This depends largely on your expectation for what a 'game' should be.
Puzzle boxes, for example, have zero on ramp, and yet many many people enjoy them, enjoy the struggle of discovery.
Arguably the edges of mathematics and science are inhabited by similar people, living where the rules are ill defined, where there is much to be discovered rather than pre-digested and spoon fed.
I have little patience for games that don't spoon feed, so I get where you're coming from. I watched my brother play DF and decided I didn't want to spend my time like that, trying to parse ascii, trying to figure out how all the things interacted.
I found exactly the discovery fulfilling in Dwarf Fortress, Rimworld and Minecraft. Once I mastered those (well, maybe it is fairer to say "once I plateaued", there are way more skilled players than me) I found much less interest in them. Sure, I still play occasionally for a bit after a big update drops, but that is pretty much it. Oh and yeah, puzzle focused games (as long as it isn't slide puzzles) are great too. I fondly remember Myst, Monkey Island and other puzzle games like that.
Some people like games where you need to grind (idle clicker games seem to be purest/insanest form of that), and that is something I don't get at all. It is just pointless busywork, just like those repetitive achievements ("kill N enemies with X style attacks") or collectables. (Achievements that are on the form "find this hidden thing" or "do this out of the box thing once" I do understand more.)
I've been using GPT-5.6 Luna for everything at this point. It is more than enough to do all the work I need to do. You have to lead it by the nose, but if you know where you're going it works really, really well.
It seems there are two distinct groups, one which is doing relatively well with Luna, Deepseek Flash and similar models while other seem to be satisfied only with the state of the art.
Depends on how in-the-loop you want to be. I personally delegate all the writing of the code to agents, but I maintain a clear mental model of the architecture, which I come up with by iterating and prototyping with agents. I can use Luna for all of this, although I switch depending on the task. It's nice to be able to throw a 1,000 word rough spec at Fable and get a personal tool that works perfectly though. I expect that as the models get better, I'll continue to be in the loop, but operate at increasingly higher levels of abstraction.
Having worked with both, it seems like a control thing to me. Either you're cool with Fable spitting out tons of code you'll never read, or you're cool with Luna doing targeted work while you manage the main work thread.
(I'm in the second boat so long as I'm responsible for the code I PR)
I'm ok with not-Fable until I need anything design-related: a nice HTML page, LaTeX typesetting, UI design. Sol is especially incapable of doing anything sensible.
Is there any alternative model with design sensibilities?
Did you add some skill for this? I've been using a frontend design skill with Sol and it's reasonable (for my purposes). I don't remember where I got that skill.md though, it probably was from OAI's own blog about this a few months ago.
fable is good at it but I find it uses the same slop in different variants every time. Even the words it uses for the different alternatives it proposes are the same (cartography, atlas, bench, signal, etc). At least you develop a good nose for slop ;) it becomes a struggle to steer it off the same path every time.
I'm happily in both depending on what it is. Even Sol / Fable cannot do some truly novel stuff and if you rely on it too heavily you get detached from the underlying systems to the point that it's both uncomfortable and detrimental.
I’ve just been using it, with a chat interface. Basically, as a “consultant.”
For me, and my projects, it’s been great. It’s made an enormous difference.
I guess my workflow may seem “quaint,” to many folks, here, but the end results speak for themselves.
I suspect that one vocation that could get heavily impacted by AI, is the consulting business. That’s where many experienced people go, as they reach their career peak.
In my last project (just about to ship), ChatGPT replaced a whole bunch of services that would usually be supplied by external advisors.
But these are also services that I would normally not be able to afford, otherwise, and would just have to “make do” with. This release will have a level of polish that I have would never been able to achieve, unassisted by AI (I had originally used “on my own,” there, but the reality is, it actually was “on my own”).
The thing about consulting is that someone needs to verify the output, know what questions to ask in the first place, and provide a throat for the client to choke in the event of an issue. Also, professional insurance. I could be wrong but in the worlds I live in professionally, accountability is still a thing.
Yup. There's some places that we'll need that accountability. I suspect that this may be filled by folks that act as "LLM brokers," using AI in the background, while dealing with the legalities, in the foreground.
But in my case, it wasn't nearly so exotic. The LLM helped me to do a much better job, preparing the App Store presentation, Web support, privacy policies, budget prognostication, and app glossary.
I have just had an extremely complex app, pass App Review, in record time (from going into review, to approval). No niggles or bounces at all.
I'd be curious to pick your brain about the process you went through for this. My mental gap here is not even knowing what to ask for a process like this.
Happy to do so. Probably not something a lot of folks here would find interesting, but I'm easy to contact, from my Web sites. People here, often do that.
Basically, my needs are different from others. I'm not working on the next NORAD upgrade, much of my work is open, and the more ChatGPT knows about me, and the app I'm designing, the better. One reason I chose it, was because of this "memory."
TL;DR: I feed it just about every scrap of information about my project as I can. Source files, documentation, screenshots, videos, information about the organization, information about the target demographic, etc.
With all that information, it gives me very useful advice.
It created a great tutorial. I usually write way too complicated ones. It did much better.
In the case of the App Store stuff, it helped me to choose the right privacy report, generated the privacy manifest, and helped me to compose all the copy on the storefront.
I'll probably be releasing the new app, soon. It's already passed review, but I want to make sure that everything is kosher, before releasing. It came together so quickly, that I have the luxury of time. I just need to release before (or as) iOS27 comes out.
