Gas Town: From Clown Show to v1.0

[flagged]

Beads is cool, but I tried to use it, and the backend didn't really make sense. I have to run an sql database in the background? How does it sync with Git? (I didn't see any files/objects committed to the repo) Plus, Dolt ended up using a constant 3-30kB/s of i/o in the background, while nothing was actually going on. That and Beads has a lot of features I'm not gonna use. All of this was just too complicated for my tiny brain.

So I slapped together my own Beads implementation (https://codeberg.org/mutablecc/dingles) over a day or two. Probably has bugs, and I'm sure race conditions if you tried to use with Gas Town, and likely does not scale. But it has the minimum functionality needed to create and track issues and sync them (locally and remotely, either via normal merge, or a dedicated ticket branch). No SQL, no extra features, just JSONL and Git. Threw a whole large software project at it, and the AI took to it like a duck to water, used it to make epics for the whole project, methodically worked through them all, dependencies first, across multiple context sessions. The paradigm of making tools the AI wants to use is clearly a winner.

Which ISO certification matters, but the key thing people should be aware of is that the primary value of the certification to customers is that your processes are documented and that deviations are tracked, so that customers can check whether the processes makes sense before signing a contract. It's important not to expect the certification itself to guarantee quality.

Does Yegge really think that building production software this way is a good idea?

Let's assume that managing context well is a problem and that this kind of orchestration solves it. But I see another problem with agents:

When designing a system or a component we have ideas that form invariants. Sometimes the invariant is big, like a certain grand architecture, and sometimes it's small, like the selection of a data structure. Eventually, though, you want to add a feature that clashes with that invariant. At that point there are usually three choices:

* Don't add the feature. The invariant is a useful simplifying principle and it's more important than the feature; it will pay dividends in other ways.

* Add the feature inelegantly or inefficiently on top of the invariant. Hey, not every feature has to be elegant or efficient.

* Go back and change the invariant. You've just learnt something new that you hadn't considered and puts things in a new light, and it turns out there's a better approach.

Often, only one of these is right. Usually, one of these is very, very wrong, and with bad consequences.

But picking among them isn't a matter of context. It's a matter of judgment and the models - not the harnesses - get this judgment wrong far too often (they go with what they know - the "average" of their training - or they just don't get it). So often, in fact, that mistakes quickly accumulate and compound, and after a few bad decisions like this the codebase is unsalvageable. Today's models are just not good enough (yet) to create a complete sustainable product on their own. You just can't trust them to make wise decisions. Study after study and experiement after experiment show this.

Now, perhaps we make better judgment calls because we have context that the agent doesn't. But we can't really dump everything we know, from facts to lessons, and that pertains to every abstraction layer of the software, into documents. Even if we could, today's models couldn't handle them. So even if it is a matter of context, it is not something that can be solved with better context management. Having an audit trail is nice, but not if it's a trail of one bad decision after another.

I suppose one could, but none of those are primary economic drivers with dim prospects for turning a profit (well, I suppose that may be true of TV).