Tag: content creation

A robot playwright - now even more up-to-date with SearchGPT.

Topical Dialogues with SearchGPT

As if recent voice improvements weren’t enough of a treat, OpenAI has just introduced another killer feature to ChatGPT, one that can likewise beef up your custom language learning resources. SearchGPT enhances the LLM’s ability to access and incorporate bang up-to-date information from the web.

It’s a development that is particularly beneficial for language learners seeking to create study materials that reflect current events and colloquial language use. With few exceptions until now, LLMs like ChatGPT have had a ‘data cutoff’, thanks to mass text training having an end-point (albeit a relatively recent one). Some LLMs, like Microsoft’s Copilot, have introduced search capabilities, but their ability to retrieve truly current data could be hit and miss.

With SearchGPT, OpenAI appear to have cracked search accuracy a level to rival AI search tool Perplexity – right in the ChatGPT app. And it’s as simple as highlighting the little world icon that you might already have noticed under the prompt field.

The new SearchGPT icon in the ChatGPT prompt bar.

The new SearchGPT icon in the ChatGPT prompt bar.

Infusing Prompts with SearchGPT

Switching this on alongside tried-and-tested language learning prompt techniques yields some fun – and pedagogically useful – results. For instance, you can prompt ChatGPT to generate dialogues or reading passages based on the latest news from your target language country/ies. Take this example:

A language learning dialogue on current affairs in German, beefed up by OpenAI's SearchGPT

A language learning dialogue on current affairs in German, beefed up by OpenAI’s SearchGPT

SearchGPT enables content that mirrors real-life discussion with contemporary vocabulary and expressions (already something it was great at). But it also incorporates accurate, up-to-the-minute, and even cross-referenced information. That’s a big up for transparency.

Unsure where that info came from? Just click the in-text links!

Enhancing Speaking Practice with Authentic Contexts

Beyond reading, these AI-generated dialogues serve as excellent scripts for speaking practice. Learners can role-play conversations, solo or group-wise, to improve pronunciation, intonation, and conversational flow. This method bridges the gap between passive understanding and active usage, a crucial step in achieving fluency.

Incorporating SearchGPT into your language learning content creation toolbox reconnects your fluency journey with the real, evolving world. Have you used it yet? 

Apples and oranges, generated by Google's new image algorithm Imagén 3

Google’s Imagén 3 : More Reliable Text for Visual Resources

Leave a comment

If you use AI imaging for visual teaching resources, but decry its poor text handling, then Google might have cracked it. Their new algorithm for image generation, Imagén 3, is much more reliable at including short texts without errors.

What’s more, the algorithm is included in the free tier of Google’s LLM, Gemini. Ideal for flashcards and classroom posters, you now get quite reliable results when prompting for Latin-alphabet texts on the platform. Image quality seems to have improved too, with a near-photographic finish possible:

A flashcard produced with Google Gemini and Imagén 3.

A flashcard produced with Google Gemini and Imagén 3.

The new setup seems marginally better at consistency of style, too. Here’s a second flashcard, prompting for the same style. Not quite the same font, but close (although in a different colour).

A flashcard created with Google Gemini and Imagén 3.

A flashcard created with Google Gemini and Imagén 3.

It’s also better at real-world details like flags. Prompting in another engine for ‘Greek flag’, for example, usually results in some terrible approximation. Not in Imagén 3 – here are our apples and oranges on a convincing Greek flag background:

Apples and oranges on a square Greek flag, generated by Google's Imagén 3

Apples and oranges on a square Greek flag, generated by Google’s Imagén 3

It’s not perfect, yet. For one thing, it performed terribly with non-Latin alphabets, producing nonsense each time I tested it. And while it’s great with shorter texts, it does tend to break down and produce the tell-tall typos with anything longer than a single, short sentence. Also, if you’re on the free tier, it won’t allow you to create images of human beings just yet.