Oh, I don't really do much more than have feedback loops, where I review the output, then ask for things like less verbosity, or a lower-level vocabulary, etc. I like to apply this at each application, rather than make a blanket rule, as each page may have a different audience.
For example, I have made a tutorial, which is meant to be a "quick reference," from within the app (Use Safari to view the page), but I am also developing a "walkthrough," to show possible funders (we're an NPO). The walkthrough is a higher-level vocabulary than the tutorial. The LLM deals with stuff like making sure to keep the glossary consistent, etc., but I like to have the final say on the output.
I'm pretty sure that I can force the LLM to use certain levels of vocabulary, through the .md file that describes the default setup, but choose not to do it.
I am still in that "trust, but verify" stage of my relationship with LLMs.
Same, all I need is speed to execute editing faster than I could in vim. Luna is cheap, intelligent enough, and fast enough I don’t lose the sense of flow.
Are you comparing cash-only prices to card prices? Some gas stations advertise cash-only prices with 20-30c added on for card processing fees—I've never seen Costco be more expensive then the card price
I also made a clone. I haven't touched it in months. I was going to put it on one of my domains and decided not to until I can sort out moderation and all that. I'm not sure I want to be on the hook for moderating a forum full time.
This is tangential to the commenter's inability to explain their choice of words which is atypical of a human who would have went with "dense", and suggests a 3T parameter model reaching for "1960s-noir-pulp-fiction-rugged-detective".
AI comments are against the rules and I think the commenter's lack of an explanation for their choice of words sufficiently establishes it wasn't their words to begin with.
Are you having some rage fit? Using dashes to construct new words, especially in ironic, humorous context is widely used prasctice in English (which you don't seem to know well either).
They say release early and often, so here's my micro BOM manager. The core data model is complete, and I'm scaffolding my way to an API for the server. UI comes next.
My development process is pretty tight, as I'm opinionated on how all the core pieces fit together. GPT-5.6 Luna has been integral to the scaffolding, but I've been in the driver's seat for how all the little pieces fit together.
From the README:
# ubom-v4
The fourth draft of my mini BOM manager, which encapsulates my very opionated way of thinking about how parts, bills of materials, and revisions relate to one another.
Unique ideas here are
1. sequences
2. taxonomy trees
where a sequence is a user generated grammar definition for arbitrary string sequences. It supports 'choice', for selectable literals within a string, 'branch' for a grammar that requires more than one definition, 'range' for values that span ranges such as 0-99 -- as well as padding out those ranges, 'rangeradix' for ranges that require position dependent radices (not radishes :D), and so on.
A sequence definition can parse a value OR generate a new value, something like `mySeq.Parse("a123")` or `mySeq.Next('a123') -> "a124"`.
A taxonomy tree applies labels to a sequence, so we can give some degree of meaning to each segment of a sequence.
This all builds up to `PartNumber`, which possesses a part number literal, and the accompanying taxonomy tree so you can see what categories a given part number occupies.
From `PartNumber`, we jump to the recursive DAG that is a BOM: `PartNumber + Revision -> BOM -> []LineItem(PartNumber, Revision)`, and the cycle continues.
# Roadmap
- strongly typed attributes, can be applied to any node in a taxonomy tree, to a part number, or to a bill of materials -- this allows you to do things like add resistor values to a specific branch of the taxonomy tree. It also enables things like querying parts by attribute, requirements satisfaction (maybe), and so on.
- A user interface. :D McMaster has the right idea here, though I'll also be barrowing ideas from Inventree.
- CRUD ops for the user facing stuff (part numbers, sequence grammars, taxonomy trees, etc.)
- A minimal change control workflow; all quality systems subsist on their change control workflows. To build a quality system from scratch, and have traceability, one needs at least an atomic change control workflow.
- Part number artifacts and artifact sources; I want to be able to point a part number at a git repo and have the revision bump with new release tags, ingest bills of materials (the git repo is the source of truth in this case), and so on.
- Multi BOM, where a part number can have a number of BOMs, one for each unit of responsibility: mech, elec, docs, production flows (depends on workflows, I think), and so on.
- Solidworks integration.
- Altium integration.
- KiCAD integration.
- Others? Is this giving you ideas? Drop an issue and lets discuss!
I've been having a great time using haxe & reflaxe macros for code generation.
You can have some minimal haxe code and build tiny compilers that use it as a source of truth for generating a http client, http server stub, cli entrypoint, docs entry, integration test, openapi spec.... Agents are good at writing the macros for whatever language you want to compile to, and now you've enforced agreement between these things as part of a build, which makes for several fewer things that you ought to be diligent about.
Unlike using something like yaml as your source of truth, haxe has a type system. You can catch some problems upstream as build errors rather than waiting to catch them downstream in the generated code.
Puzzle boxes, for example, have zero on ramp, and yet many many people enjoy them, enjoy the struggle of discovery.
Arguably the edges of mathematics and science are inhabited by similar people, living where the rules are ill defined, where there is much to be discovered rather than pre-digested and spoon fed.
I have little patience for games that don't spoon feed, so I get where you're coming from. I watched my brother play DF and decided I didn't want to spend my time like that, trying to parse ascii, trying to figure out how all the things interacted.
I also don't like puzzle boxes that much.
To each their own.
reply