all2

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!

This sounds amazing. I might give this a go!

Note to be confused with Haxe: https://haxe.org/

Probably because of the 'minimalist' qualifier.

The heaviness of your layering will depend directly upon the environment you will be in. The above is adequate for most temperate climates.

If you plan on being at higher elevations during local fall/winter/spring, your base layer will likely be light (and moisture wicking, please do this), and your first layer will likely need to start heavier than a temperate climate base layer.

Having spent a considerable amount of time in the North Central US during those seasons, the layering strategy is appropriate, but the heavier outer layers are non-negotiable, especially as the average temperature drops below 15F.

For those that don't have dead comments showing in their HN UI, Mike has a response adjacent to this one [0].

[0] https://news.ycombinator.com/item?id=49244312

@dang, the creator of this idea is having his comments killed off for some reason.

You have a robot. You need it to be smarter. You buy a new model cartridge (probably a PCIE 9.x). Now you need some domain specific skills. You'd like it to be able to cook, and you'd like it to not dent your walls anymore. You buy 'improved spatial reasoning LORA' card and 'Gordon Ramsey's Chef ULTRA9000' card.

Now your robot can respond sarcastically when you ask for chicken nuggets. Again. It also doesn't dent your walls anymore.

This is more complex than "houses cost less then".

Given a fiat currency and fractional reserve banking, the dollar floats in value like a leaf on the wind.

Houses cost less, people made proportionally less (inflation is a consideration here), and interest rates still bite you in the butt over the long haul, regardless of your monetary baseline.

My parents bought their house when rates were about 12-14%... "High" is relative.

I think routing should be pushed 'down the stack' so to speak.

What I mean is that most tasks can be recursively fragmented into smaller tasks, and once you've hit suitable leaf nodes -- where the task is very granular -- you can begin to deterministically show which models perform better or worse for that specific task. Then, when your agent is running a workflow, you may use various models for different steps in a workflow. For example, some models may excel at exploration, some at determining a good architectural fit for an implementation, some at actually writing the implementation, and so on.

But you don't know until you define your 'work' taxonomy, and still further, you won't know until you have a statistically significant number of runs on a given chunk of work. Once you have that, though, you can hone in on models that excel at one specific task or another and prefer those the majority of the time (say ~80%) and hold back the remainder work as a 'test corpus' just in case a different or new model does even better.

This is something I've kept in the back of my head as I've been working through my agent harness primitives -- specifically enabling different models per chunk of work.

Not GP, but my datasets weigh in at around 2-20GB depending.

My solution to this is to not have clocks in my house at all.

This has nothing to do with the fact that I still haven't figured out how to set the time on my microwave. :D

Just providing context for folks who don't know what MARS is and want to see stuff run in the UI. :D

As a side note, anyone is welcome to add 'CEO of HTMX' to their LinkedIn profile.

...I may have done this.

The nrol 39 mission patch is one of my favorites. You should find the authorizing docs for that patch and read the hand written notes. They're hilarious.

Have you ever heard of the rather excellent Pen Island, vendors of fine pens? On my work computer, so you can plumb the internet archive for yourself.

From the git repo:

    webMARS is a browser implementation of MARS MIPS 4.5: editor, assembler, simulator, help system, and classic MARS tools in a single web UI.

    Overview

    - Single-page IDE for editing, assembling, running, stepping, backstepping, and debugging MIPS programs.
    
    - Multi-window desktop/mobile UI with registers, text/data segments, labels, messages, Run I/O, and tool windows.
    
    - Built-in help system with localized pages and embedded reference material.
    
    - Persistent browser workspace for files, session restore, settings, and tool state.
    
    - Single JavaScript assembler and simulator core, with no native runtime dependency.

And from [0]:

    MARS is a lightweight interactive development environment for programming in MIPS assembly language, intended for educational-level use with Patterson and Hennessy's Computer Organization and Design.

---

To run the demo program:

1. Run > Compile

1a. In the popup window select 'Open ASM as new file'

2. Run > Assemble, context will change to the 'Execute' tab.

3. Click the little 'Go' button near top-center.

4. ???

