This is not new. Some checkouts do start with zip code and they feel much more efficient. (US only delivery, so country already assumed)

The German side always had slick presentations (they always had good visual marketing) and impressive claims, but whenever I tried to work with their products, I always found the claims overstated and that they hadn't really executed deeply. This despite my German counterparts working hard (I visited HQ in Germany and when they work, they really work and clock the hours, no idle chitchat)... yet it doesn't translate to impact.

A lot of their products had impressive front-ends but half-baked back-ends (on the American side, it's the reverse -- our interfaces looked like crap, but our stuff actually worked and often delivered in less time).

A lot of their designs were also non-human friendly (if you've ever driven a German car, you'll realize that the car was built for engineers and not for end users -- weird little user-hostile features pop up everywhere). I don't understand why this is -- this is a nation that produced Dieter Rams. Tobi Lutke (CEO Shopify) likes to talk about how Germans grew up surrounded by good design, yet that design culture never permeated many German products. I own a Bosch in-unit washer/dryer and it's frustratingly unintuitive and has a "my (the engineer's) way or the highway" philosophy.

I went to a BMW talk once about the infotainment system (it was built on the latest Azure tech), but came away feeling that the work was not deep. It was skin deep.

I wonder what has happened to the German builder/tinkerer culture that made German manufacturing great. In the 1980s and 1990s, Germany was synonymous with excellence. But in the 2000s-present, not so much (except maybe in very narrow mittelstand verticals, e.g. Zeiss).

cracks me up. I once leased a BMW for 3 years. By the time I returned the car, I still didn't what all the cryptic buttons for HVAC and other controls. They just refused to follow established automotive ergonomic conventions.

Anyway, my father used to do business with Germans for a long time. He had many interesting stories to share, but one that has always stayed with me is, his disdain for how cheap / penny pinching his German companies and their employees were when doing deals. This was in the 90s, so definitely passed the West Germany glory days.

My take is, in the era of global competition, Germans didn't know how to strike the right balance and effective allocate resources. Where to compromise, and where not to. I don't know if it's sheer stubbornness or they're just wired differently.

I think most people(Americans mostly) don't have the faintest idea how true that is right now. Here's a comment of mine from a few weeks ago giving such a present-day example that will blow your brains of how cheap german companies are. https://news.ycombinator.com/item?id=47018023

I feel like German companies know they lost the innovation race (I mean companies that aren't Zeiss), they lost the cheap manufacturing race "thanks" to Russian gas dependence and ideological denuclearisation before enough renewables were built, so all that's left for them now to stay afloat is reducing labor and operating costs by offshoring and pinching all the pennies they can find, but even that it not enough since from where I stand there's weekly corporate bankruptcies and layoffs and that's including the fact that the government has been speeding like crazy the last 3+ years to make sure the private sector industry doesn't completely collapse.

I wish I could find the reference I’m thinking of, but the idea was that Germans buying absurdly cheap wine and their constantly underfunded trains were part of a pattern of deliberate domestic under-investment to keep exports competitive.

Someone ITT surely knows more.

And unfortunately the focus on austerity post-2008 spearheaded by Germany only held the EU economy back compared to the US.

Yes and: ossified, top-heavy, ever more bureaucratic, MBA/consultant brain rot.

From your linked comment:

> willing to bet my entire salary that the costs of all the new extra bureaucratic overhead

Yup.

Of course, now they (and almost every other manufacturer) have followed Tesla off the cliff and made everything a screen, so the current generation cars have abysmal controls.

     I don't know if it's sheer stubbornness or they're just wired differently.

There is no long-term strategic thinking anymore, only feel-good policies and short-term cash burning for their respective clientele.

As a young person it infuriates me but there is nothing we can do.

The is always something you can do. Sometimes it's hard or uncomfortable but you can still have an impact on the things you care about if you're willing to do enough.

However bad Germany is in this regard, I suspect the US is far worse. There is no cohort in the US who remembers living in "East US" to temper the excesses of the people who've only known ease and comfort (though of course those people will tell you they worked hard to <insert career/prosperity path that no longer exists).

East Germany introduced the Transsexuellengesetz in 1980, which allowed people to change their first name or gender, as long as they provided, among other things, two psychiatric evaluations to ensure the condition was permanent, and not some decision driven by some temporary influence or fashion, but a full diagnosis of transsexualismus.

Or is this just lazy bigotslop?

They try to hold on to everything until retirement and don't care about anything else. In ten years Germany is like, what? 60 percent over 60?

