Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Ask HN: What's the coolest non standard application of LLMs you've seen?

news.ycombinator.com

Post reply on HN
Print view View original

51–60 of 65 posts

Re: Ask HN: What's the coolest non standard application of LLMs you've seen?

#51

Post by GolDDranks »

tkgally wrote: post #37
GolDDranks wrote: post #9

I'm attempting to create a frequency list of words for language learners. (In Japanese.) Commonly, these lists are based in just what word appears in the text at "surface" level. However, words commonly have multiple "senses" or nuances of meaning in which they are used. Dictionaries list these senses, but it has been traditionally hard to disambiguate which sense the word is used in, given an usage in text. LLM's ma…

That’s a great idea. I hope it can be done for other languages, too. I used to help prepare study materials for Japanese learners of English. The other editors and I would try to adjust the vocabulary to keep it at an appropriate level for the target learners. Word-frequency lists provided some guidance, but they showed only how often words appeared in the surveyed texts, not the meanings in which they were used. The…

Thanks you! Yep, multi-word idioms are tough. How do you quantify whether a phrase is just a "sum" of it's words, or is there some additional meaning, "idiomness" to it. I haven't thought a lot about that yet, but it's a problem that I need to solve for this.

Re: Ask HN: What's the coolest non standard application of LLMs you've seen?

#52

Post by lysecret »

joisig wrote: post #17
lysecret wrote: post #14

Counting my calories.

Me too, initially in a chat with GPT-4 [0] and then in a (private for now) wrapper that sends me a text message when analysis is complete, sums up the day's meals, and compares to my total calories burned per Apple Watch. [0] https://joisig.com/gpt-4-passable-personal-nutritionist

Very cool!:) Just went over the article and this is close to how I use it. I implemented it in an Iphone app and added some Rag tricks. Let me know if you want to try it out.

Re: Ask HN: What's the coolest non standard application of LLMs you've seen?

#53

Post by lysecret »

maxlamb wrote: post #41
lysecret wrote: post #14

Counting my calories.

How? From meal description?

Yes from descriptions. ALso, often I have a rough idea of how many calories something has. So one of the main features is you can say: Protein shake with 140 cals and 35 grams of protein remember as P1, and then whenever I have the same thing again I just type P1.

I have an Iphone app I have been using for half a year (and lost 10kg), if there is interest write me Email in bio I might release it then ;)

Re: Ask HN: What's the coolest non standard application of LLMs you've seen?

#54

Post by tkgally »

GolDDranks wrote: post #51
tkgally wrote: post #37

Earlier quoted context omitted.

That’s a great idea. I hope it can be done for other languages, too. I used to help prepare study materials for Japanese learners of English. The other editors and I would try to adjust the vocabulary to keep it at an appropriate level for the target learners. Word-frequency lists provided some guidance, but they showed only how often words appeared in the surveyed texts, not the meanings in which they were used. The…

Thanks you! Yep, multi-word idioms are tough. How do you quantify whether a phrase is just a "sum" of it's words, or is there some additional meaning, "idiomness" to it. I haven't thought a lot about that yet, but it's a problem that I need to solve for this.

If you’d like to discuss these issues, feel free to get in touch. My website URL is on my profile page. I’m not a programmer or expert on natural language processing, but I have worked on over a dozen Japanese-English and English-Japanese dictionaries and enjoy thinking about such problems.

Re: Ask HN: What's the coolest non standard application of LLMs you've seen?

#55

Post by swah »

edit: misread the title

The uncensored one [1] - finally gave me instructions for making crack and a bomb. It felt cool that it would answer everything, like a 90s zine.

[1] https://huggingface.co/TheBloke/dolphin-2.1-mistral-7B-GGUF

Note on that page: This model is uncensored. I have filtered the dataset to remove alignment and bias. This makes the model more compliant. You are advised to implement your own alignment layer before exposing the model as a service. It will be highly compliant to any requests, even unethical ones. Please read my blog post about uncensored models. https://erichartford.com/uncensored-models You are responsible for any content you create using this model. Enjoy responsibly.

