My observation has been that there are a lot of personal styles to engaging with the LLMs that work, and "hold the hand" vs "in-depth plan" vs "combination" doesn't really matter. There is some minimum level of engagement required for non-trivial tasks, and whether that engagement comes mid-development, at the early design phase, or after isn't really that big of a deal. Eg; "Just enough planning" is a fine way of approaching the problem if you're going to be in the loop once the implementation starts.
It's a bad faith question or one so deeply uninformed that parent is correct. It only takes a couple clicks to see the ideas of the people who are "just asking questions".
I swear “check their post history” has got to be weakest form of ad hominem going. “I can deflect from answering difficult questions if I attack the messenger” is just so weak.
You are mistaken, probably not for the first time today.
To be clear, almost (all?) of mine do not either and it's partially due to the fact I have been really interested in formal methods thanks to Hillel Wayne, but I don't seem to have the math background for them. To the man who has seen a fancy new hammer but cannot afford it, every problem looks like a nail.
The origin of it is a hypothesis I can get better quality code out of agents by making them do the things I don't (or don't always). So rather than quitting at ~80% code coverage, I am asking it to cover closer to 95%. There's a code complexity gate that I require better grades on than I would for myself because I didn't write this code, so I can't say "Eh, I know how it works inside and out". And I keep adding little bits like that.
I think the agents have only used it 2 or 3 times. The one that springs to mind is a site I am "working" on where you can only post once a day. In addition, there's an exponential backoff system for bans to fight griefers. If you look at them at the same time, they're the same idea for different reasons, "User X should not be able to post again until [timestamp]" and there's a set of a dozen or so formal method proofs done in z3 to check the work that can be referenced (I think? god this all feels dumb and sloppy typed out) at checkpoints to ensure things have not broken the promises.
I guess my feeling is that formal verification _even in the LLM era_ still feels heavy-handed/too expensive for too little value for a lot of the problems I'm working on.
I guess I am trying to think laterally right now. There’s a lot of attention given to crafting the right prompt to get what you need, but I am a belt and suspenders kinda guy and my concern is even if we get it right the first time, what guarantee do I have I don’t ask for a change a year from now without thinking through the implications and it subtly breaks stuff. There’s basically zero cost to me currently to require formal verification, as long as we don’t count the oceans I am helping to boil.
UO Outlands has been pretty popular for a few years. They’ve implemented a lot of custom aspects (specialties), craft, new dungeons, land, as well as weekly quests and events. My brother and I play it a few hours a week. It’s incredibly popular for the nostalgia and its player base seems to be pretty consistent. It reminds me of early UO where your exploring, learning, and dying a lot. And there tends to be players everywhere you go.
Most active is UO Outlands. Several thousands players?
They've reworked a lot of systems and it's basically 100x better than original UO.
There are several systems in place, which original devs wouldn't even dream of and saying that, official Ultima Online is still running. :D
It's PvP server, but with balanced PvP which really works for everyone. Not like original devs, they just dropped PvP because cookie-cutter players cried.
Outlands is impressive from a technical standpoint, they've put an insane amount of work into it and the player count speaks for itself. I played there for a while.
Personally though, I feel they've overengineered it a bit. So many custom systems layered on top that it starts to feel more like WoW with UO graphics than actual UO. The original charm was in the simplicity
you, a sword, and a world that didn't care about your feelings. But that's just my taste, and clearly thousands of players disagree with me, so what do I know.
And yes, the fact that official UO is still running in 2026 is both beautiful and insane
This was the bummer to me when I tried it. I liked the bug-ridden classic experience before the notoriety patch.
I recently tried https://www.classicuo.eu/ ClassicUO, and the nostalgia was incredible. Granted it is not playable, but there is something about that experience that all of the assistants, hotkeys, etc. fail to capture.
Thanks! There are still a few active shards out there, mostly us "old guys" in our 40s chasing the nostalgia of our teenage years. UO has a way of never really dying. Combat and skills are still a ways off,
but the foundation is solid enough that I'm adding features every week (in spare times,) I'll keep pushing updates!
UO was such a big part of my life back then, it’s great to hear that it’s still going. Maybe I’ll set up a server to play with my kids - although they’ll never be able to get the full experience with player killers, trolls, scammers, people hawking their stuff at the bank, dragon trainers, etc.
I've been tinkering with the same thing -- wanting to set up a little server so that we can all play together as a family. We've enjoyed Diablo 2, Minecraft, and Terraria as a family, but I feel like it would be fun to set up a little UO server. I'd really like to find a good tutorial for how to set up a chill / casual-friendly server (I like there to be some grind, but I don't want it to feel like "stock" UO) -- so something with accelerated skill gains and whatnot.
I don't know if there are "family-friendly" presets for such things, but so far Copilot has been reasonably helpful at helping me along -- I just don't have it all working yet. If you have any resources you come across, I would be interested in comparing notes. :)
There are several PvE UO servers, which are heavily against griefing. So I would say, pretty safe environment to play there with your kids and still with other people.
That's a great idea, UO is honestly perfect for playing with kids. The crafting, housing, exploring dungeons together. And who knows, maybe you become the dragon trainer this time around!
This reminds me of Origin Systems and Ultima Online. The number of player-run shards over the years promising Classic UO gameplay and the number of player hours spent on them is enormous.
What happens when value Z is not >= X? What happens when value Z doesn't exist, but values J and K do? What should be done when...
I hear what you're saying, but I think it's going to be entertaining watching people go "I guess this is why we paid Bob all of that money all those years".
Hence the "not obviously require" bit: Some portion of those "simply gluing things together" will not actually be simple in truth. It'll work for a time until errors come to a head, then suddenly they'll need a professional to rip out the LLM asbestos and rework it properly.
That said, we should not underestimate the ability of companies to limp along with something broken and buggy, especially when they're being told there's no budget to fix it. (True even before LLMs.)
This seems needlessly nitpicky. Of course there will be edge cases, there always are in everything, so pointing out that edge cases may exist isn't helpful.
But it stands to reason that would be a huge shift if a system accessible to non-technical users could mostly handle those edge cases, even when "handle" means failing silently without taking the entire thing down, or simply raising them for human intervention via Slack message or email or a dashboard or something.
And Bob's still going to get paid a lot of money he'll just be doing stuff that's more useful than figuring out how negative numbers should be parsed in the ETL pipeline.
My work has turned into churning out a PR, marking it as a draft so no one reviews it, and walking away. I come back after thinking about what it produced and usually realize it missed something or that the implications of some minor change are more far-reaching than the LLM understood. I take another pass. Then, I walk away again. Repeat.
Honestly I'm not sure much has changed with my output, because I don't submit PRs which aren't thoughtful. That is what the most annoying people in my organization do. They submit something that compiles, and then I spend a couple hours of my day demonstrating how incorrect it is.
For small fixes where I can recognize there is a clear, small fix which is easily testable I no longer add them to a TODO list, I simply set an agent off on the task and take it all the way to PR. It has been nice to be able to autopilot mindless changesets.
reply