Live data from Hacker News

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

news.ycombinator.com

21–30 of 65 posts

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

#21

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…

Can you talk a little more about the process? I’m guessing you’re not just prompting gpt to list most common words.

Are you asking the LLM to annotate text and then count number of annotations?

How do you make sure that each disambiguation has a stable label throughout?

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

#22
Jira issue generator.

Custom GPT with instructions that outputs issues according to our issue templates in markdown.

Allows me to write horribly typoed bullet point lists and get out surprisingly good issues.

Gets me 80-90% done in a fraction of the time. I can then just edit them to get them to be what I need.

What I'd really want to get working is a PR desription generator.

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

#23
post #22

Jira issue generator. Custom GPT with instructions that outputs issues according to our issue templates in markdown. Allows me to write horribly typoed bullet point lists and get out surprisingly good issues. Gets me 80-90% done in a fraction of the time. I can then just edit them to get them to be what I need. What I'd really want to get working is a PR desription generator.

Gitbutler is doing that iirc and replit also might have sth like that

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

#25
post #22

Jira issue generator. Custom GPT with instructions that outputs issues according to our issue templates in markdown. Allows me to write horribly typoed bullet point lists and get out surprisingly good issues. Gets me 80-90% done in a fraction of the time. I can then just edit them to get them to be what I need. What I'd really want to get working is a PR desription generator.

Why can't the bullet points just be used as is? Either they contain enough signal, or they don't and llm won't help anyways.

I fear everything will be expanded by llms soon. "write an email, three paragraphs, about X", instead of just sending X directly. Then the receiver gets a wall of text, and uses an llm to distill it back to X' before reading. Just hope too much didn't get lost in the inverse compression through llm.

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

#26
I'm using it to filter out the content that's displayed in my browser screen as I browse: https://karimjedda.com/llms-in-the-middle-content-aware-clie...

Essentially, I wrote a small browser extension, that takes the content of LinkedIn, Twitter, YouTube posts/titles, and filters them out based on if they are clickbait, low effort, etc.

It's liberating :D

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

#27
We’re playing with embodied LLMs that can externalise thoughts in a virtual environment. The idea is to help facilitate knowledge work.

It’s not our main area of interest, but it’s been interesting to experiment with how human/machine and machine/machine interactions work in real-time when you limit how fast agents can move or write. It's much easier to engage in a dialogue with agents that can't create / move tens of sticky notes and graphics faster than you can create one.

You can see a short, old video of the environment at https://www.temin.net

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

#28
post #19

It has to be the auto-playing Tomb Raider agent, where LLMs were used to give Lara self-awareness. I've never seen anything like it. It starts off with some classical computer vision shenanigans to understand the character movement, map layout, and to create the 'desire' to explore. Then the LLM is given input of images, sound descriptions and prior thoughts, lettting Lara remark on the situation, which feels very su…

I'm watching it now, it's quite entertaining. But there are quite a few comments on YouTube suggesting it's a hoax?

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

#29

I'm using it to filter out the content that's displayed in my browser screen as I browse: https://karimjedda.com/llms-in-the-middle-content-aware-clie... Essentially, I wrote a small browser extension, that takes the content of LinkedIn, Twitter, YouTube posts/titles, and filters them out based on if they are clickbait, low effort, etc. It's liberating :D

That's awesome, I want to do something similar: categorize the content in social media, so I can choose what to see when I want. Sometimes I want to avoid politics, sometimes I'm ok with it, for example. Sometimes I want to see only content about game development.

What's your plan with your project, will you turn it into a product for others, open source it, or neither? I would love it if it was either of the former!

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

#30
post #13
post #7

Earlier quoted context omitted.

trusting any idea that floats into your head is a terrible idea. you have to vet the ideation.

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.

Post reply on HN