Tag: LLMs

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.

Two AI robots squaring up to each other

AI Worksheet Wars : Google Gemini Advanced vs. ChatGPT-4

3 Comments

With this week’s release of Gemini Advanced, Google’s latest, premium AI model, we have another platform for language learning content creation.

Google fanfares Gemini as the “most capable AI model” yet, releasing benchmark results that position it as a potential ChatGPT-4 beater. Significantly, Google claims that their new top model even outperforms humans at some language-based benchmarking.

So what do those improvements hold for language learners? I decided to put Gemini Advanced head-to-head with the leader to date, ChatGPT-4, to find out. I used the following prompt on both ChatGPT-4 and Gemini Advanced to create a topic prep style worksheet like those I use before lessons. A target language text, vocab support, and practice questions – perfect topic prep:

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.

I then laid out the results, with minimal extra formatting, in PDF files (much as I’d use them for my own learning).

Here are the results.

ChatGPT-4

ChatGPT-4, gives solid results, much as expected. I’d been using that platform for my own custom learning content for a while, and it’s both accurate dependable.

The introductory text referenced the real-world topic links very well, albeit a little dry in tone. The glossary was reasonable, although ChatGPT-4 had, as usual, problems leaving out “obvious cognates” as per the prompt instructions. It’s a problem I’ve noticed often, with other LLMs too – workarounds are often necessary to fix these biases.

Likewise, the gap-fill was not “in a different order”, as prompted (and again, exposing a weakness of most LLMs). The questions are in the same order as the glossary entries they refer to!

Looking past those issues – which we could easily correct manually, in any case – the questions were engaging and sensible. Let’s give ChatGPT-4 a solid B!

A French worksheet on Reality TV, created by AI platform ChatGPT-4.

You can download the ChatGPT-4 version of the worksheet from this link.

Gemini Advanced

And onto the challenger! I must admit, I wasn’t expecting to see huge improvements here.

But instantly, I prefer the introductory text. It’s stylistically more interesting; it’s just got the fact that I wanted it to be “engaging”. It’s hard to judge reliably, but I also think it’s closer to a true CEFR A2 language level. Compare it with the encyclopaedia-style ChatGPT-4 version, and it’s more conversational, and certainly more idiomatic.

That attention to idiom is apparent in the glossary, too. There’s far less of that cognate problem here, making for a much more practical vocab list. We have some satisfyingly colloquial phrasal verbs that make me feel that I’m learning something new.

And here’s the clincher: Gemini Advanced aced the randomness test. While the question quality matched ChatGPT-4, the random delivery means the output is usable off the bat. I’m truly impressed by that.

A French worksheet on Reality TV, created by Google's premium AI platform, Gemini Advanced.

…

You can download the Gemini Advanced version of the worksheet from this link.

Which AI?

After that storming performance by Gemini Advanced, you might expect my answer to be unqualified support for that platform. And, content-wise, I think it did win, hands down. The attention to the nuance of my prompt was something special, and the texts are just more interesting to work with. Big up for creativity.

That said, repeated testing of the prompt did throw up the occasional glitch. Sometimes, it would fail to output the answers, instead showing a cryptic “Answers will follow.” or similar, requiring further prompting. Once or twice, the service went down, too, perhaps a consequence of huge traffic during release week. They’re minor things for the most part, and I expect Google will be busy ironing them out over coming months.

Nonetheless, the signs are hugely promising, and it’s up to ChatGPT-4 now to come back with an even stronger next release. I’ll be playing around with Gemini Advanced a lot in the next few weeks – I really recommend that other language learners and teachers give it a look, too!

If you want to try Google’s Gemini Advanced, there’s a very welcome two-month free trial. Simply head to Gemini to find out more!

Does AI have a noun problem? Strategies for avoiding it.

AI Has A Noun Problem : Let’s Fix It!

2 Comments

If you’re using AI for language learning content creation, you might have already spotted AI’s embarrassing secret. It has a noun problem.

Large Language Models like ChatGPT and Bard are generally great for creating systematic learning content. They’re efficient brainstormers, and can churn out lists and texts like there’s no tomorrow. One use case I’ve found particularly helpful is the creation of vocab lists – all the more so since it can spool them off in formats to suit learning tools like Anki.

But the more I’ve used it, the more it’s become apparent. AI has a blind spot that makes these straight-out-the-box vanilla lists much less useful than they could be.

A fixation with nouns.

Test it yourself; ask your platform of choice simply to generate a set of vocab items on a topic. Chances are there’ll be precious few items that aren’t nouns. And in my experience, more often than not, lists are composed entirely of noun items and nothing else.

ChatGPT-4 giving a list of French vocabulary items - all nouns.

