Yea, my issue with Opus 4.5 is it's the first model that's good enough that I'm starting to feel myself slip into laziness. I catch myself reviewing its output less rigorously than I had with previous AI coding assistants.
As a side project / experiment, I designed a language spec and am using (mostly) Opus 4.5 to write a transpiler (language transpiles to C) for it. Parser was no problem (I used s-expressions for a reason). The type checker and transpiler itself have been a slog - I think I'm finding the limits of Opus :D. It particularly struggles with multi-module support. Though, some of this is probably mistakes made by me while playing architect and iterating with Claude - I haven't written a compiler since my senior year compiler design course 20+ years ago. Someone who does this for a living would probably have an easier time of it.
But for the CRUD stuff my day job has me doing? Pffttt... it's great.
Trivyn: Ontology-first knowledge platform. Runs on a single machine, via a single executable. I wanted a simpler alternative to the large complicated enterprise products that tend to dominate this space.
I'm really trying to get a private beta out the door by Christmas. I do plan to have a free version for academic/personal use.
Backend is written in Rust, uses oxigraph for its triple store.
I've found most LLMs I've tried generate better code in typed, procedural languages than they do in something like Clojure.
From the perspective of a primarily backend dev who knows just enough React/ts to be dangerous, Claude is generating pretty decent frontend code, letting me spend more time on the Rust backend of my current side project.
> generate better code in typed, procedural languages
Better in what sense? I've been using Anthropic models to write in different Lisps - Fennel, Clojure, Emacs Lisp, and they do perform a decent job. I can't always blindly copy-and-paste generated code, but I wouldn't do that with any PL.
Yea, my house is on Starlink... so at the moment I'm working in the back room of my wife's restaurant (she has cable internet). At least I get free coffee here.
Hiring managers and HR area increasingly only open to unicorn candidates that have the exact amount of experience in the exact tech stack. While a few of those people exist, it's definitely more likely they end up interviewing people that are open to lying. So now your pipeline is filled with 90% liars, some just small white lies and others who have made a resume that has exclusively tailored lies just for your org.
The jobs aren't that hard and many people that fudged their experience are capable, so the liars that are hired perform adequately and hiring team sees no reason to adjust their strategy.
Eventually this gets out-of-hand as people learn to further exploit these practices.
I’ll be surprised if it does. Software jobs are slumping for several reasons and the section 174 hack fixes one for a while but causes between one to four other problems depending on where you live.
I worked in defense contracting for most of my ~20 year career up until a few months ago. So I'm experiencing this culture shock the other way around. Being the oldest person on a team is... strange.
Still have my clearance for a couple years I suppose - perhaps all this anti-remote madness will be over before then.
Been coding on the JVM for a good chunk of my career. Though the last several years has been in languages other than Java - Scala, Clojure (my personal favorite), and Kotlin.
Finally managed to get a job offer (after being unemployed for a bit) doing Python. It's starting to look like demand for JVM experience is beginning to wane. Might be time to move on anyway :shrug:
I'm old... as long as there's a steady paycheck involved, I'll code in whatever language you say.
Though, currently working on a little personal project in Scala. :)
It's not just software -- My wife owns a restaurant. Operating a restaurant you quickly learn the sad fact that quality is just not that important to your success.
We're still trying to figure out the marketing. I'm convinced the high failure rate of restaurants is due largely to founders who know how to make good food and think their culinary skills plus word-of-mouth will get them sales.
My wife ran a restaurant that was relatively successful due to the quality of its food and service. She was able to establish it as an upper-tier experience, by both some word of mouth, but also by catering to right events, taking part in shows, and otherwise influencing the influencers of the town, without any massive ad campaigns. As a result, there were many praises in the restaurant's visitor book, left by people from many countries visiting the city.
It was not a huge commercial success though, even though it wasn't a failure either; it generated just enough money to stay afloat.
If it paid for people's lives and sustained itself, that sounds like a huge success to me. There's a part of me that thinks, maybe we'd all be better off if we set the bar for success of a business at "sustains the lives of the people who work there and itself is sustainable."
> There's a part of me that thinks, maybe we'd all be better off if we set the bar for success of a business at "sustains the lives of the people who work there and itself is sustainable."
This would be beautiful in a world where retirement was better and it didn’t feel like inflation or financial crashes are looming around the next corner most of the time.
For many folks, trying to get savings and putting money into investments is less about wanting a lavish lifestyle later and more about just wanting financial security in case something bad happens.
> you quickly learn the sad fact that quality is just not that important to your success.
Doesn't that depend on your audience? Also, what do you mean by quality?
Where I live, the best food can lead to big success. New tiny restaurants open, they have great food, eventually they open their big successor (or their second restaurant, third restaurant, etc.).
I believe this is called something like the 'Michelin Curse' but my google is not returning hits for that phrase, though the sentiment seems roughly correct [0]
In the restaurant business, the keys are value and market fit.
There is a market for quality, but it's a niche. Several niches actually.
But you need to attract that customer. And the food needs to be interesting. And the drinks need to match. Because foodies care about quality but also want a certain experience.
Average Joe Blow who dines at McDonald's doesn't give a flying fuck about quality, that's true. Market quality to him and he'll probably think it tastes worse.
If you want to make quality food, everything else needs to match. And if you want to do it profitably, your business model needs to be very focused.
It can't just be the same as a chain restaurant but 20% more expensive...
As a side project / experiment, I designed a language spec and am using (mostly) Opus 4.5 to write a transpiler (language transpiles to C) for it. Parser was no problem (I used s-expressions for a reason). The type checker and transpiler itself have been a slog - I think I'm finding the limits of Opus :D. It particularly struggles with multi-module support. Though, some of this is probably mistakes made by me while playing architect and iterating with Claude - I haven't written a compiler since my senior year compiler design course 20+ years ago. Someone who does this for a living would probably have an easier time of it.
But for the CRUD stuff my day job has me doing? Pffttt... it's great.
reply