Re: Ask HN: What's the coolest non standard application of LLMs you've seen?

#56

Post by wenc »

GolDDranks wrote: post #9

I'm attempting to create a frequency list of words for language learners. (In Japanese.) Commonly, these lists are based in just what word appears in the text at "surface" level. However, words commonly have multiple "senses" or nuances of meaning in which they are used. Dictionaries list these senses, but it has been traditionally hard to disambiguate which sense the word is used in, given an usage in text. LLM's ma…

How about the highest frequency phrases and variations?

As a language learner, I’ve found that high frequency word lists to not be that useful. It’s too atomic of a unit devoid of context. Memorizing word lists don’t lead to speaking a language — but learning phrases often do. Even better is to learn phrases within a context, like a restaurant or a lecture.

LLMs might actually add value. Word frequencies are simply statistical counts, but finding common phrases is a more co more complicated problem — and the LLMs structure (attention) might actually be the solve.

(I actually ask this if ChatGPT 4 today. I ask it to tell me the highest value phrases I should learn if I’m in a restaurant. I also ask it to break down phrases for me, and give me a lesson on conjugations etc.)

Re: Ask HN: What's the coolest non standard application of LLMs you've seen?

#57

Post by _boffin_ »

tobr wrote: post #20

Maggie Appleton shared some interesting ideas a few months ago[1]. I especially find the ”Branches” concept interesting, just the idea of exploring multiple paths from a starting point in parallel. 1: https://maggieappleton.com/lm-sketchbook

Shit... this is exactly what i've been thinking of for the past few months! Those examples with the UI solve so many problems and I just love the ideas!

link: https://news.ycombinator.com/item?id=38398563#38407664

Have anything more like this?

Re: Ask HN: What's the coolest non standard application of LLMs you've seen?

#58

Post by tomcam »

hiAndrewQuinn wrote: post #39

I've recently been experimenting with training LLMs on the personal corpus of a dear family friend who passed recently, with the intent to eventually embed the device in his tombstone up north so that people can come and commune with him. He was a well-known tarot reader, mystic and Haskeller in the northern Finnish community; without his help it's very likely I would have been deported from the country before I coul…

Brilliant. Cannot wait to see the v1.0 announcement here on HN

Re: Ask HN: What's the coolest non standard application of LLMs you've seen?

#59

Post by nvy »

barnabee wrote: post #30
nvy wrote: post #13

Earlier quoted context omitted.

Thankfully humans are great at pattern matching and it's trivial for me to "vet this ideation": LLMs are notorious for getting subtleties wrong, and in legal agreements like terms of employment the subtleties are often of material import. Therefore this is a bad idea. If you don't want to read/don't understand the terms of your job offer then pay a lawyer. Asking JobOfferGPT is just asking for trouble.

I’m not sure it’s so black and white. Reading yourself (at whatever level you are capable of and can tolerate) followed by asking an LLM to highlight any areas of the terms that are non-standard, may cause concern, could be restrictive, or might cost you later could help identify subtleties you might have missed. Certainly it’d seem no worse and possibly better than just reading the terms, especially as a layperson.

And what do you do when your interpretation is correct and the LLM is incorrect, contradicting you, but you aren't sure who's correct and who isn't?

Re: Ask HN: What's the coolest non standard application of LLMs you've seen?

#60

Post by vunderba »

hiAndrewQuinn wrote: post #39

I've recently been experimenting with training LLMs on the personal corpus of a dear family friend who passed recently, with the intent to eventually embed the device in his tombstone up north so that people can come and commune with him. He was a well-known tarot reader, mystic and Haskeller in the northern Finnish community; without his help it's very likely I would have been deported from the country before I coul…

Yeah, I imagine it won't be long before we'll have virtual seances online for people who have passed.

Black mirror really popularized this idea too.

Post reply on HN