Everyone knows it won't work, but try to hold on to it as long as possible.

Also feel free to peruse election programs yourself. Most parties put out short versions.

You also don't need to run for office to have an effect on party lines. I'm a member of a party. There are congresses on a regional (Bundesland) and national level. In my party the process is voting for proposals before the national congress due to the huge amount of proposals, but usually every proposal on regional level is discussed and voted on. It does not take much time to prepare a proposal, but it shapes the discourse.

That’s exactly my point. If a problem exists or a solution to a problem is possible about which no party is willing to talk about, it will not show it. The choice of topics is based on party opinions, not on voter surveys. This is called bias.

> Also feel free to peruse election programs yourself.

I read the full programs. This is the main reason why I think German political system is in the state of crisis.

> I'm a member of a party.

You surely know some examples when a party member shaped the discourse and set the course of institutional reforms. How long did it take for that person to achieve such results?

It's not a bias. I think you're misunderstanding the meaning of the word. We vote for parties and the wahl-o-mat compares the opinion of these parties. It would be biased if it would give an unfair advantage or disadvantage to one or some parties. The parties' opinions not being a good representation of the important challenges we face is not a bias of the wahl-o-mat. You can question its usefulness but calling it biased is calling it dishonest.

And honestly? That sucks. You can question its usefulness but please don't call an initiative that aims to give the populace a better political overview biased for no reason. You're not helping shape political discourse for the better here. I just checked: There weren't any no google results for "wahl-o-mat bias" yet. Now there are.

Edit: the word „Bias“ may not exist in Google search, but this topic is certainly discussed in German language space and it is easy to find:

https://www.zeit.de/kultur/2025-02/peter-mueller-bundesverfa...

Honestly, I'm not a big fan of the thing myself and I agree that most of your proposals would improve the tool. But calling it a tool that compares political parties biased makes it sound deceptive. And I don't believe that it's deceptive. It's just ineffective.

The fact that it gives an "unfair advantage to incumbents" also isn't really a bias of the tool. It really just is the most obvious fair way to structure it. Large parties are large because a large amount of people vote for them. So they obviously have more visibility.

But I also agree that the majority rule of an ageing population in Germany is problematic. With most incumbents seemingly agreeing to not talk about the future.

Let’s say there are parties A, B and C. A and B offer something populist solutions Sa and Sb to very important problem X, C does not promise anything on it, but offers solution for less important problem Y (single issue party). If voter thinks that Sa and Sb are the only choices, they may choose A or B, because it feels right. If voter was informed that neither Sa, nor Sb solve the problem, but some other solution Sx not supported by any party would do it, party C could become a reasonable choice - at least you get something done this way. This would be impartial judgement. Wahl-O-Mat inhibits this scenario, so yes, it is biased, it is deceptive.

> Die Mietpreisbremse in baden-württembergischen Städten und Gemeinden soll abgeschafft werden

> Länger leerstehende Mietwohnungen sollen ihren Eigentümerinnen und Eigentümer konsequent entzogen und vermietet werden.

Why do you think those options are not good options to address the housing crisis? Are there other levers? Of course, but Mietpreisbremse (freezing rents) and Leerstand (empty houses) are certainly key levers. And the point of the Wahl-o-Mat is to give you an indication over overlap, not to list and let you decide on single political initiatives.

What exactly is not true?

> Are there other levers? Of course, but Mietpreisbremse (freezing rents) and Leerstand (empty houses) are certainly key levers.

They are not the key levers, which everyone with basic knowledge of economics should understand immediately.

Regardless of whether certain segment is operated by market, by regulation or by combination of two, it is always about supply matching the demand. If you have more demand than supply, either prices will increase or you enter the state of deficit, where non-market mechanisms will decide who will get home and who will not. In either case prolonged state of reduced supply leads to crisis. Neither of those levers does solve problem of supply reliably. There’s simply not enough empty homes on the market to consider efficient management of them a solution. Rent controls also do not help here, because they actually reduce supply, by creating black market of subleases and reducing mobility (people stick to their regulated contracts).

The solution to the problem requires multiple reforms at once, which will fix short term and long term supply:

1. Dramatically deregulating supply side and reducing NIMBY influence. Project approvals should not take 7 years as in Berlin Friedrichshain and should not be blocked by survival of some rare toads like in Berlin Pankow.

2. Streamlining microdistrict planning, where one project includes construction of thousands of homes along with the necessary infrastructure. May include rapid construction tech (Plattenbau 2.0). It is not enough to build one building here and there, we need to build a lot more.

