eithed

no profile record

コメント

7 日前議論

Mostly agree with the author. Would add, most importantly, dont trust anything LLM does or says. Today I asked Claude to uniform behaviour of 3 components. I asked to do it 5 times, because at the end of each go there was something still unaligned that Claude found a way to rationalize. Sure - when asked the way it would say "This is on me", or "I thought it was a concious choice". Not once did it surface a question on what to do, nor did it mention any of the issues. So yeah, short leash, look at its thinking, correct his shit. This is today, Sonnet 5. Probably tomorrow it will be better or worse - thats another thing. The way you talk to Claude today will give you different results tomorrow

7 日前議論

Same; the most infuriating parts - Claude caused the issue and Claude misdiagnosed the issue, making me spend more time than if I was debugging it myself.

9 日前議論

[flagged]

16 日前議論

Yes and no.

If I were to ask you - what convention you want to follow for your database columns - camelcase or snakecase? There's no correct global answer. There's no overarching truth that should apply to all databases in existence (even if you'll focus on a certain type of database). Hence the no.

But yes, because in the context of existing system there is a convention. If it's snakecase, you create new tables with snakecase column names.

LLMs will generally follow conventions, but sometimes they will not, because indeed - global truths (or at least, the "last article it read" truths) sometimes win over (I assume)

16 日前議論

I agree and indeed externalize everything you know *that matters*.

Want to follow certain pattern, or convention - define it, ie active record vs repository pattern, stick is as an ADR! You don't know what you want? Look at what Claude produces and then acquire taste, mark this as convetion that future sessions will follow, but stick to *one* convention!

Treat your LLMs as junior developers willing to apply various patterns willy nilly, caring only about fulfilling the ACs of given task and not about the longevity or well being of the system in general. They will not look at bigger picture to check if given pattern applies globally, or even if there are any other patterns.

23 日前議論

> They conflate domain expertise with coding expertise, and then assess that people with domain expertise demonstrate great success at coding tasks

I didn't read it as such - I read that people with expertise have more success in reaching the goal of the session. Still your point stands = how is this news?

What baffles me, is that expertise of writing code is not important and is hand waved away = non-technical person can reach their goal and the session will be deemed successful. They don't conflate that domain expert = developer, and they dismiss that expertise (ie. updating legal rules matters, not how they are implemented) so i'm confused. Shouldn't both matter?

24 日前議論

I'm tired of people not taking responsibility for things they do and not being held accountable for their actions - politicians mostly; for example - currently in Poland there's a controversy around Zondacrypto (read here: https://www.politico.eu/article/a-missing-investor-millions-...); I'm so disillusioned that I believe nothing will come out of it - it will again be a case of "nobody did it, it just a thing that happened". Or our politicians escaping to Hungary (and USA) to avoid prosecution (and still being paid out money even though they're not in Poland and cannot possibly attend parlamentary sessions) where they'll live to spew hatred and how they were wronged. Sure, you did nothing wrong and these are just repressions, nevermind the millions that you stole during political campaign.

And generally people thinking about themselves and not considering that we're living in society: "let me blast music so that walls shake and fuck neighbours", "let me just leave my mattress here on the curb blocking the path, somebody will pick it up", "let me not clean after my dog shitting on the sidewalk", "I'm seeing people queuing to get on a train, let me just not notice the queue", "let me just walk down the street with my eyes on the phone, surely other people will accomodate me and get out of my way". This is the variation of the above, but to the civic level; just don't make lives of others harder.

28 日前議論

Is it enshittification, or is USA simply turning into fascist state?

29 日前議論

Leaving this here, as I couldn't leave it on authors blogpost:

I grew accustomed to these choices, so would navigate through them on autopilot. Once I was quick enough to get "We noticed suspicious activity indicating that you're a bot"; had to retry everything from beginning and hesitate when clicking :)

先月議論

Ah, I see what you mean now. Yes, my mind went straight to static analysis and testing (unit, feature, uat, mutation). Thanks for expanding on your point!

先月議論

https://www.danielzarick.com/uploads/2018-05-draw-the-owl.jp...

先月議論

Don't forget that LLMs are trained on human code. If they cannot understand what your code does then they cannot make changes to it, or at least - having them understand your codebase becomes expensive (more trips to Anthropic servers)

先月議論

I disagree. What I should have added is that with agents (as well as humans) you do need to have tests that verify what was done.

先月議論

I mirror your thoughts. I think we'll end up with "perfect map" paradox = you cannot be vague or indecisive on what you want (and if you are then these decisions don't matter) and you're creating a 1:1 representation of what the code needs to be.

I'd substitute "owner" for the team and in that sense the owner will not need to be human.

We're at this state where Claude is great at doing the "middle" part of work, but it's crap at gathering requirements and verification of what it has done. I also don't see people caring about these aspects of software development as shown in the article

先月議論

Exactly - the normalization of craft (?) is interesting

先月議論

Don't forget that you can adjust your requirements (either via plan or skill) to ensure the mistakes do not happen. The problem is that neither LLMs, nor humans (that don't work with the domain) will know they made these mistakes. Even coders don't think about everything all the time

先月議論

The road will be built to some specs, including features nobody asked for. If the corpus was trained for roads built in Arctic, you will get penguin crossings.

先月議論

I agree. But if I'm paying for the road (even as a taxpayer) I get angry that after a year it's full of potholes and that there are unnecessary signs warning about penguin crossing, making it cost 2 times more than it should have (and dont get me started why this road is really a highway leading to my house). I'd want certain qualities. And this article is basically = you will get a road, built quickly

But yes, you are right - I don't build roads and don't know what is a price to build a road and how to determine the quality of correctly built one, nor I will ever care or learn.

先月議論

True, but you should say that about every thing. Does it matter to you how the car drives, as long as it takes you to your destination? Well, yes, it matters: how will it deal with a crash, and if it's possible to replace a part and if anybody can just open it if you leave it outside. I will be amazed if somebody shows me their home-printed car, but if they'll try to sell it to me like a new one...

先月議論

Fair enough, but enterpreunership should, I guess, ask questions if given Next Big Thing has substance behind it or is it just snake oil.