That said, it’s a big improvement on the free competition like Bing’s Image Creator. Well worth checking out if you have a bunch of flashcards to prepare for a lesson or learning resource!

Shelves of helpful robots - a bit like Poe, really!

Which LLM? Poe offers them all (and some!)

Leave a comment

One of the most frequent questions when I’ve given AI training to language professionals is “which is your favourite platform?”. It’s a tricky one to answer, not least because we’re currently in the middle of the AI Wars – new, competing models are coming out all the time, and my personal choice of LLM changes with each new release.

That said, I’m a late and recent convert to Poe – an app that gives you them all in one place. The real clincher is the inclusion of brand new models, before they’re widely available elsewhere.

To illustrate just how handy it is, just a couple of weeks ago, Meta dropped Llama 3.1 – the first of their models to really challenge the frontrunners. However, unless you have a computer powerful enough to run it locally, or access to Meta AI (US-only right now), you’ll be waiting a while to try it.

Enter Poe. Within a couple of days, all flavours of Llama 3.1 were available. And the best thing? You can interact with most of them for nothing.

The Poe Currency

Poe works on a currency of Compute Points, which are used to pay for messages to the model. More powerful models guzzle through compute points at a higher rate, and models tend to become cheaper as they get older. Meta’s Llama-3.1-405B-T, for example, costs 335 points per message, while OpenAI’s ChatGPT-4o-Mini comes in at a bargain 15 points for each request.

Users of Poe’s free tier get a pretty generous 3000 Compute Points every day. That’s enough credit to work quite extensively on some of the older models without much limitation at all. But it’s also enough to get some really useful (8-ish-requests daily) use from Llama 3.1. And, thanks to that, I can tell you – Llama 3.1 is great at creating language learning resources!

Saying that, with the right prompt, most of the higher-end models are, these days. Claude-3.5-Sonnet is another favourite – check out my interactive worksheet experiments with it here. And yes, Claude-3.5-Sonnet is available on Poe, at a cost of 200 points per message (and that’s already dropped from its initial cost some weeks back!). Even the image generation model Flux has made its way onto the platform, just days after the hype. And it’s a lot better with text-in-image (handy if you’re creating illustrated language materials).

Poe pulls together all sorts of cloud providers in a marketplace-style setup to offer the latest bots, and it’s a model that works. The latest and greatest will always burn through your stash of Computer Points faster, but there’s still no easier way to be amongst the first to try a new LLM!

AI Parallel Texts for Learning Two Similar Languages

Leave a comment

I’ve seen a fair few social media posts recently about linguist Michael Petrunin’s series of Comparative Grammars for polyglots. They seem to have gone down a storm, not least because of the popularity of triangulation as a polyglot strategy.

They’re a great addition to the language learning bookshelf, since there’s still so little formal course material that uses this principle. Of course, you can triangulate by selecting course books in your base language, as many do with Assimil and other series like the Éditions Ellipse.

Parallel Texts à la LLM

But LLMs like ChatGPT, which already do a great job of the parallel text learning style, are pretty handy for creative comparative texts, too. Taking a story format, here’s a sample parallel text prompt for learners of German and Dutch. It treats each sentence as a mini lesson in highlighting differences between the languages.

I’m learning Dutch and German, two closely related languages. To help me learn them in parallel and distinguish them from each other, create a short story for me in Dutch, German and English in parallel text style. Each sentence should be given in Dutch, German and English. Purposefully use grammatical elements which highlight the differences between the languages, which a student of both does need to work hard to distinguish, in order to make the text more effective.

The language level should be lower intermediate, or B1 on the CEFR scale. Make the story engaging, with an interesting twist. Format the text so it is easy to read, grouping the story lines together with each separate sentence on a new line, and the English in italics.

You can tweak the formatting, as well as the premise – specify that the learner already speaks one of the languages more proficiently than the other, for example. You could also offer a scenario for the story to start with, so you don’t end up with “once upon a time” every run. But the result is quite a compact, step-by-step learning resource that builds on a comparative approach.