ChatGPT-4 giving a list of French vocabulary items – all nouns.

It’s a curious bias, but I think it has something to do with how the LLM conceives key words. The term is somehow conflated with all the things to do with a topic. And nouns, we’re taught at school, are thing words.

Getting Over Your Noun Problem

Fortunately, there’s therapy for your AI to overcome its noun problem. And like most AI refining strategies, it just boils down to clearer prompting.

Here are some tips to ensure more parts-of-speech variety in your AI language learning content:

  1. Explicit Instruction: When requesting vocabulary lists, spell out what you want. Specify a mix of word types – nouns, verbs, adjectives, adverbs, etc. to nudge the AI towards a more balanced selection. When it doesn’t comply, just tell it so! More verbs, please is good start.
  2. Increase the Word Count: Simply widening the net can work, if you’re willing to manually tweak the list afterwards. Increase you vocab lists to 20 or 30 items, and the chances of the odd verb or adjective appearing are greater.
  3. Contextual Requests: Instead of asking for lists, ask the AI to provide sentences or paragraphs where different parts of speech are used in context. This not only gives you a broader range of word types, but also shows them in action.
  4. Ask for Sentence Frames: Instead of single items, ask for sentence frames (or templates) that you can swap words in an out of. For instance, request a model sentence with a missing verb, along with 10 verbs that could fill that spot. “I ____ bread” might be a simple one for the topic food.
  5. Challenge the AI: Regularly challenge the AI with tasks that require a more nuanced understanding of language – like creating stories, dialogues, or descriptive paragraphs. This can push its boundaries and improve its output.

Example Prompts

Bearing those tips in mind, try these prompts for size. They should produce a much less noun-heavy set of vocab for your learning pleasure:

Create a vocabulary list of 20 French words on the topic “Food and Drink”. Make sure to include a good spread of nouns, verbs, adjectives and adverbs. For each one, illustrate the word in use with a useful sentence of about level A2 on the CEFR scale.
Give me a set of 5 French ‘sentence frames’ for learning and practising vocabulary on the topic “Summer Holidays”. Each frame should have a missing gap, along with five examples of French words that could fit in it.
Write me a short French text of around level A2 on the CEFR scale on the topic “Finding a Job in Paris”. Then, list the main content words from the text in a glossary below in table format.

Have you produced some useful lists with this technique? Let us know in the comments!

AI prompt engineering - the toolkit for getting better results from your platform of choice.

Better AI Language Learning Content with C-A-R-E

2 Comments

AI isn’t just for chat – it’s also great at making static language learning content. And as AI gains ground as a content creation assistant, prompt engineering – the art of tailoring your requests – becomes an ever more important skill.

As you’d expect, frameworks and best practice guides abound for constructing the perfect prompt. They’re generally all about defining your request with clarity, in order to minimise AI misfires and misunderstandings. Perhaps the most well-known and effective of these is R-T-F – that’s role, task, format. Tell your assistant who it is, what to do, and how you want the data to look at the end of it.

Recently, however, I’ve been getting even more reliable MFL content with another prompt framework: C-A-R-E. That is:

  • Context
  • Action
  • Result
  • Example(s)

Some of these steps clearly align with R-T-F. Context is a broader take on role, action matches to task and result roughly to format. But the kicker here is the addition of example(s). A wide-ranging academic investigation into effective prompting recently flagged “example-driven prompting” as an important factor in improving output, and for good reason: the whole concept of LLMs is built on constructing responses from training data. It’s built on the concept of parroting examples.

Crafting AI prompts with C-A-R-E

As far as language content is concerned, C-A-R-E prompting is particularly good for ‘fixed format’ activity creation, like gap-fills or quizzes. There’s a lot of room for misinterpretation when describing a word game simply with words; a short example sets AI back on track. For example:

– I am a French learner creating resources for my own learning, and you are an expert language learning content creator.
– Create a gap-fill activity in French for students around level A2 of the CEFR scale on the topic “Environment”.
– It will consist of ten sentences on different aspects of the topic, with a key word removed from each one for me to fill out. Provide the missing words for me in an alphabetically sorted list at the end as a key.
– As an example, a similar question in English would look like this: “It is very important to look after the ———- for future generations.”

This produces excellent results in Microsoft Copilot / Bing (which we love for the freeness, obviously!) and ChatGPT. For example:

Creating AI language learning content with Microsoft Copilot / Bing Chat

Creating AI language learning content with Microsoft Copilot / Bing Chat

Providing short examples seems like an obvious and intuitive step, but it’s surprising how infrequently we tend to do it in our AI prompts. The gains are so apparent, that it’s worth making a note to always add a little C-A-R-E to your automatic content creation.

