Month: March 2023

Quick reference for myself: the shortcut to open the command palette (aka heads-up display) in various programs:
– intellij idea: C-S-a
– VS Code: C-S-p
– obsidian: C-p
– KDE: M-
– Github: C-k
– Libreoffice: S-

Not yet implemented (but coming): kate, krita

Background: The command palette is my favourite UI innovation of recent years, one I already find it hard to live without. One shortcut brings up a searchable list of commands, which permanently removes the hassle of browsing through menus. But every program has chosen its own shortcut to bring up the palette, and I find them hard to remember. Hence this cheat-sheet

[shortcuts are listed emacs-style: M is alt, C is ctrl, S is shift]

Sentences I have enjoyed:

Mauritius, arguably Africa’s most successful economy, has outsourced its final court of appeal to Britain’s privy council, improving its reputation for rule of law and becoming a successful offshore financial centre in the process
–[How to create a city | Financial Times ]

We begin with a striking fact: The defendant’s face alone matters greatly for the judge’s jailing decision. In fact, an algorithm given only the pixels in the defendant’s mugshot accounts for up to half of the predictable variation.
–[Machine Learning as a Tool for Hypothesis Generation – Marginal REVOLUTION ]

apparently the salinity of our bodies matches that of primordial seas, so in a sense we never really left the oceans. Our micro-organic aquatic ancestors simply constructed meatbag spaceships with artificial life-support aquatic environments inside to explore beyond their oceanic home world.
–[Salt-Seeking ]

A banking system is a superposition of fraud and genius that interposes itself between investors and entrepreneurs
–[interfluidity » Why is finance so complex? ]

Bracing against this year’s endless future-shock, I’ve still been maintaining my “Awesome Prompt Design” collection of links.

But when so much is happening day by day, it’s a struggle to keep any kind of perspective. So here are the sources I’ve been finding most useful for filtering the firehose:

• Simon Willison has the perspective of a skilled programmer without an AI background. So his attempts to understand and explain things fit appropriately into my level of knowledge
• Nick St. Pierre is pushing the boundaries of image- and now video- generation, especially good on AI. Best of all, he gives crystal-clear twitter-thread explanations of what he’s doing, in enough detail to follow along at home
• Zvi Mowshowitz (thezvi) is smart and reads everything. Unfortunately he tends to also write everything, making his AI Roundups a challenge to get through
• The Neuron is a bare-bones daily email covering the big releases

I’ve been mentally replaying how different my language-obsessed childhood would have been if GPT had been around then.

Even now, while my head says “you don’t need to learn more languages”, it’s hard to stay away from such a shiny new thing.

So here are some of the ways I’ve been using GPT for langauge study

Conversation

Moving general-purpose interactions with GPT into the language I’m learning is a good step towards immersion. It’s a big step up from just reading foreign-language materials online – this way I’m forced to compose full-sentence queries in my target languge.

Ideally, GPT would correct my text while I’m doing this. Alas, it tends to abandon the language-tuition side-quest and focus in on whatever else we are talking about. This fits a general pattern where GPT is pretty bad at balancing multiple tasks within a single conversation

Where I don’t know a language well enough to talk to GPT in it, I can ask it to fill in the blanks. I start off with a prompt like this:

If I write in English in quotation marks (“like this”), you should translate what I write into simple Turkish. If I write in Turkish, you should correct any mistakes and reply in simple Turkish. If I write in English without quotation marks, you should reply in English

Here is an alternative prompt in a similar style.

Explanation

GPT does a reasonable job of explaining grammar:

Please explain the form and meaning of the past definite verb in Turkish. Give examples

Of course, there’s not much advantage of doing this over looking in a textbook. Where GPT shines is in explaining words in context, such as explaining a line from a Turkish pop song:

gloss the meaning and grammatical form of each word in this line: Dedim ama kalbim sanki karakolda

• Dedim: “I said” – past tense of the verb “demek” (to say)
• ama: “but” – conjunction used to indicate a contrast or contradiction
• kalbim: “my heart” – noun (heart)
• sanki: “as if” – conjunction used to indicate a comparison or resemblance
• karakolda: “in a police station” – noun phrase (police station)
  Overall meaning: “I said it, but my heart feels as if it’s in a police station.”

Flashcards

I use Anki to memorize vocabulary. It’s a flashcard program with spaced repetition. That means it tries to quiz me on each word while I can just remember it, which helps the knowledge to burrow ever-deeper into my mind.

I can use ChatGPT to generate content for flashcards. Anki accetps

I will paste text in Turkish. You should create a glossary of all words used in the text, with English translation. The glossary should be in csv format: each line should be formatted as the Turkish word, then a comma, then the English translation. The lines should be arranged in order of the first appearance of the Turkish word in the text.

I’ve found it hard to prevent GPT inserting a space after the comma in this output format, and decided to just live with that.

I’d only recommend GPT’ing flashcards where you have some special need, such as vocabulary from a particular text or on a particular topic. If you just want a general word-list for a language, the hand-crafted shared decks available on the Anki website are much more reliable.

Language games

Squidgies is an app for GPT-enhanced language learning. They’ve done us a favour by releasing the prompts they use to generate language games and class activities. Things like:

Generate a list of questions for someone learning English to practice speaking. Topic: eating in a restaurant

or:

The objective of this game is for the player to have their partner guess the word they’re thinking of.
Correct grammatical errors and non-English text with CORRECTION on a new line. Accept partial sentences.
If the student’s response does not make sense, ask him/her to clarify what he means.

An article on why so much music comes form Sweden:

Sweden by accident created unusually good conditions for musical scene creation.
What is a scene? It is a group of people who are producing work in public but aimed at each other. [Swedish bands] performed on stage — but the audience was mainly their friends who played in other bands. If they were anything like the other local scenes I’ve seen, they challenged and supported each other to be bolder, more ambitious, better.

These scenes in turn were enabled by policies that gave Swedish kids free music lessons, with the side-effect of providing young musicians with plenty of jobs teaching music.

Something similar happened in the UK in the 80s and 90s, now imagined as a golden age of making music while claiming the dole. Thatcher inadvertently helped this along. Her Enterprise Allowance Scheme, intended to help the unemployed start new businesses, became a standard route for anybody trying to make a musical career.
So just about any band which got started in the 80s or 90s – from Oasis and Pulp all the way down – spent some time on benefits at the start.