ChatGPT creating parallel texts in German and Dutch with an English translation.

ChatGPT creating parallel texts in German and Dutch with an English translation.

Variations and Limitations

I also tried prompting for explanatory notes:

Where the languages differ significantly in grammar / syntax, add an explanatory note (in English) to the sentences, giving details.

This was very hit and miss, with quite unhelpful notes in most runs. In fact, this exposes the biggest current limitation of LLMs: they’re excellent content creators, but still far off the mark in terms of logically appraising the language they create.

It is, however, pretty good at embellishing the format of its output. The following variation is especially impressive in an LLM platform that shows a preview of its code:

I’m learning Spanish and Portuguese, two closely related languages. To help me learn them in parallel and distinguish them from each other, create a short story for me in Spanish, Portuguese and English in parallel text style. Each sentence should be given in Spanish, Portuguese and English. Purposefully use grammatical elements which highlight the differences between the languages, which a student of both does need to work hard to distinguish, in order to make the text more effective.

The language level should be lower intermediate, or B1 on the CEFR scale. Make the story engaging, with an interesting twist.

The output should be an attractively formatted HTML page, using a professional layout. Format the sentences so they are easy to read, grouping the story lines together with each separate sentence on a new line, and the English in italics. Hide the English sentences first – include a “toggle translation” button for the user.

Claude by Anthropic creating an HTML-formatted parallel story in Spanish and Portuguese.

Claude by Anthropic creating an HTML-formatted parallel story in Spanish and Portuguese.

It’s another use case that highlights LLMs’ greatest strength: the creation of humanlike texts. For linguists, it matters not a jot how much (or little) deep understanding there is beneath that. With the language quality now almost indistinguishable from real people-speak, AI texts serve as brilliant ‘fake authentic’ language models.

e-Stories as parallel texts are yet another fun, useful flavour of that!

Robots exchanging gifts. We can exchange - and adapt - digital resources now, with Claude's shareable Artifacts.

Sharing Your Language Learning Games with Claude Artifacts

Leave a comment

If Claude’s recent improvements weren’t already impressive enough, Anthropic has only gone and done it again – this time, by making Artifacts shareable.

Artifacts are working versions of the programs and content you, the user, prompt for in Claude. For example, they pop up when you ask the AI to write a language practice game in HTML, running the code it writes as a playable activity. Instant language learning games – no coding required.

Now, you can share your working, fully playable creations, with a simple link.

Instant Spanish Quiz with Claude

Take this simple Spanish quiz (very topical given the forthcoming Euros 2024 final!). I prompted for it as follows:

Create an original, self-contained quiz in Spanish for upper beginner / lower intermediate students of the language, on the topic “Spain in the European Football Championships”. It should be completely self-contained in an HTML page. The quiz should be multiple choice, with ten questions each having four alternative answer buttons – only one is right, and there is always one ‘funny’ alternative answer in the mix too.

Every time the quiz is played, the questions and the answers are in a random order. The student can keep trying answers until they get the right one (obviously after clicking an answer button, it should be disabled). Incorrect buttons turn red – correct ones green. Keep score of the player’s accuracy as they work through the questions (number of correct clicks / total clicks).

Make sure it looks attractive, slick and smart too, with CSS styling included in the HTML page.

If you have Artifacts turned on (see here for more). you should see your working game appear in a new pane. But now, you’ll also see a little Publish link in the bottom-right corner. Click this, and you can choose to make your creation public with an access link.

Publishing your working language activities using a share link with Claude Artifacts

Publishing your working language activities using a share link with Claude Artifacts

Remixing Artifacts

But wait – there’s more. When colleagues access your Artifact, they will see a Remix button in that bottom-right corner.

