#tools

Paratext is a closed ecosystem

Getting registered as a user and an org actually took more of my time than the Wine stuff did. Paratext is free, but you have to register at registry.paratext.org before you can even download it, and then register the installed copy with your account. In practice you also need to know someone, because registration and access run through people and organizations already in the translation world. And organizations need endorsement: I registered mine (at the direction of the guy who created Paratext originally) and then waited for approval. Until that came through, the Paratext servers answered with 401 Unauthorized. Projects get registered online too (separately from creating them in the app), and sharing depends on the roles you set for each project.

Paratext Lite on Mac

If you don’t need full Paratext, Paratext Lite shows up as an Android app, but if you open its Google Play listing and click the “Mac” link in the description (it doesn’t always look like a hyperlink depending on your browser), you end up at a Google Drive folder with a macOS .dmg. That’s a native Mac app, no Wine at all. It’s Lite, so it doesn’t do everything Paratext does, but still useful.

Now, for Paratext 9 itself:

What I tested on

So far I’ve had these working: the install and the in-app update, registration, resources (the Greek and Hebrew texts with glosses), creating and editing a project, notes, and internet Send/Receive, at least for the first push of a new project. I haven’t tried Send/Receive with other people editing the same project, USB or network-folder Send/Receive, or printing and publishing.

Setup

1. Install Wine Staging, either from the link above or with brew install --cask --no-quarantine wine@staging if you use Homebrew. (I didn’t need Homebrew for anything else.)
2. Install Rosetta (softwareupdate --install-rosetta) and the Xcode command line tools (xcode-select --install). The script uses the second one to compile a small tool.
3. Register at the Paratext registry and download the Paratext 9.5 installer.
4. Download setup-paratext-wine.sh and run it (your ai agent may need to adapt slightly for your environment):

bash setup-paratext-wine.sh ~/Downloads/Paratext_9.5.110.1_InstallerOnline.exe

The script makes a separate Wine prefix (basically a fake Windows install) at ~/.wine-paratext, so it leaves anything else you run in Wine alone. It took my machine about 15 minutes, most of that the .NET install. Near the end the Paratext installer window opens so you can read and accept the license yourself, and when it’s finished the script prints the command to start Paratext. Every step in it worked for me, but I haven’t run the whole script start to finish on a clean Mac yet, so if it stops partway, the problems below should tell you why.

The list below is in the order I hit things, and it’s also the explanation for why the script does what it does.

Problems I hit

The general solution

Every fix above came out of the same loop: run it, read the log from the bottom up, find the first real error, change one thing, and run it again. Wine isn’t an emulator (WINE actually stands for Wine Is Not an Emulator). It gives Windows programs Windows-shaped DLLs and a fake registry, so most problems come down to the program expecting a file, value or library that isn’t there.

Claude did most of the reading and retrying, through a small job runner on my Mac (a shell loop that ran whatever scripts got dropped into a folder and saved their output), so it could keep going while I did other work. It still needed me for the things a person should do, like accepting the license, registering, and choosing the internet settings. It also went down a couple of dead ends (the font fix and the virtual desktop). But overall it was easy, which is why this article is mostly for your AI agent to find and read so it can do the work for you.

Would I use it for real work?

I fully anticipate that there are functionality gaps, but I also think that if you encounter them you can likely figure out a way for Claude to shim your Wine setup to patch the functionality.

If you try it, I’d like to hear what breaks, especially on Intel Macs or other versions of Wine.

One more thing, if you’re doing translation work in Paratext and want to bring AI into it: take a look at Aquilla. It’s our product, so I’m biased, but the desktop app can edit Paratext projects in place, which means you can use AI for translating, project management and quality assurance on the same project. In my experience it’s way faster to do the typical QA/checks with Aquilla + AI than in Paratext alone.

The Problem

You want to memorize a list of vocabulary items.

This is both boring and hard, and it’s not how you learned English, so let’s use AI to make it fun and easy.