3. Shifting from majority rental to majority ownership model in which mobility is supported by market, low commissions (remove notaries, reduce taxes) and fast registration of property rights. It must be possible to sell and buy in 2-3 weeks maximum. The large landlords should be re-privatized: first, state takes over, then rentals are converted to subsidized lease deals with tenants with transferrable rights, in which tenants will effectively own their homes, while continuing to pay the current, never increasing amounts.

4. Progressive tax on property ownership kicking in from 0% on 3-5 apartments to significant percentage of rent value on 50+ apartments. The for-profit landlord business model must become unattractive, while not putting too much pressure on small landlords which are more market-friendly.

This kind of reform is neither left, nor right. It’s anti-capitalist, because it prevents concentration of capital and negative redistribution, but it is also pro-market, because it hands over the ownership to millions of people which can then freely sell and buy for their own use.

Spend your money elsewhere, perhaps?

At least Volkswagen is still building relatively cheap and reliable cars for the masses- they can compete with Kia and Skoda.

So, when I was working, I found the decisions regarding the infotainment mind boggling, to me they made zero sense, until I found some random documents deep in the BMW intranet, where I found the logic of it all: The focus was actually increasing the car range, so for example instead of having one infotainment dedicated hardware, one for the doors, one for the brakes, etc... now the cars have the least amount of computers as possible, located in the locations that result in the least wires as possible, with the goal of saving weight. Because of this, the software layer now had to deal with extra virtualizations, software that originally was to run on a specific microcontroller and do a specific task, and communicated with other parts by wire, now shares a generalized CPU with many other software, and communicate by virtual machines sending messages to each other.

Marvelous stuff from the point of mechanical engineering, indeed results in lighter car and less parts. But the end result for the user? It is mind bogglingly bad, several VMs running on top of each other, everything is slow, the Infotainment instead of being just Infotainment now do several other things.

I had written some of the surprising non-Infotainment stuff the Infotainment do, but that probably would cross into violating NDAs territory, so better not. Just let's say the Infotainment has to meet some non-entertainment related EU regulations.

https://insideevs.com/features/724945/zonal-architecture-sof...

But bafflingly to me, almost zero of my coworkers seemed to be aware of it. They would just get the seemly weird orders from above and would execute them, without figuring out the end goal, and this does result into some bad software engineering (because people don't know the end goal they don't know what they can optimize, so they just don't).

It’s also true though that the last wave of G models has improved driving dynamics but cheapened out in interior materials. Peak BMW interiors happened between 2019-2022 with the G01, G30, G05 and iX, i4. Being my favorites the iX and the G01.

BMW also has the best infotainment system after Tesla. And it still integrates well with Android Auto and Apple CarPlay.

My wife and I both have F31s, which we will drive until we can no longer source replacement parts unless the industry comes to its senses first (unlikely). Any time we've ever looked at plausible replacements, the screen-based controls are an immediate hard no.

I've formed the impression that every country's engineering and design cultures are essentially aesthetics.

I once had the chance to chatt with an old German colleague about the change in mentality over multiple decades. One thing he highlighted was the change from "lower error rate equals less waste, and higher final sale price" to "customer complaints or defect rates should be above a threshold, otherwise we are investing too much in the process control".

Particularly due to the desire to derisk the process; design by collaboration with the end user, and contracts with quality requirements, rather than the design being owned by the manufacturer.

It's really that the upper management does not appreciate change over departments if it's not their idea.

There is always the mentality that "why fix it if it works" where you actually have to wait for people to go to their pension to really grab a process and drive change.

You then get partially digitalized processes where digital native departments are concerned but they always have to solve the problem of interacting with a bunch of legacy systems and workflows, which in itself is so much harder and more inefficient.

Over engineered stuff which hate the user is staple of German manufacturing. Look on tanks during WW2. Impressive on the surface but unreliable crap for everyone who used it.

Parts are very easy to get at, all screws are Torx of identical size, and there's one very obvious way to take the machine apart and put it back together again. Made the replacement a breeze.

Now do an alternator on a VAG car :)

I drive a German car, all be it one from 2015, I don’t recognise this statement at all.

I find it quite well designed.

This sounds more like over generalised FUD to me.

Sthe keyboards are not QWERTY. They're QWERTZ.

Traffic lights are in excessive combinations of green/yellow/red. Sometimes you might have yellow/red light sometimes only red.

Roads often have "end of speed limit" sign. But the speed limit might have been temporary for construction. So now you have to remember the original speed limit. Why not post the actual speed limit again?