Remixing Artifacts in Claude

Remixing Artifacts in Claude

By hitting that, they can pick up where you left off and tweak your materials with further prompting. For instance, to keep the quiz format but change the language and topic, they could simply ask:

Now create a version of this quiz for French learners on the topic “France at the Olympic Games”.

It makes for an incredibly powerful way to network your learning resources. It’s also perfectly possible to take advantage of all this using only Claude’s free tier, which gives you 10 or so messages every few hours.

More than enough to knock up some learning games.

Have you created anything for colleagues to adapt and share on in Claude? Let us know in the comments!

A language learning topic menu created by Claude AI.

Claude Artifacts for Visually Inspired Language Learning Content

Leave a comment

If you create language learning content – for yourself, or for your students – then you need to check out the latest update to Claude AI.

Along with a competition-beating new model release, Anthropic have added a new feature called Artifacts to the web interface. Artifacts detects when there is self-contained content it can display – like webpage code, or worksheet text – and it pops that into a new window, running any interactive elements on the fly. In a nutshell, you can see what you create as you create it.

This makes it incredibly easy to wrap your learning content up in dynamic formats like HTML and JavaScript, then visually preview and tweak it to perfection before publishing online. This favours interactive elements like inline games, which can be impressively slick when authored by Claude’s Sonnet 3.5; it turns out that model update is a real platform-beater when it comes to coding.

Using Claude’s new Artifacts Feature

You can give Artifacts a whirl for free, as Claude’s basic tier includes a limited number of interactions with its top model every few hours. That’s more than enough to generate some practical, useful material to use straight away.

First of all, you’ll need to ensure that the feature is enabled. After logging into Claude, locate the little scientific flask icon by the text input and click it.

Claude - locating the experimental features toggle

Claude – locating the experimental features toggle

A window should pop up with the option to enable Artifacts if it’s not already on.

Claude - enabling Artifacts.

Claude – enabling Artifacts.

Now it’s on, you just need a prompt that will generate some ‘Artifactable’ content. Try the prompt below for an interactive HTML worksheet with a reading passage and quiz:

Interactive HTML Worksheet Prompt

Create an original interactive workbook for students of French, as a self-contained, accessible HTML page. The target language level should be A2 on the CEFR scale. The topic of the worksheet is “Summer Holidays“. The objective is to equip students with the vocabulary and structures to chat to native speakers about the topic.

The worksheet format is as follows:

– An engaging introductory text (250 words) using clear and idiomatic language
– A comprehensive glossary of key words and phrases from the text in table format
– A gap-fill exercise recycling the vocabulary and phrases – a gapped phrase for each question with four alternative answer buttons for students to select. If they select the correct one, it turns green and the gap in the sentence is filled in. If they choose incorrectly, the button turns red. Students may keep trying until they get the correct answer.

Ensure the language is native-speaker quality and error-free. Adopt an attractive colour scheme and visual style for the HTML page.

With Artifacts enabled, Claude should spool out the worksheet in its own window. You will be able to test the interactive elements in situ – and then ask Claude to tweak and update as required! Ask it to add scoring, make it drag-and-drop – it’s malleable ad infinitum.

An interactive worksheet created by Claude.ai, displaying in the new Artifacts window

An interactive worksheet created by Claude, displaying in the new Artifacts window

Once created, you can switch to the Artifacts Code tab, then copy-paste your page markup into a text editor to save as an .html file. Then, it’s just a case of finding a place to upload it to.

Pulling It Together

After you’re done with the worksheets, you can even ask Claude to build a menu system to pull them all together:

Now create a fun, graphical, colourful Duolingo-style topic menu which I can use to link to this worksheet and others I will create. Use big, bold illustrations. Again, ensure that it is a completely self-contained HTML file.

Here’s the result I got from running that – again, instantly viewable and tweakable:

A language website menu created by Claude.ai, displayed in Claude's Artifacts feature.

A language website menu created by Claude, displayed in the Artifacts feature.

You’ve now got the pieces to start to stitch together into something much bigger than a single worksheet.

