I’m not sure how to explain it, but the more I see LLM-written code the more I feel it’s bad code doing a good job of masquerading as good code. I think this take will become less-hot in the next year or two when we see enterprise greenfield projects that were created entirely with LLM “assistance” go to prod. I think we’ll find that the code is difficult for humans to read, understand, debug, and extend- and I think the larger the codebase the harder it will be for LLMs to maintain. More opportunity for hallucination, larger context windows needed, more tokens bought and spent for smaller and smaller code changes. I think the more code an LLM writes for an app, the worse that codebase becomes.

So a PE of 500 means it would take 500 years for the earnings of the company to equal the current market cap (price per share X number of shares). This implies absurd (almost certainly impossible) growth over the next 500 years. Of course anyone expecting to pull their investment out and spend it on retirement can’t be looking at a 500-year investment horizon. I suppose the 1% can, though. What the hell else are they going to spend their cash on?

We no longer have the luxury of welcoming bootcamp engineers into our field with open arms. We need to protect our craft. Call these fools out or they'll keep spreading hype/FOMO.

Some people have suggested you write the unit tests by hand to basically "check" the LLM's work and keep it honest, but to write good unit tests you have to understand the underlying code, which takes time (since you didn't write it), so to me this is another bullet point that suggests LLMs will eventually be relegated to "StackOverflow+" duty - give me snippets, but I'll still write effectively all the code.

So I’m thinking we’ve just about reached apex with LLMs, and they have failed at replacing software engineers (companies can freeze hiring juniors at their own, future peril using any excuse they like).

So the problem for me is that I’ve noticed a trend with my coworkers- they usually don’t have a formal CS background (e.g., Comp Sci degree), their resumes are unimpressive, and they have personal websites where anyone can download a copy of their resume. I haven’t seen this at any previous job. It’s just weird, man. Anyway, so my problem is when they are purported to be the best of the best at this company, and they’re chugging the LLM kool-aid, I’m struggling to figure out whether they’re really ahead of the curve and getting the drop on the rest of us, or they’re doing basically no work and waving through each other’s PRs with little to no oversight on what the LLMs are writing. The bush league nature of many of the bugs I’m seeing going all the way to prod makes me think it’s the latter.

Meanwhile, these guys and their teams are completing an absurd number of story points each sprint. My team is dead last (and coincidentally we’re all pretty anti-AI for writing code).

I’m waiting for the other shoe to drop. I’m waiting for the C suite to call our project a failure and lay everyone off. The product generally works, though I think if the devs were truly rockstars, things would be much smoother. It seems like LLMs are letting middle-of-the-road or mediocre devs appear to be rockstars purely on output speed. Nobody in this org cares if the output has 4x the bugs it should have, just that it was completed quickly.

The main issue I think is that nobody- including the rockstar tech leads- knows how the system works. They don’t know the code. There’s a bug and it takes forever to track down. Don’t ask about unit tests.

I think in a perfect world, these LLMs are treated like another tool rather than another person- meaning you and I still write a large portion of the code, and we read and understand every line- especially the lines generated by LLMs. It’s still a huge productivity multiplier for me to not have to remember how to do mundane things like write out arrays into CSV files- before I’d find a close implementation on StackOverflow and tweak to my needs. Now I can just describe what I want the CSV to look like and Claude Code generally gets it right on the first try.

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.

I mean there’s no way average joes like us stand a chance doing anything but dollar cost averaging into index funds.

E: imagine if there was a law passed that required those IMs to be public in near-real-time (releasing the transcripts days later defeats the purpose).

I remember some startup selling a stock market data API as a subscription. I don’t think they exist anymore. So anyone who spent weeks, months of their free time building an app around that API is now completely shit out of luck.

I suspect the real APIs are still running the same code they ran in the 90s and if you have to ask how much they cost, you can’t afford them.