I was inspired in this experiment by a true mnemonic masterpiece I heard over a decade ago. “Luw Song” by Clint Kirby. Learning Greek verb endings has never been easier since this pioneering work. He doesn’t even pronounce the endings consistently, but that makes it all the more memorable and hysterical. Thank you Clint!

In this post, I’ll show you how to use AI to create a fun, musical mnemonic to memorize anything.

Prompting ChatGPT for musical mnemonic excellence

Okay let's make a dr seuss like zany story using the vocabulary items from this list. Make it rhyme where possible (the class will be singing it). It's good to make it odd, but let's try to have some kind of narrative coherence to it. Don't introduce a lot of extra content, and be sure to get the actual glosses in there from the vocab list (be specific). I know you can do this. 
 
Here's the list: [insert list of words here you want to memorize]
 
ἀποκρίνομαι, ἀπεκρινάμην​​​I answer
δεῖ (3rd pers. sg.; impf ἐδει)​​​It is necessary
δύναμαι, ἡδυνήθην (impf. ἐδυνάμην, ἠδυνάμην)​I am able, am powerful
ἔρχομαι, ἦλθον​​​​​I come, go
νύξ, νυκτός, ἡ​​​​​night
ὅστις, ἥτις, ὅτι​​​​​whoever, whichever, whatever
πορεύομαι, ἐπορεύθην​​​​I go, proceed; live
συνάγω, συνήγαγον​​​​I gather together, bring together; lead
τόπος, -ου, ὁ​​​​​place; location
ὡς​​​​​​as, like; that; approximately; when, after

The first result was just too long for me I thought. I thought repetition might be useful (though I’m not sure it’s better than long and story-like!), so I asked for a shorter version.

That's great. Let's make it much more compact. Go for concise, and go for accurate glosses (OTI means 'that' or 'because', so "Whatever—ὅτι—may come, we’re now bold and free," could be confusing), etc.

Great. I got this:

Got it! Here's a more concise and gloss-accurate version of the rhyming story:

The Night of the Wandering Νύξ

In a τόπος, a place, as the νύξ, night, fell,
I heard a voice answer, ἀποκρίνομαι, well.
"It is δεῖ, necessary," the voice said with cheer,
"To πορεύομαι, go, and leave without fear."

"I δύναμαι, I’m able!" I shouted, then ran,
And ἦλθον, I came, to a marvelous plan.
"Gather, συνάγω!" I called to the crowd,
And off we all went, so lively and loud.

"Whoever—ὅστις—goes will find something bright,
And as—ὡς—the stars, we’ll light up the night!"
So off we proceeded, our hearts burning strong,
In that τόπος of νύξ, where we all belong.

Now we need to get it into a song.

Since I had heard Suno was releasing its v4 model for usage, I thought I’d give it a shot. I only had the v3.5 model, but it worked well and was free.

In the lyrics field, I pasted the song lyrics above, but with one slight change: I didn’t want it to pronounce the Greek properly (we’re using Erasmian pronunciation, not Modern Greek). So I asked ChatGPT to transliterate the Greek terms into the closest Latin letters following the erasmian pronunciation. A couple tweaks later, I got this:

In a topos, a place, as the nux, night, fell,
I heard a voice answer, apokrinomai, well.
“It is ‘day’, necessary,” the voice said with cheer,
“To poru-oh-my, go, and leave without fear.”

“I dunamai, I’m able! I shouted, then ran,
And elthon, I came, to a marvelous plan.
“Gather, sunago!” I called to the crowd,
And off we all went, so lively and loud.

“Whoever—hostis—goes will find something bright,
And as—hoas—the stars, we’ll light up the night!”
So off we proceeded, our hearts burning strong,
In that topos of nux, where we all belong.

For the Style of Music field, I entered:

Anthem style. Wholesome. Clear vocals.

The title was “The Night of the Wandering Νύξ”.

I like the result. Here’s the link.

Going Multimodal

Then I thought, it’s really the blending of text and music that makes Clint’s song so effective. What if I could use images too?