Instant website – without writing a line of code!

Have you had chance to play with Claude’s new Artifacts feature yet? Let us know in the comments what you’ve been creating!

ChatGPT French travel poster

A Second Shot at Perfect Posters – ChatGPT’s Image Tweaker

Leave a comment

The big ChatGPT news in recent weeks is about images, rather than words. The AI frontrunner has added a facility to selectively re-prompt for parts of an image, allowing us to tweak sections that don’t live up to prompt expectations.

In essence, this new facility gives us a second shot at saving otherwise perfect output from minor issues. And for language learning content, like posters and flashcards, the biggest ‘minor’ issue – the poor spellings that crop up in AI image generation – makes the difference between useful and useless material.

Rescuing ChatGPT Posters

Take this example. It’s a simple brief – a stylish, 1950s style travel poster for France. Here’s the prompt I used to generate it:

Create a vibrant, stylish 1950s style travel poster featuring Paris and the slogan “La France”.

I wanted the text “La France” at the top, but, as you can see, we’ve got a rogue M in there instead of an N.

ChatGPT generated image of a French travel poster

To target that, I tap the image in the ChatGPT app. It calls up the image in edit mode, where I can highlight the areas that need attention:

ChatGPT image editing window

Then, I press Next, and can re-prompt for that part of the image. I simply restate the slogan instructions:

The slogan should read “La France”.

The result – a correct spelling, this time!

ChatGPT French travel poster

It can take a few goes. Dodgy spelling hasn’t been fixed; we’ve just been given a way to try again without scrapping the entire image. Certain details also won’t be retained between versions, such as the font, in this example. Others may be added, like the highly stylised merging of the L and F in the slogan (a feature, rather than a bug, I think!).

But the overall result is good enough that our lovely 1950s style poster wasn’t a total write-off.

Another case of AI being highly imperfect on its own, but a great tool when enhanced by us human users. It still won’t replace us – just yet!

Image tweaking is currently only available in the ChatGPT app (iOS / Android).

Neon robots racing. Can Claude 3 win the AI race with its brand new set of models?

Claude 3 – the New AI Models Putting Anthropic Back in the Game

Leave a comment

You’d be forgiven for not knowing Claude. This chirpily-named AI assistant from Anthropic has been around for a while, like its celebrity cousin ChatGPT. But while ChatGPT hit the big time, Claude hasn’t quite progressed beyond the Other Platforms heading in most AI presentations – until now.

What changed everything this month was Anthropic’s release of all-new Claude 3 models – models that not only caught up with ChatGPT-4 benchmarks, but surpassed them. It’s wise to take benchmarks with a pinch of salt, not least because they’re often internal, proprietary measures. But the buzz around this latest release echoed through the newsletters, podcasts and socials, suggesting that this really was big news.

Tiers of a Claude

Claude 3 comes in three flavours. The most powerful, Opus, is the feistiest ChatGPT-beater by far. It’s also, understandably, the most processor-intensive, so available only as a premium option. That cost is on a level with competitors’ premium offerings, at just under £20 a month.

But just a notch beneath Opus, we have Sonnet. That’s Claude 3’s mid-range model, and the one you’ll chat with for free at https://claude.ai/chats. Anthropic reports that Sonnet still pips ChatGPT-4 on several reasoning benchmarks, with users praising how naturally conversational it seems.

Finally, we have a third tier, Haiku. This is the most streamlined of the three in terms of computing power. But it still manages to trounce ChatGPT-3.5 while coming impressively close to most of those ChatGPT-4 benchmarks. And the real clincher?

It’s cheap.

Haiku costs a fraction of the price per token of competing models to developers. That means it’s a lot cheaper to build it into language learning apps, opening up a route for many to incorporate AI into their software. That lower power usage too is a huge win against a backdrop of serious concerns around AI energy demands.