If you’ve been struggling to get reliable (or just plain sensible!) results with your AI language learning content, give C-A-R-E a try – and let us know how it goes in the comments!

A digital brain, complete with memory - ChatGPT take note!

Your ChatGPT Teacher – With Persistent Memory!

Leave a comment

The interactivity of AI models like ChatGPT and Bing make them the perfect medium for exchange-based language learning. But for one thing: their lack of persistent memory.

The standard setup, to now, has been for a ‘black box’ style conversation on AI platforms. You initiate a session with your instructions, you chat, and it’s over. You can revisit the conversation in your history, but as far as AI is concerned, it’s lost in the mists of time.

It’s something that throws a mini spanner in the works of using AI for language (or any kind of) learning. Teaching and learning are cumulative; human teachers keep records of what their students have studied, and build on previous progress.

DIY ChatGPT Memory

There seems to be little movement in the direction of AI with memory amongst the big platforms, although OpenAI’s recent announcement of memory storage for developer use might lead to third-party applications that ‘remember’. But in the meantime, users within the AI community, ever adept at finding workarounds and pushing the tech, have begun formulating their interim alternatives.

One clever way around it I recently spotted takes advantage of two elements of ChatGPT Plus: custom instructions and file upload/analysis. In a nutshell, an external text file serves as ChatGPT’s ‘memory’, storing summarised past conversations between student and AI teacher. We let ChatGPT know in the custom instructions that we’ll be uploading a history of our previous conversations at the beginning of a learning session. We also specify that it analyse this file in order to pick up where we left off. At the end of each session, we prompt it to add a round-up of the present conversation to that summary, and give the file back to us for safekeeping.

Custom Instructions

Here’s how I’ve worked the persistent memory trick into my own custom instructions:

If I upload a file ‘memory.txt’, this will be a summary of our previous conversations with you as my language teacher; you will use this to pick up where we left off and continue teaching me. When prompted by me at the end of our session, update the file with a summary of the present conversation and provide me with a link to download it for safekeeping. This summary should include a condensed glossary of any foreign language terms we’ve covered.

Wording it as such makes memory mode optional; ‘teacher remembering’ only kicks in if you upload memory.txt. This way, you can otherwise continue using regular, non-teach ChatGPT without any fuss.

The only thing that remains is to create a blank text file called memory.txt to start it all off. Remember to start a new chat before giving it a whirl too, so your new custom instructions take. As you use the technique in your everyday learning chats, you’ll see memory.txt blossom with summary detail. As an offline record of your learning, it even becomes a useful resource in its own right apart from ChatGPT.

Just make sure you keep it safe – that’s your teacher’s brain you have right there!

A page of conversation summaries - my ChatGPT 'memory' file in action.

My ChatGPT ‘memory’ file in action.

Let us know your experiences if you give this technique a go! And if you’re stuck for lesson ideas, why not check out my book, AI for Language Learners?

A deck of neon flashcards. Anki cards might not be quite as fancy!

From ChatGPT to Anki : Instant Potted Vocab Decks!

1 Comment

With cutting edge AI galvanising the language learning world, traditional tools like Anki – which would have been considered the leading edge not that long ago – seem well in the shade. But it’s not a question of either-or. Traditional and new tech can work in happy symbiosis to support language learning.

Preparing for a recent high-stakes language mission (OK, island-hopping hol!) to Greece, I wanted to turboboost my Greek vocab. Anki was my tool of choice, of course, but one question remained: where to source new flashcard decks? Large Language Models like ChatGPT and Bing were easy choices for generating topical vocab lists, but how much copy-pasting would that involve? I wasn’t keen on spending hours formatting cards manually.

Thankfully, ChatGPT Plus’ Advanced Data Analysis mode can provide a bridge between old and new. Forget that slightly intimidating title – the main boon is simply that this mode can output a text file. And, given the right format, Anki can take such a text file as an import source. With a bit of prompting prowess, we can automate the whole process – from topic to cards, in one fell swoop. Before long, I had a fresh daily drip-drip of new words and phrases, a real shot in the arm for my Greek pre-trip.

Here’s how to task ChatGPT with the whole job of Anki deck creation. If you don’t have the Plus version, no problem – scroll down for a modified version that works with completely free plans and services!

Automatic Anki Decks – Plus Style

First of all, start a new chat in ChatGPT, and make sure Advanced Data Analysis is selected in the drop-down menu under ChatGPT-4.

Selecting Advanced Data Analysis mode in ChatGPT-4.

Selecting Advanced Data Analysis mode in ChatGPT-4.

