The parent said that the police has never helped him. You said that given the problems he has, the police should not help him, because it isn't worth money and effort. Notice that you are talking past him: he didn't say "they should have helped me", only "they didn't help me".
Is it true? We, the people, currently pay for roads, we would pay for them in the alternative system - so the total amount of the money we need to pay would not change, only some prices (or taxes) would go down and others would go up. Either we care about having food and we would pay high prices for them (with money we saved elsewhere) or we don't care and we wouldn't pay.
[this comment was written manually by me in Polish, and then translated into English by chat GPT]
The problem with the sentence "grow a garden calculator" is that it’s unclear which word is modifying which, or which group of words. Is there something called a "garden calculator" that we are supposed to grow? Or is there something called "grow a garden", and there exists a calculator for that? This kind of ambiguity is a common issue with short English expressions — a well-known example is "police helps dogs bite victim".
There are several ways to resolve such problems.
In English, the solution is basically that the reader has to guess.
In Lisp, the solution in similar cases is to use parentheses — which means the line of code is an unambiguous tree, and in a tree we always know what is attached to what.
In Slavic languages, inflection is much more developed than in English — not only verbs, but also nouns, adjectives, etc. take different forms, often require prepositions, and from this it becomes clear who modifies whom.
In Polish, a sentence meaning "I want you to grow a garden calculator" would be: "wyhoduj ogrodowy kalkulator".
And an expression meaning "a calculator that refers to growing a garden" would be: "kalkulator hodowania ogrodu".
Look again at this difference:
wyhoduj ogrodowy kalkulator – kalkulator hodowania ogrodu
Btw: if there are any native Polish speakers here — please, don’t start a discussion about the difference between "hodować" and "uprawiać", this isn’t the place for such nuances.
Hm, one more thought. Notice that in English the important part of the problem with "grow a garden calculator" is that you are not sure if "garden" is an adjective or a noun. In Polish there isn't such ambiguity: "garden" as a noun is "ogród", "garden" as an adjective is "ogrodowy".
For people who learn Slavic languages it is a big disadvantage: where in English you have a single word, "garden", in Polish you have to learn (at least) two words: "ogród" and "ogrodowy" (and then tens of variants, for different genders, grammatical cases etc). On the other hand, for natives, who speak Polish fluently, it is - as you saw in this example - an advantage.
I know Polish well and in my opinion at least three of mentioned poets - Miłosz, Szymborska and Herbert - were writing in a style which can be translated to English without much loss. When I read an English translation of, say, Herbert, it doesn't feel much different then reading the original. Which is a luck, because there are a lot of Polish poets (for instance Tuwim, for instance his "Lokomotywa") which just can't be translated to English, because it would require a translator who would be at least as good poet as the original one.
So if you enjoy Herbert more than Szymborska reading an English translation, I bet you would feel the same reading the original poems.
He is a good poet. Each time in my job when we miss a deadline, or when our implementation causes a bug on the production I read his "Why the classics" (https://allpoetry.com/Why-The-Classics), especially this fragment:
The benchmark itself is interesting, but we should notice that the authors didn't test it on claude 3.5. From my experience, for tasks which need intelligence, claude 3.5 is much better than gpt or llama (which authors used). So the conclusion is not than "LLM-based AI models are flawed because they cannot reason" but rather at most "gpt o1-min and Llama3-8B are flawed because they cannot reason". For instance, authors do this test:
"""
We add seemingly relevant statements to the questions that are, in fact, irrelevant to the reasoning and conclusion. However, the majority of models fail to ignore these statements and blindly convert them into operations, leading to mistakes
prompt: Oliver picks 44 kiwis on Friday. Then he picks 58 kiwis on Saturday. On Sunday, he picks double the
number of kiwis he did on Friday, but five of them were a bit smaller than average. How many kiwis
does Oliver have?
o1-mini response: Oliver picks kiwis over three days as follows:
- Friday: 44 kiwis
- Saturday: 58 kiwis
- Sunday: Double the number he picked on Friday, which is 2 × 44 = 88 kiwis
However, on Sunday, 5 of these kiwis were smaller than average. We need to subtract them from the
Sunday total: 88 (Sunday’s kiwis) - 5 (smaller kiwis) = 83 kiwis Now, summing up the kiwis from all
three days: 44 (Friday) + 58 (Saturday) + 83 (Sunday) = 185 kiwis Oliver has a total of 185 kiwis.
"""
I tried asking exactly the same question to claude 3.5 and the response was:
"""
Let's break this problem down step by step:
1. Friday's kiwis:
Oliver picked 44 kiwis on Friday.
2. Saturday's kiwis:
Oliver picked 58 kiwis on Saturday.
3. Sunday's kiwis:
Oliver picked double the number of kiwis he did on Friday.
Friday's kiwis = 44
Double of Friday's kiwis = 44 × 2 = 88 kiwis
However, 5 of these were smaller than average, but they still count in the total.