Claude and Content Creation

So how does it measure up in terms of language learning content? I set Claude’s Sonnet model loose on the sample prompt from my recent Gemini Advanced vs. ChatGPT-4 battle. And the verdict?

It more than holds its own.

Here’s the prompt (feel free to adapt and use this for your own worksheets – it creates some lovely materials!):

Create an original, self-contained French worksheet for students of the language who are around level A2 on the CEFR scale. The topic of the worksheet is “Reality TV in France“.

The worksheet format is as follows:

– An engaging introductory text (400 words) using clear and idiomatic language
– Glossary of 10 key words / phrases from the text (ignore obvious cognates with English) in table format
– Reading comprehension quiz on the text (5 questions)
– Gap-fill exercise recycling the same vocabulary and phrases in a different order (10 questions)
– ‘Talking about it’ section with useful phrases for expressing opinions on the topic
– A model dialogue (10-12 lines) between two people discussing the topic
– A set of thoughtful questions to spark further dialogue on the topic
– An answer key covering all the questions

Ensure the language is native-speaker quality and error-free.

Sonnet does an admirable job. If I’m nitpicking, the text is perhaps slightly less fun and engaging than Gemini Advanced. But then, that’s the sort of thing you could sort out by tweaking the prompt.

Otherwise, it’s factual and relevant, with some nice authentic cultural links. The questions make sense and the activities are useful. Claude also followed instructions closely, particularly with the inclusion of an answer key (so often missing in lesser models).

There’s little to quibble over here.

A language learning worksheet created with Claude 3 Sonnet.

A Claude 3 French worksheet. Click here to download the PDF!

Another Tool For the Toolbox

The claims around Claude 3 are certainly exciting. And they have substance – even the free Sonnet model available at https://claude.ai/chats produces content on a par with the big hitters. Although our focus here is worksheet creation, its conversational slant makes it a great option for experimenting with live AI language games, too.

So if you haven’t had a chance yet, go and get acquainted with Claude. Its all-new model set, including a fabulous free option, makes it one more essential tool in the teacher’s AI toolbox.

An illustration of a cute robot looking at a watch, surrounded by clocks, illustrating AI time-out

Avoiding Time-Out with Longer AI Content

Leave a comment

If you’re using AI platforms to create longer language learning content, you’ll have hit the time-out problem at some point.

The issue is that large language models like ChatGPT and Bard use a lot of computing power at scale. To keep things to a sensible minimum, output limits are in place. And although they’re often generous, even on free platforms, they can fall short for many kinds of language learning content.

Multi-part worksheets and graded reader style stories are a case in point. They can stretch to several pages of print, far beyond most platform cut-offs. Some platforms (Microsoft Copilot, for instance) will just stop mid-sentence before a task is complete. Others may display a generation error. Very few will happily continue generating a lengthy text to the end.

You can get round it in many cases by simply stating “continue“. But that’s frustrating at best. And at worst, it doesn’t work at all; it may ignore the last cut-off sentence, or lose its thread entirely. I’ve had times when a quirky Bing insists it’s finished, and refuses, like a surly tot, to pick up where it left off.

Avoiding Time-Out with Sectioning

Fortunately, there’s a pretty easy fix. Simply specify in your prompt that the output should be section by section. For example, take this prompt, reproducing the popular graded reader style of language learning text but without the length limits:

You are a language tutor and content creator, who writes completely original and exciting graded reader stories for learners of all levels. Your stories are expertly crafted to include high-frequency vocabulary and structures that the learner can incorporate into their own repertoire.

As the stories can be quite long, you output them one chapter at a time, prompting me to continue with the next chapter each time. Each 500-word chapter is followed by a short glossary of key vocabulary, and a short comprehension quiz. Each story should have five or six chapters, and have a well-rounded conclusion. The stories should include plenty of dialogue as well as prose, to model spoken language.

With that in mind, write me a story for French beginner learners (A1 on the CEFR scale) set in a dystopian future.