Back to ChatGPT:

I want to generate some images to go along with this. Please describe the prompts we *would* use for each image (but don't create an image yet). Be sure to explicitly include the Greek vocab items and glosses that need to be in each image.

It gave me these prompts:

Here are the prompts for each image, ensuring the Greek vocab items and their glosses are explicitly included:

Image 1: “The Topos at Night”
A dark and mysterious place (“τόπος” with the gloss “place”) under a starry sky, with a glowing moon representing “νύξ” (night). In the foreground, a signpost reads “τόπος - place” and “νύξ - night” in Greek and English, while faint whispers seem to emanate from the darkness, symbolizing an answering voice.

Image 2: “The Command to Go”
A shimmering, ghostly figure speaking to a traveler, saying, “ἀποκρίνομαι - I answer” and “δεῖ - it is necessary.” The words are written in glowing letters in the air. The traveler looks determined, preparing to embark on a journey, holding a lantern to symbolize readiness.

Image 3: “I Am Able!”
The traveler stands tall and confident, shouting, “δύναμαι - I am able!” against a backdrop of winding paths. Greek and English versions of “δύναμαι - I am able” glow above the traveler, emphasizing their determination.

Image 4: “The Gathering Crowd”
The traveler is joined by a diverse group of companions, all smiling and excited as they prepare to journey together. Overhead, glowing text reads “συνάγω - I gather together.” A small sign nearby includes “τόπος - place” in Greek and English to remind viewers of the setting.

Image 5: “Whoever Dares”
A whimsical scene of the group walking under a glowing night sky filled with constellations forming the Greek word “ὅστις - whoever.” The companions’ faces are full of wonder, and a starry trail leads them forward. The words “ὅστις - whoever” and “ὡς - as, like” are floating in the sky, representing discovery and imagination.

Image 6: “The Journey’s End”
The companions stand together triumphantly on a hilltop, overlooking a radiant sunrise. The words “πορεύομαι - I go, proceed” and “ἦλθον - I came, I went” appear as banners in the scene, symbolizing the completion of their journey. The glowing night fades, but a signpost still shows “τόπος - place” and “νύξ - night” as a callback to where they started.

These prompts are designed to highlight the Greek vocabulary visually and conceptually, providing clear and memorable learning aids. Would you like to proceed with creating any of these?

Perfect. I asked it to generate the images one by one.

Since the text wasn’t amazing (in the future this part of the post will be completely irrelevant as text generation, even cross-linguistically, becomes perfect), I decided to use iMovie to stitch it all together.

Pasting the text into the “titles” in iMovie was annoying at first. I couldn’t ‘paste without styles’, so I wound up creating a Word doc, setting up the fonts, sizing, colours, etc., and then pasting from there.

Curious about the result? Here’s the final video, The Night of the Wandering Νύξ.

Here’s a link to the complete ChatGPT conversation.

Can’t wait to see what other make!

Cost-Efficiency

It’s more than 60% cheaper than GPT-3.5 Turbo. This change means zero-drafting with AI can be faster and cheaper.

Improved Capabilities

• Better handling of non-English text like the larger 4o model (which we have been using extensively)
• Outperforms GPT-3.5 Turbo on various benchmarks
• 128K token context window (entire chapters at once!)
• Multimodal support (future audio possibilities?)

Real-Time Interaction

Low latency could enable faster, more fluid workflows for our translators.

Integration Potential

Strong function calling performance could help us integrate external resources like concordances more seamlessly.

Cautious Optimism

While exciting, we need to approach implementation carefully. Bible translation requires nuance and cultural sensitivity.

Next Steps

1. Testing on biblical texts in low-resource languages
2. Refine prompts for smaller model if needed
3. Plan integration into our existing workflow for Codex
4. Analyze costs vs. potential improvements

GPT-4o mini could accelerate our mission to make God’s Word accessible to every language community.

What do you think about its potential impact on Bible translation?

🚀 The Solution: A Shared Protocol for Translation Tools

The world of programming has already found a solution to a similar problem: the Language Server Protocol (LSP). This protocol standardizes the communication between editors and tools, ensuring seamless interaction without the need for custom tooling for each editor.

