throwaway7783

I think we have to wait and see if long term maintainability will be any different from human coded software. Every single long surviving human written codebase I have worked with, has significant amounts of tech debt and large pieces had to be rewritten from time to time. This is of course anecdotal and I'm sure clean and elegant old codebases exist somewhere.

How does this work in a production setup? Can this be set up like a server, or is it mostly for individual users to play around with data?

This. I hate VSCode as an IDE and is the reason why I have not used Cursor. I wish Jetbrains actually had some brains to build a better coding agent inside their IDEs (which I think are one of the best out there), but for now Im stuck with codex/cc + Jetbrains IDE

"We only need to consult the database for the user's secret..." , which kinda defeats the purpose.

LinkedIn doesn't have any redressal mechanisms for anything. Someone I knew went through a lot of abuse by a LI user and kept making new accounts to harass. LinkedIn's response - "We did not find anything that violates our ToC". No wonder it has become a cesspool of spam, fraud and abusers.

a.k.a the vaunted "Ideal Customer Profile". This is really critical for many many things in business and life.

Can you please elaborate on the differences? They are practically interchangeable, but conceptually there might be another layer on top of entities and relationships for somewhat richer semantics (like describing a relation, or additional annotations on the entity)

Yeah, but now this is implicit information (no price == marker row) and duplicate the entire row. And it is baking in "price" as the special field. This may not be just one field for another temporal entity

Works when there is always an active price. Having an explicit end date allows certain rows to be inactive automatically after validity period. Think of seasonal categories/products etc which dont exist after a specific period

It is at the org level

True, it is the only objective signal, but as you have observed as well, it is also a very poor one.

I said it in another thread. Yes, of course we cannot match the local store interactivity. What I mean is coast to coast RTT is 65-80ms. And the server can be optimized to return back basic operations (adding a comment, a new ticket, reading one back etc) can be done within tens of milliseconds, keeping the entire thing under 100ms coast-to-coast. If one can colocate servers with users, it becomes even less. I'd rather to server side "reconciliation" than do both (because serverside thing doesnt go away even with localstore, it is just deferred).

Based on all the comments above, it is very debatable if it is a better product all said and done

100% agree. A traditional CRUD app (like Linear) can be made pretty low latency without local-first. The complexity is not worth it.

Writing an eventually consistent database is hard, it maybe fine for Linear's use cases, but not knowing if my updates made it to the server (aka my team),is problematic. The sync lags have created untold problems in other projects I have worked for, so I always go for a synchronous solution. All the fancy stuff comes out only if it's absolutely needed. I'd rather optimize my server to be blazing fast, and have the user "suffer" network latency.

Even if we forget "rockstar", there are certainly different levels of engineers. More experience doesn't automatically mean better either. That is not to say experience doesn't matter. It matters quite a bit. Sure , good interns can sometimes have good feedback or spot mistakes. But not consistently enough.

All of this to say that it's not just experience that makes one a better engineer.

Sure, but the context here is only about code.

But doesn't your counter point assume all products that failed were not good enough?

Can you share your local LLM setup?

Fair enough. How do you do BM25?

Nice thing about our use case is that its not strictly analytics, but looking at most recent raw data. ClickHouse is definitely the powerhouse for analytics

I'm in the same camp. Do you use any specific extensions? Especially for OLAP and time series (partitioned tables + related extensions work fine, but curious if you use anything else)

Obviously this is just my experience. Claude code pushes back much harder than Codex.

I follow the same process. I have a design in mind for the problem at hand, but I don't reveal it to Codex. I go back and forth a bit to see if its proposals are better than mine. I go back and forth on tradeoffs of various approaches. And then I ask it to compare its proposals with mine. I "win" most of the time but there are many times where it shows a me a better, or simpler approach, or makes me rethink the solution altogether.

Once this is done, the mechanical coding parts are mostly routine (for codex)

I am not sure if you are replying to me or someone else. I never said I'm characterizing Zed as a text editor. Never used it, and have no opinion on it. My listing above was on why I am sticking with Jetbrains. Also did not say anything about AI.

IDEs/Editors ultimately are a very personal choice assuming they have sufficient features for a given language ecosystem.

I agree they probably have the opportunity (next biggest brand after GitHub), but nothing they are doing is looking like they are taking it. Duo seems to be their best effort so far to ride the AI wave, which everyone and their mother does already.

I'm in the java ecosystem, so YMMV.

- Automatic spring service detection

- Debugger (remote, local , with access to state, stack and ability to modify the state while stepping through), though I assume this is possible with neovm?

- built-in profiler

- can run individual tests seamlessly

- understands bytecode enhancers like Lombok

- Find Usage, find symbol, language specific navigation, showing class hierarchies, going up/down the hierarchies etc (maybe in conjunction with LSP, other editors can do a decent job?)

- Advanced refactoring (extracting classes, interfaces, inlining functions, extracting functions/methods)

- built-in database explorer

- built-in Git support (I have struggled mightily with VSCodes git interactions - but this might just be an individual preference)

- markdown/html previews

Basically, I barely have to get out of the IDE.

We use GitLab. They are no way in an incredible position to moonshot anything. They are yet another git provider with a management plane around it.

The article mixes transaction semantics (distributed or otherwise) with idempotency.

Idempotency or not, many points in the articles are are about atomic transactions.

By that logic, all "injustice" is "I don't like it when X happens" - there is nothing more.