By sectioning, you avoid time-out. Now, you can produce some really substantial learning texts without having to prod and poke your AI to distraction!

There may even be an added benefit. I’ve noticed that the quality of texts output by section may even be slightly higher than with all-at-once content. Perhaps this is connected to recent findings that instructing AI to thing step by step, and break things down, improves results.

If there is a downside, it’s simply that sectioned output with take up more conversational turns. Instead of one reply ‘turn’, you’re getting lots of them. This eats into your per-conversation or per-hour allocation on ChatGPT Plus and Bing, for example. But the quality boost is worth it, I think.

Has the section by section trick improved your language learning content? Let us know your experiences in the comments!

An image of a robot struggling with numbreed blocks. AI has a problem with random ordering.

Totally Random! Getting Round AI Random Blindness in Worksheet Creation

2 Comments

If you’re already using AI for language learning content creation, you’ve probably already cried in horror at one of its biggest limitations. It’s terrible at putting items in a random order.

Random order in language learning exercises is pretty essential. For instance, a ‘missing words’ key below a gap-fill exercise should never list words in the same order as the questions they belong to.

Obvious, right? Well, to AI, it isn’t!

Just take the following prompt, which creates a mini worksheet with an introductory text and a related gap-fill exercise:

I am learning French, and you are a language teacher and content creator, highly skilled in worksheet creation.
Create a French worksheet for me on the topic “Environmentally-Friendly Travel”. The language level should be A2 on the CEFR scale, with clear language and a range of vocabulary and constructions.
The worksheet starts with a short text in the target language (around 250 words) introducing the topic.
Then, there follows a gap-fill exercise; this consists of ten sentences on the topic, related to the introductory text. A key content word is removed from each sentence for the student to fill in. For instance, ‘je —— en train’ (where ‘voyage’ is removed).
Give a list of the removed words in a random order below the exercise.

The output is very hit and miss – and much more miss! Perhaps 90% of the time, ChatGPT lists the answer key in the order of the questions. Either that, or it will produce feeble jumbling attempts, like reversing just the first two items on the list.

AI’s Random Issue

One prompt-tweaking tip you can try in these cases is SHOUTING. Writing this instruction in caps can sometimes increase the bullseyes. Put them IN RANDOM ORDER, darn it! It doesn’t help much here, though. It just doesn’t seem worth relying on Large Language Models like ChatGPT to produce random results.

The reason has something to do with the fundamental way these platforms function. They’re probability machines, guessing what word should come next based on calculations of how likely word X, Y or Z will be next. Their whole rationale is not to be random; you might even call then anti-random machines.

No wonder they’re rubbish at it!

A Road Less Random

So how can we get round this in a reliable way that works every time?

The simplest fix, I’ve found, is to find another, non-random way to list things differently from the question order. And the easiest way to do that is to simply list things alphabetically:

I am learning French, and you are a language teacher and content creator, highly skilled in worksheet creation.
Create a French worksheet for me on the topic “Environmentally-Friendly Travel”. The language level should be A2 on the CEFR scale, with clear language and a range of vocabulary and constructions.
The worksheet starts with a short text in the target language (around 250 words) introducing the topic.
Then, there follows a gap-fill exercise; this consists of ten sentences on the topic, related to the introductory text. A key content word is removed from each sentence for the student to fill in. For instance, ‘je —— en train’ (where ‘voyage’ is removed).
Give a list of the removed words in alphabetical order below the exercise.

The likelihood of this order being the same as the questions is minimal. Hilariously, AI still manages to mess this order up at times, adding the odd one or two out-of-place at the end of the list, as if it forgot what it was doing, realised, and quickly bunged them back in. But the technique works just fine for avoiding the order giving the answers away.

A simple fix that basically ditches randomness completely, yes. But sometimes, the simplest fixes are the best!

Random blindness is a good reminder that AI isn’t a magical fix-all for language learning content creation. But, with an awareness of its limitations, we can still achieve some great results with workarounds.