Stuff like this is absolutely everywhere in the German society for apparently no reason.

EDIT: Adding the best for last.. in Germany when you have an IBAN bank account (you know the I stands for international) you must have German international bank account, or else it will be rejected by everyone and everything.

There are many different keyboard layouts, at least nowadays there is only one German layout. For Spanish there are 2 different layouts which are both actively sold.

The meaning of yellow on traffic lights is no problem, you'll see it for no longer than 2 seconds. Unless it flashes yellow which means that the traffic light is shut off, then "right before left" applies. Some countries only have a green light, no red and no yellow. Now that is a problem because if the light is off because you a) don't see it, you have to know that it is there, and b) don't know if it is operational.

The end of a speed limit indication means the same as no speed limit indication. The lawful limit for the type of road applies, 50 in the city, 100 for rural roads, unlimited for Autobahn. Thats why on the Autobahn there will be a speed limit indication after every on-ramp, if there is no speed limit sign then it is unlimited.

(Except Deutsche Bahn; no-one argues at criticism there. It’s quite refreshing!)

"The end of a speed limit indication means the same as no speed limit indication. The lawful limit for the type of road applies, 50 in the city, 100 for rural roads,"

See, that's already wrong because the "Landstraße" may be 70, 80 or 100 depending on the exact road. If there's construction you might have a lower speed for the construction and then "end of limitation" at which point you have to remember whether the road is 70, 80 or 100.

Another example, if you have a Landstraße that is 100km/h, but you have a section that is 80km/h which has construction that has 50km/h, after construction you see "end of limit" what's the speed you're allowed to drive? 80 or 100? If you just had the speed limit sign all this confusion would simply not exist.

You are supposed to guess the speed limit from the size and shape of the road too. When I ask, almost nobody knows what is the speed of a road, they just wing it.

By law the speed limit has to be posted before an automatic speed trap (they are everywhere in France). Essentially training everybody that speeds limits are only for avoiding the speed trap "tax", but don't matter otherwise.

It’s this way in the entire country. There are many things I can get upset with in Germany (I moved abroad 10y ago and have an outsider’s perspective by now) but the traffic light example to me just indicates you didn’t ask why certain things were the way they were.

That was not the point, that's the standard way the lights will work.

The point is that sometimes you have a light combination where actual light post only has yellow/red for example (no green light). Sometimes you have a light post that has red only (on, off).

(I'm sure there are various German things to criticize or to make fun of. Much of what I read here, however, says more about the (US?!) authors, though.)

I have an (admittedly) older BMW. It just works. At first I thought that the cruise control lever is worse than buttons on the weel. After spending a lot of time in the car - no it isn't, it's much better.

(He loved his time there and the people of course).

Perhaps they were built for engineers designing the car not for the actual people repairing or maintaining them - they are notorious for requiring a cascade of disassembly for repairs of simple components, require specialist tools, overengineering of components etc.

I used to have a 2005 c-class mercedes, and that was a great car. Everything was well thought-out and had some very nice touches I didn't even know I needed and haven't seen in any other car my dad has had since then. It was very reliable and even had a recall some 3 years ago for a minor issue with the sunroof – which didn't manifest in my specific car.

I also have a Siemens dishwasher that is absolutely great. It has direct buttons on the front for direct selection of the different washing cycles it has, plus delayed start, extra rinse, and half load. It has an app, but you'd never know if you didn't read the manual – everything is accessible through the front panel and intelligible icons. The drawers are adjustable with the latches you need to pull on falling right under your fingers when you hold them.

In contrast, my LG washer + dryer is much more of a PITA to operate, with indicators that don't fall in front of the labels. I have to count the programs and the wheel clicks just to be sure which one is actually selected, even though I've had it for two years now. The thing doesn't even have a dedicated spin cycle! You can only select it as part of some other, larger cycle, or by using the app to upload a "custom" program. But without the app, there's no way of knowing what the currently loaded 'custom' program does until you actually start it.

Essentially you convert the differential equations into an algebraic system by discretizing the solution. The method is called Orthogonal Collocation on Finite Elements (OCFE), and it was developed by chemical engineers.

The Lagrange polynomials were calculated at special knots that corresponded to Radau interior points, which work great for stiff systems.

It’s great for solving differential algebraic equations through purely sparse matrix operations, no explicit integration like Runge Kutta. (Well, it’s implicit Runge Kutta).