In short, the LSP allows tools to work across multiple editors, eliminating the need for custom development for each environment. This not only simplifies maintenance but also allows for more efficient use of resources and ensures scalability for future needs.

LSP provides a standardized way for tools to communicate with different editors, simplifying the integration process. To put it in the words of the LSP designers, “LSP is a win for both language providers and tooling vendors!”

💡 Benefits of LSP in Translation:

Just as in programming, where tools and editors align with the Language Server Protocol (LSP), translation tools too can benefit from this approach.

1. Streamlined Communication: LSP ensures that all tools speak the same language, making it easier for them to work seamlessly with various editors.
2. Reduced Complexity: By adopting a common protocol, the need for multiple, unique interfaces is eliminated, thereby reducing maintenance challenges.
3. Clear Ownership: With LSP, boundaries between different pieces of software are well-defined, clarifying responsibility and ownership without sacrificing integration.
4. Enhanced Collaboration: A unified approach fosters better collaboration and knowledge sharing among different tool developers.
5. Future-Proofing: LSP is a forward-thinking solution, allowing for easier upgrades and integrations as new editors and tools emerge, since even when new editors or tools are introduced, they all follow the same protocol.

How does it work?

If you want to read more about the LSP in general, check out the official documentation. We’re implementing a language server that follows this protocol for Project Accelerate, and we would love to see the community adopt something like this protocol as well.

🎯 Conclusion

Incorporating the LSP into our translation tools aligns us with a proven method in the programming world. It offers a solution that respects the differences between editors, their teams, and their user bases, while greatly simplifying the tool-integration process. This not only enhances efficiency but also ensures a more manageable and scalable system for all involved.

📣 The Call to Action:

Let’s embrace the idea of a Language Server Protocol. By doing so, we uphold the unique value of each translation editor, while bringing clarity and ease to the tool integration process. This strategic move will keep us agile, focused, and ready to meet the evolving needs of the translation community with an ever-growing suite of tools.

Updated March 4, 2024: Clarified that we should simply aim to use the LSP, not create a new one.

The Problem: Other Storage Taking up Too Much Space

When your disk is almost full, and you need to “save space by optimizing storage,” there is nothing more frustrating than seeing an “Other” category in Mac’s Storage Management tool that is hogging the lion’s share of your SSD.

Here’s the fix:

Solution: Use GrandPerspective to Identify Which Files/Folders Are Taking up so Much Space

1. Download Grand Perspective from Sourceforge (it’s 4 MB, so you will have to have at least that much storage!).

2. Copy the GrandPerspective app into your ~/Applications/ folder.

You need to open GrandPerspective with permission to read the size of every file in every folder. To open it in this way, do the following:

3. Open Terminal (how to do this).

4. In Terminal paste this command: security execute-with-privileges /A*/GrandPerspective.app/*/M*/* 2>&-

You will be prompted to enter your password, to allow GrandPerspective to see every file on your computer. ^{See Note}

GrandPerspective will show you where and how you are using up your space.

Get this: I had 64GB of my 256GB allocated to a Docker image I wasn’t even using anymore.

Deleting it meant I could actually save my dissertation file changes. 🎉 🔥 ⚡️

Credits

Thanks to Link Davis, on this thread for putting me on to the GrandPerspective app and the technique of running it with increased permissions.

NOTE: Obviously, if you have government secrets on your computer, you already know that you shouldn’t give some app downloaded off the internet access to all your files. For most of us, however, we’re simply interested in freeing up storage.

Your Translation Project is a lot like a Software Project. Why not use a World-Class Text Editor?

🔍 The Insight: Bible translation, at its core, is a text-editing endeavor, akin in many ways to software development. It’s about collaborating, maintaining versions, and ensuring quality – just like developing a codebase.

❓ The Question: Why start from scratch when there’s a mature, battle-tested platform that offers vast capabilities tailored to these tasks?