5. Profit!

---

[0] https://computerscience.missouristate.edu/mars-mips-simulato...

Is this the old monolith vs micro-services argument?

I guess this boils down to 'how granular and function specific are your building blocks?' and where you draw the lines programmatically: library interfaces in a single program/executable, API/ABI between two or more programs/executables, HTTP API/other transport protocol across network boundaries between two or more programs/executables, and so on.

I'm not sure I'm slicing this along the correct abstractions, though.

Is one ever truly finished rebuilding an entire code-base one piece at a time?

If I had to do a 'code quality' checker I think I'd try to use some combination of syntax tree analysis, data flow analysis, and LOC changed.

Something like that.

Too many new nodes in the syntax tree, or a sub-tree that appears sufficiently similar to another sub-tree (for various definitions of similar), data-flow/side effects gets more convoluted, too many LOC, and so on.

They told me the future would have horrors beyond my comprehension.

But I understand this particular horror. I might even agree... :D

I wouldn't consider those things embarrassing. You may even consider it an opportunity to discuss the book at a later date?

My version, off-the-cuff:

""" Making a demo that does some things is easy. Making a demo that does all the things is hard.

We took a lot of time to make this product polished. We nailed down a lot of UX gotchas and a lot of bugs that come from poorly written back-end code.

If you don't need the polish, then a demo is more than sufficient. We built this for those who just want to ship, not fight with their agent about tech stack stuff. """

You're good, man. I get it. Your heart and soul goes into a thing and the only comment you get is 'hey, look at these other posts with this suspicious user activity'. Nothing about your work.

I've had to deal with this in various areas of my life. I can't say I have a good solution.

Role play, which is a huge consumer of tokens. You can glance at openrouter's usage stats and see what apps tokens are going to and what the inference content was classified as. It's quite revealing.

Not what GP was going for, I think. They called out a green user with a very specific comment history and made no comment about this submission.

How do people even find this kind of thing? Is it manually? Are there search tools for this?

If you spend enough time with an LLM and aren't paying attention, you'll pick up on its mannerisms. I did this awhile ago (the "its not this, its that" thing) and someone here called me on it. After that callout, I've tried to be more aware of how much of that stuff leaches into my head and out into text.

I know this is a facetious dismissal, but I'll try to respond anyway.

> I imagine you wanted to say "ignores the Declaration of Independence", which you quoted?

Correct.

> Sure, if you believe that this declaration endowed you with the unalienable property rights then just go ahead and don't pay the property tax, what is going to happen if your property rights are truly unalienable, right?

I'm not advocating for breaking laws, regulations, or rules of the nation I live in.

> Also, how theft would be even possible if property rights had been unalienable? If someone stole from you and you retained your property rights you could just keep enjoying your property and exclude the thief from your property as the right entitles you.

This is less about the pragmatics of 'possession' and its intricacies (the old adage 'possession is 9/10s of the law' is relevant here), and more about the policies of the governments that rule, and ultimately that answer to the people they rule.

If I am advocating for anything, it is change in laws and the appropriate limits on government to limit the levying of taxes on possessed things. In this case, land.

> So yes, your rights are given to you by the state and you don't really have any without the state enforcing them.

This ignores the Constitution and the acknowledgement of 'inalienable rights'.

   We hold these truths to be self-evident, that all men are created equal, that they are endowed by their Creator with certain unalienable Rights, that among these are Life, Liberty and the pursuit of Happiness.--That to secure these rights, Governments are instituted among Men, deriving their just powers from the consent of the governed, [...]

In essence, the government of the United States derives its power from the governed, and otherwise wields no true power. The Constitution of this nation is written specifically limiting powers of the government, and not enumerating the rights of the people.

> If you could naively own your property then you could just tell the tax collectors to fuck off, what are they going to do with your property if it had been truly yours?

Yes. This is where the second and fourth amendments to the constitution are important. True sovereignty (not in the sense of that 'sovereign citizen' nonsense) comes with martial ability; that is, the right to take another life. Sovereignty is necessarily paired with 'power', as without it, there isn't any true ability to protect one's rights.

---

All that said, I'm appealing to an ideal when I say 'property tax is theft'.