CLI tools on the other hand are like precision instruments. Yes, you have to install them locally once, but after that, they have access to your local environment and can discover things on their own. There are two CLIs are particularly powerful for working with large structured data: `jq` and `duckdb` cli. I tell the agent to never load large JSON, CSV or Parquet files into context -- instead, introspect them intelligently by sampling the data with said CLI tools. And Opus 4.6 is amazing at this! It figures out the shape of the data on its own within seconds by writing "probing" queries in DuckDB and jq. When it hits a bottleneck, Opus 4.6 figures out what's wrong, and tries other query strategies. It's amazing to watch it go down rabbit holes and then recovering automatically. This is especially useful for doing exploratory data analysis in ML work. The agent uses these tools to quickly check data edge cases, and does a way more thorough job than me.

CLIs also feel "snappier" than MCPs. MCPs often have latency, whereas you can see CLIs do things in real time. There's a certain ergonomic niceness to this.

p.s. other CLIs I use often in conjunction with agents:

`showboat` (Simon Willison) to do linear walkthroughts of code.

`br` (Rust port of Beads) to create epics/stories/tasks to direct Opus in implementing a plan.

`psql` to probe Postgres databases.

`roborev` (Wes McKinney) to do automatic code reviews and fixes.

I do believe that as vision/multi-modal models get to a better state, we would see even crazier interaction surfaces.

RE: duckdb. I have a wonderful time with ChatGPT talking to duckdb but I have kept it to inmemory db only. Do you set up some system prompt that tell it to keep a duckdb database locally on disk in the current folder?

No, I don't use DuckDB's database format at all. DuckDB for me is more like an engine to work with CSV/Parquet (similar to `jq` for JSON, and `grep` for strings).

Also I don't use web-based chat (you mentioned ChatGPT) -- all these interactions are through agents like Kiro or Claude Code.

I often have CSVs that are 100s of MBs and there's no way they fit in context, so I tell Opus to use DuckDB to sample data from the CSV. DuckDB works way better than any dedicated CSV tool because it packs a full database engine that can return aggregates, explore the limits of your data (max/min), figure out categorical data levels, etc.

For Parquet, I just point DuckDB to the 100s of GBs of Parquet files in S3 (our data lake), and it's blazing fast at introspecting that data. DuckDB is one of the best Parquet query engines on the planet (imo better than Apache Spark) despite being just a tiny little CLI tool.

One of the use cases is debugging results from an ML model artifact (which is more difficult that debugging code).

For instance, let's say a customer points out a weird result in a particular model prediction. I highlight that weird result, and tell Opus to work backwards to trace how the ML model (I provide the training code and inference code) arrived at that number. Surprisingly, Opus 4.6 is does a great job using DuckDB to figure out how the input data produced that one weird output. If necessary, Opus will even write temporary Python code to call the inference part of the ML model to do inference on a sample to verify assumptions. If the assumptions turn out to be wrong, Opus will change strategies. It's like watching a really smart junior work through the problem systematically. Even if Opus doesn't end up nailing the actual cause, it gets into the proximity of the real cause and I can figure out the rest. (usually it's not the ML model itself, but some anomaly in the input). This has saved me so much time in deep-diving weird results. Not only that, I can have confidence in the deep-dive because I can just run the exact DuckDB SQL to convince myself (and others) of the source of the error, and that it's not something Opus hallucinated. CLI tools are deterministic and transparent that way. (unlike MCPs which are black boxes)

or install Docker and have the agent run CLI commands in docker containers that mount the local directory. That way you essentially never have to install anything. I imagine there's a "skill" that you could set up to describe how to use docker (or podman or whatever) for all CLI interactions, but I haven't tried yet.

How is it that you’re getting ads?

Region might matter. I set it to Australia/New Zealand region and for about a year it didn't show ads. But it does, now, even though it talks with an Australian accent.

What helps is also getting it to generate a docs of your code so that it has map.

This is actually how humans understand a large code base too. We don’t hold a large code base in memory — we navigate it through docs and sampling bits of code.

This is an interesting opinion.

I feel we are nowhere near the terminal state for programming languages. Just as we didn't stop inventing math after arithmetic, we will always need to invent higher abstractions to help us reason beyond what is concrete (for example, imaginary numbers). A lot of electrical engineering wouldn't be possible to reason about without imaginary numbers. So new higher abstractions -- always necessary, in my opinion.

That said, I feel your finer point resonates -- about how new languages might not need to be constrained to the limitations of human ergonomics. In fact, this opens up new space of languages that can transcend human intuition because they are not written for humans to comprehend (yet are provably "correct").

