot of my free time in those days trying to "find a problem" for blockchain and NoSQL to solve. I remember thinking I must be a lousy software engineer because I just wasn't getting the hype. Now I know it's because whenever something new comes out, people talk about how it can do X Y and Z, and there's a disconnect between what a technology CAN do, and what it SHOULD do. I can use blockchain for all sorts of things, but in most cases it wouldn't be the best option. Same for NoSQL DBs. Same for LLMs. The more you understand blockchain, the more you realize it's only good as a globally-distributed, immutable ledger - and currency is the only practical application of that in our society today (e.g., Bitcoin). NoSQL is the same way - yeah you can use MongoDB for whatever app, but it's going to be a bad time maintaining and scaling when you're storing relatively simple and consistent records. A CRUD app usually doesn't warrant a NoSQL DB.

LLMs are the same. I'm finding they are good at search-type tasks, where frankly not much "thinking" is involved. Therefore, with respect to writing software, they are best suited for simple, internal tools. Even then, I have to baby it, especially with today's LLMs. Claude Opus has been nerfed (most-likely quantized) to make space in the datacenters for Mythos, and eventually Mythos will be bad too for the same reasons. The question becomes, as it always has, "will LLMs rise up to the challenge" and history tells us "no." These things never live up to the hype. When you understand how LLMs work, you understand why ChatGPT 3.5 isn't that much worse than GPT 5.5, artificial benchmarks be damned.