The users of Readlang and this forum are a phenomenal group of people.
I was wandering how other people use LLMs. Maybe we could start a thread and share how we use them. These models get more powerful every day and people are finding new ways to use them? What questions do you ask them? For what type of applications? What resources have you found useful to learn how to use them better?
We could all share insights and learn from each other how to use them better.
Exploring art in a museum:
I share your sentiment about Readlang’s community.
Personally, I currently use LLMs for reading, language learning, legal breakdowns and advice (that I take with a huge grain of salt, of course), cooking recipes based on the ingredients I have, and for assistance with coding. If a year ago I barely used ChatGPT, now it’s a daily occurrence basically. Think the trend has established itself there, so I’m pretty sure I will discover more ways to integrate this technology into my life in the future.
Love the idea of using it to explore art in a museum!
I use it for so many things! I now use ChatGPT more than I use Google search.
I’ve also used the ChatGPT API for various things:
Interested to hear other uses that people have!
This applies to ALLof its output as it is still prone – by design – to random confabulation…it is just becoming more difficult to detect as we (naively) trust more complex tasks to it while populating the internet with the embedded falsehoods of its output. Deep Bullshit would be a better name right now rather than Deep Research.
How is this different than what people do? Just turn on your financial new TV.
We should always be skeptical and if the information is important and consequential, we should always check it.
These are statistical and probabilistic models. So, if a model has a 95% probability of being right, that means it’s wrong 5% of the time. Is that bull shit? If a medical diagnostic test is right 95% of the time, do we call the incorrect diagnosis bullshit and stop using the test?
Understanding that they are probabilistic means that we don’t fully trust them, but also that we don’t throw them out.
I’ve been playing a lot with the o1 pro and halucinations have come down significantly because it uses a lot of compute to verify the information.
If I ask it very hard questions it will ocasionally make mistakes, but I would argue a human would make even more given those same questions. So what is the bar?
O1 pro for example cites its resourcesh. Here’s one regarding a question about Eleusian Mysteries. This is not random bullshit from the internet.
References: – Burkert, W. Ancient Mystery Cults. Harvard University Press, 1987.
– Mylonas, G. E. Eleusis and the Eleusinian Mysteries. Princeton University Press, 1961.
– Plato, Republic, Phaedo, Symposium (Loeb Classical Library or other critical editions).
– Cicero, De Legibus II.36 (on praise of the Eleusinian rites).
The way to test these models is to ask them hard questions about what you already know. Test them in a language you know or about a text you know well. If given proper context, I would argue they are more right than people.
Again, o1 pro has come a long way. To cite Tyler Cowen in the post above, if you haven’t played with o1 pro your views about what these models can do are outdated.
I’m using Deep research. I find it extremely useful for certain tasks. It saves me time. And the beauty is that I can actually check its work. And I do. I can spend hours googleling around. Or minutes checking its sources.
The point remains though that actors who want to spread disinformation will do it. But is that new? Dissinformation and missinformation have been around for thosands of years. The internet has been full of it for a long time. Yet that didn’t stop Wikipedia from being very effective as accurate as Encyclopedia Britanica.
Don’t ask DeepSeek questions about China if you want an accurate answer. That might be true of OpenAI for other topics. Yet, we have multiple competing models. And we’ll get even more.
I think we’ll have competition for getting more accurate with these models. It will work like the press. A reputable newspaper that has a discerning audience is scared of publishing false stories because they will lose subscribers. And its competitors will keep it honest.
We will still have quality resources, Oxford Handbooks, Roudledge Encyclopedias, etc. How do those texts become authoritative? How does knowledge build? Through a peer review process, scientific method, etc. Recurisve models are applying the same concepts.
Take it with a grain of salt, always check the work, but keep your eyes open. The changes are real. Or you can discount it a miss out. There are plenty of people who still look up words in a paper dictionary. My local bookstore has a full shelf of them.
I use it for so many things! I’ve tried a few different models, but for a while, Gemini was my go-to for cross-checking my language learning—it felt like having a patient study buddy. I also relied on it to organize my endless lists for reading, gaming, shows to watch, and even coding projects. (Confession: I’d ask it to translate terminal commands between systems, and it saved me so much frustration!)
Lately, though, I’ve been gravitating toward DeepSeek—controversial, I know! But the language flow feels more natural to me, almost conversational? It’s helped me refine my prompts in a way that just clicks. The responses are clearer, which either gives me exactly what I need or inspires me to tweak my questions until everything aligns. It’s like… the better the tool understands me, the better I learn to communicate. A little meta, but it works!
I’ve become a big fan of Gemini Gems, especially for vocab practice. Having set up a gem, all I have to do is enter a video URL or a text in PDF, the language and level, press a button, and hey-presto, I have an instant vocab lesson. How you do it is entirely up to you, but I get it to select fifteen of the more challenging words from the source for the given level, which I then have to match to their definitions, also in the target language. This is followed by two more gap-fill exercises using the target words - a set of fifteen context sentences with the target words blanked out, and finally a short story using all the target words, again blanked out. I’m finding this a really fun way of (hopefully) acquiring new vocabulary. And Gemini usually suggests some follow-up activity, so I get a bit of writing practice as well.
Update
The selected target words now have a clickable link to Wiktionary and are shown together with the sentences they originally appear in.
I usually load the text or video transcript into Readlang first, to check for unknown vocab. Then I add Gemini’s definitions, which often include words I don’t know. And finally the completed example sentences and story, which I get from Gemini when I ask for answers. This is so I can have all my vocabulary in one place, which is of course Readlang.
I have another gem that produces follow-up exercises to teaching videos, another to convert sentences collected from Duolingo from Brazilian Portuguese to European Portuguese. And another which I use as an English teacher, to produce an hour-long lesson from a given video. Very handy.
Update
I’ve just discovered Flashcards in Notebook LM. I upload lists of sentences from Duolingo, and it gives me a set (of about 75) cards, with the English translation on the front and the sentence in the target language on the back. It has no sound feature, unfortunately, but when I do it on my Android phone I can highlight the target sentence and get it spoken by Google Translate.