As engineers, we care about human intuition because we are concerned about failure modes. But what if we could evolve along a more theoretical direction, similar to the one Haskell took? Haskell is basically "executable category theory" with some allowances for humans. Even with those tradeoffs, Haskell remains hard for most humans to write, but what if we could create a better Haskell?

Then farther along, what if we created a LEAN-adjacent language, not for mathematical proofs, but for writing programs? We could throw in formal methods (TLA+) type thinking. Today formal methods give you a correctness proof, but are disconnected to implementation (AWS uses TLA+ for modeling distributed systems, but the final code was not generated from TLA+, so there's disconnect). What if one day we can write a spec, and it generates a TLA+ proof, which we can then use to generate code?

In this world, the code generator is simply a compiler -- from mathematically rigorous spec to machine code.

(that said, I have to check myself. I wonder what this would look like in a world full of exceptions, corner cases, and ambiguities that cannot be modeled well? Tukey's warning comes to mind: "Far better an approximate answer to the right question, than an exact answer to the wrong question")

On the other hand, LLMs are great at Go because Go was designed for average engineers at scale, and LLMs behave like fast average engineers. Go as a language was designed to support minimal cleverness (there's only so many ways to do things, and abstractions are constrained). This kind of uniformity is catnip for LLM training.

Writing a spec is akin to "working backwards" (or future backwards thinking, if you like) -- this is the outcome I want, how do I get there?

The process of writing the spec actually exposes the edge cases I didn't think of. It's very much in the same vein as "writing as a tool of thought". Just getting your thoughts and ideas onto a text file can be a powerful thing. Opus 4.5 is amazing at pointing out the blind spots and inconsistencies in a spec. The spec generator that I use also does some reasoning checks and adds property-based test generation (Python Hypothesis -- similar to Haskell's Quickcheck), which anchors the generated code to reality.

Also, I took to heart Grant Slatton's "Write everything twice" [1] heuristic -- write your code once, solve the problem, then stash it in a branch and write the code all over again.

> Slatton: A piece of advice I've given junior engineers is to write everything twice. Solve the problem. Stash your code onto a branch. Then write all the code again. I discovered this method by accident after the laptop containing a few days of work died. Rewriting the solution only took 25% the time as the initial implementation, and the result was much better. So you get maybe 2x higher quality code for 1.25x the time — this trade is usually a good one to make on projects you'll have to maintain for a long time.

This is effective because initial mental models of a new problem are usually wrong.

With a spec, I can get a version 1 out quickly and (mostly) correctly, poke around, and then see what I'm missing. Need a new feature? I tell the Opus to first update the spec then code it.

And here's the thing -- if you don't like version 1 of your code, throw it away but keep the spec (those are your learnings and insights). Then generate a version 2 free of any sunk-cost bias, which, as humans, we're terrible at resisting.

Spec-driven development lets you "write everything twice" (throwaway prototypes) faster, which improves the quality of your insights into the actual problem. I find this technique lets me 2x the quality of my code, through sheer mental model updating.

And this applies not just to coding, but most knowledge work, including certain kinds of scientific research (s/code/LaTeX/).

[1] https://grantslatton.com/software-pathfinding

Try Kiro. It's just an all-round excellent spec-driven IDE.

You can still use Claude Code to implement code from the spec, but Kiro is far better at generating the specs.

p.s. if you don't use Kiro (though I recommend it), there’s a new way too — Yegge’s beads. After you install, prompt Claude Code to `write the plan in epics, stories and tasks in beads`. Opus will -- through tool use -- ensure every bead is implemented. But this is a more high variance approach -- whereas Kiro is much more systematic.

Then reset context and implement each task one by one. Nothing gets forgotten.

In my experience you have to refer to the relevant docs on things explicitly in every single issue for it to work well.

Python too -- hear me out. With spec-driven development to anchor things, coupled with property-based tests (PBT) using Hypothesis, it's great for prototyping problems.

You wouldn't write mission critical stuff with it, but it has two advantages over so-called "better designed languages": massive ecosystem and massive training.

If your problem involves manipulating dataframes (polars, pandas), plotting (seaborn), and machine learning, Python just can't be beat. You can try using an LLM to generate Rust code for this -- go ahead and try it -- and you'll see how bad it can be.

Better ecosystems and better training can beat better languages in many problem domains.

People do, they also write mission critical stuff in Lua, TCL, Perl, and plenty of other languages. What they generally won't do is write performance critical stuff in those languages. But there is definitely some critical communication infrastructure out there running with interpreted languages like these out there.