Polish s, ś, sz, z, ź, ż, rz, c, ć, cz, si, zi, ci – what's the difference?

https://news.ycombinator.com/item?id=47533035

:)

Much simpler, IMHO

single letter = sound

letter + z = "hissing" version of the sound

letter + accent = soft version of the hissing sound

letter + i = same previous item, but caused by "i"

rz = legacy, czechs still pronounce it as a different letter

This is how I understand it as Ukrainian

Westernmost Eastern Europeans would do anything but use the actual script that makes sense for their language. How hard is it to just use с, ш, щ, ч and ц like civilized peoples.

Added Openclaw skill here: https://clawhub.ai/sliday/tamp

It's a local proxy (npx @sliday/tamp) that sits between your coding agent (Claude Code, Aider, Cursor, Cline, etc.) and the upstream API. It compresses tool result blocks — JSON minification, TOON columnar encoding for arrays, line-number prefix stripping, whitespace normalization, and optional LLMLingua-2 neural compression — achieving ~52.6% fewer input tokens with zero behavior change.

I need to keep optimising it. I agree.

> How do I see the stats of a city? Click the city tile.

> When I use the "mine" tool, what happens? The nearest dwarf attempts to so the task? Dwarf live in mines, this is city extension tool basically.

Fair point on COBOL—I oversimplified. Programming languages exist for precision and execution, not because machines can't parse English. That framing was sloppy.

But I push back on "the entire premise is wrong."

The interesting part isn't "AI can execute pseudocode"—nobody debates that. The point is the artifact: the .md output matters, not the runtime. A codebase where every function is readable English changes who can participate in a pull request, audit logic, or catch wrong assumptions. "Multiply by 9/5" vs "multiply by 1.8" is an editorial conversation, not a code review.

It's a proof of concept to show the artifact is executable, not a production proposal. It's slow (today), expensive, and non-deterministic - I said so in the post. The question is whether the intermediate representation (English) has value beyond performance? I believe that the loop is shortened here: there're no in-between element intent→weird non-human language→result, it becomes intent→result. No NEED to create synthetic procedures, explaining how the code works in plain language should give us the output.

An old person enters a bank, asks to open an account, speaks plainly in his native language, the teller clicks buttons, and the account is created. From the subjective perspective, there's no in-between interface: the old person had a though, than it got realized.

Your loop is wrong, as it will go ‘intent -> llm(?) -> result’. Which doesn’t need to compile, but the llm its own black box of magic function that may or may not reproduce the same result based on intent. Also I would think the number of tokens would be concerning, as your example prompt looks 3x larger then the code snippet.

This is a direct copypaste from a Claude chat. God save us all.

My son suggested it; we love it. I guess it's a subjective thing.

Could be. I think part of the problem is that the larger it is, the more obvious that it looks like clip art.

It also calls "attention" to it - which could work if a large mountain represented a mechanical difference - more or richer ore, etc.

But I grew up playing classic tile based games (Civ II, Heroes of Might and Magic, etc), so I have a fairly critical eye for it.

Also VERY risky.

Great suggestions, will do.

Also, one of the companies I'm working with hopes to get all sorts of strict certifications and gov contracts, it simply cannot hire talent from Russia, North Korea, Syria, Iran and alike. Yes, the position is fully remote, but there's one hard requirement.