Now, we’re ready for our prompt. Like our AI speaking prep worksheets, the beauty of this is just how specific you can make your flashcards. The topic can be as broad or narrow as you like. Here’s a sample prompt to create a French deck on the talking point ‘social issues’:

Hello! I’m learning French, and I’d like you to create an Anki flashcard deck to help me. To import a deck, Anki requires a CSV file format with just a “Front”, “Back” and “Tags” field corresponding to the English. the target language phrase and the part of speech. There is no need for header fields, so the first line should represent the first vocabulary item.
Can you create such an Anki-ready list of 50 flashcard items on the topic “Social Issues” for me, then save it for me as a .txt file I can import into the app?
– Provide a good mixture of essential and useful nouns, verbs, adjectives, and useful phrases / sentence frames (ie., so it’s not just a list of nouns!).
– Provide each term in its dictionary form if appropriate, indicating gender, plural and essential or irregular parts briefly as per convention where applicable.
– Ensure that all terms relate to the contemporary culture of the target language country as much as possible.
– Please draw on resources in the original target language when researching which words will be most useful, cross-referencing with all available data and checking constantly to make sure that the target language for the flashcards is accurate and colloquial, never bookish or unnatural.

Limitations (For Now)

One limitation with the Advanced Data Analysis mode is that it can’t run concurrently with ChatGPT’s now restored web-connected mode, or Browse with Bing. All that means is that it will be relying on its banks of training data for the vocab collation, rather than the web. But in most cases, it shouldn’t make too much difference given the vastness of that data (although it will notify you apologetically about it – see below). We’re waiting for the day – hopefully soon – that OpenAI allows users to run several premium features together.

ChatGPT Plus whirring away creating an Anki deck.

ChatGPT Plus whirring away at an Anki deck. Quirky repartee not as standard, but provided by special request thanks to custom instructions! I like my AI cheeky.

Into Anki We Go

One you have your ChatGPT-infused vocab file ready, you can import it straight into Anki. In the Anki desktop app, head to File > Import, and select the file you saved. The import settings window will pop up, including, crucially, which field matches to which column of your data under Field Mapping. The app guesses correctly for the most part, but occasionally you may need to specify that the third column (part of speech) maps to the tags field.

Importing CSV data into Anki decks.

Importing CSV data into Anki decks.

And that’s it. You should get a brief report of the number of items added, and they’re ready to play with straight away. Instant, fresh vocab decks in seconds!

No ChatGPT Plus? No problem!

Now, the above is all very well if you have ChatGPT Plus. Many platforms lack the file output side of things. But you can still get them do the heavy work of vocab-hunting and file-formatting; all you need to do is the final copy-paste-save.

Here’s how to alter the prompt for plain old vanilla ChatGPT and Bing, coaxing it to provide Anki-ready output. I’ve also made the format a little clearer, which might help if you’re using slightly older models like ChatGPT-3.5.

Hello! I’m learning French, and I’d like you to create an Anki flashcard deck to help me. To import a deck, Anki requires a CSV file format with just a “Front”, “Back” and “Tags” field corresponding to the English. the target language phrase and the part of speech.
Can you create such an Anki-ready list of 25 flashcard items on the topic “Driving a Car” for me? Output the CSV data as formatted as code so I can easily copy-paste into a text file for Anki.
– Don’t include header fields in the CSV – the first line of your output should be the first vocabulary item (ie., car,la voiture,noun).
– Provide a good mixture of essential and useful nouns, verbs, adjectives, and useful phrases / sentence frames (ie., so it’s not just a list of nouns!).
– Provide each term in its dictionary form if appropriate, indicating gender, plural and essential or irregular parts briefly as per convention where applicable.
– Ensure that all terms relate to the contemporary culture of the target language country as much as possible.
– Please draw on resources in the original target language when researching which words will be most useful, cross-referencing with all available data and checking constantly to make sure that the target language for the flashcards is accurate and colloquial, never bookish or unnatural.

Your platform should spool out some easily copiable code. Simply paste this into a text file, save, and import into Anki.

Even using 3.5, I got some great results featuring practical, useful vocabulary sets.

Creating Anki decks with the free ChatGPT3.5 model.

Creating Anki decks with the free ChatGPT3.5 model.

Experiment, Experiment, Experiment!

As with all AI prompts, it’s worth experimenting with everything to tweak, improve and get the absolute best out of it. The number of cards, the mix of words and phrases, the source of the material – make it your own. When you have it just right, you can create cards for your own, or your students’ learning, in seconds.

Oh, and don’t forget to save your perfect prompts somewhere you can copy-paste them from later, too!

If you’re keen for more artificial intelligence tips to boost your learning, please check out my book AI for Language Learners. It’s packed with practical examples to fuel your linguistic adventures!