Enabling users at jumblejournal.org to journal by hand using openAI OCR. Also, for journal extraction of growth vectors
Ask HN: What are you actually using LLMs for in production?
41–50 of 70 posts
Re: Ask HN: What are you actually using LLMs for in production?
#42Lots of non-chatbot uses in property management. Auditing leases vs. payment ledgers. Classifying maintenance work orders. Creating work orders from inspections (photos + text). Scheduling vendors to fix these issues. Etc.
Re: Ask HN: What are you actually using LLMs for in production?
#43Analyzing firehoses of data. RSS feeds, releases, stuff like that. My job involves curating information and while I still do that process by hand, LLMs make my net larger and help me find more signals. This means hallucinations or mistakes aren't a big deal, since it all ends up with me anyway. I'm quite bullish on using LLMs as extra eyes, rather than as extra hands where they can run into trouble.
Is cost a major consideration for you here? Like if you're dealing with firehose data which I'm assuming is fairly high throughput, do you see an incentive for potentially switching to a more specific NLP classifier model rather than sticking with generative LLMs? Or is it that this is good enough/the ROI of switching isn't attractive? Or is the generative aspect adding something else here?
If you do the calculations against the cheapest available models (GPT-4.1-nano and Gemini 1.5 Flash 8B and Amazon Nova Micro for example - I have a table on https://www.llm-prices.com/ ) it is shockingly inexpensive to process even really large volumes of text.
$20 could cover half a billion tokens with those models! That's a lot of firehose.
Re: Ask HN: What are you actually using LLMs for in production?
#44I am using it for FisherLoop [1] to translate text/extract vocabulary/generate example sentences in different languages. I found it pretty reliable for longer paragraphs. For one sentence translations it lacks context and I have to manually edit sometimes. I tried adding more context like the paragraph before and after, but then I found it wouldn't follow the instructions and only translate the paragraph I wanted but also the context, which I found no good way to prevent. So now I manually verify, but it saves me still ~98% of the work.
Re: Ask HN: What are you actually using LLMs for in production?
#45I work for Hinge, the dating app. We use them for our "prompt feedback" feature, where the LLM gives constructive feedback on how to improve your prompts if it judges them as low-effort or clichéd.
Doesn't this create a signal problem long term? If everyone is using it now prompts aren’t a good gauge.
It's optional and doesn't generate responses for you, instead just nudging you in better directions. So it's certainly not generating a bunch of indistinguishable profiles. Quite the opposite, it gives people a second chance to expand on their own views or experiences.
Re: Ask HN: What are you actually using LLMs for in production?
#46Internal research assistants. Essentially 'deep research' hooked up to the internal data lake, knowledge bases, etc. It takes some iterations to make a tool like this actually effective, but once you've fixed the top N common roadblocks, it just sorta works. Modern (last 6 months) of models are amazing.
If all you've built is RAG apps up to this point, I highly recommend playing with some LLM-in-a-loop-with-tools reasoning agents. Totally new playing field.
Re: Ask HN: What are you actually using LLMs for in production?
#47One of my clients is doing m&a like crazy and we are now using it to help with directory merging. Every HR and IT department does things a little differently and we want to match them to our predefined roles for app licensing and access control.
You used to either budget for data entry or just graft directories in a really ugly way. The forest used to know about 12000 unique access roles and now there are only around 170.
Re: Ask HN: What are you actually using LLMs for in production?
#48I work for Hinge, the dating app. We use them for our "prompt feedback" feature, where the LLM gives constructive feedback on how to improve your prompts if it judges them as low-effort or clichéd.
Won’t this lead to long-term everyone using the same prompt? It seems like this already naturally happens.
Re: Ask HN: What are you actually using LLMs for in production?
#491. Pre-prompting for image and video generation. Gives you way better results for less than a cent of added cost. Although many image models do this thing for you; you have to understand each individual model and apply this judiciously.
2. I build REPLs into any manual workflow that makes use of LLMs. Instead of just being like "F@ck, it didn't work!" you can instead tell the LLM why it didn't work and help it get the right answer. Saves a ton of time.
3. Coming up with color palettes, themes, and ideas for "content". LLMs are really good at pumping out good looking input for whatever factory you have built.
Re: Ask HN: What are you actually using LLMs for in production?
#50I work for Hinge, the dating app. We use them for our "prompt feedback" feature, where the LLM gives constructive feedback on how to improve your prompts if it judges them as low-effort or clichéd.
Won’t this lead to long-term everyone using the same prompt? It seems like this already naturally happens.
It doesn’t pick your prompt, just evaluates your response. AFAIK it doesn’t suggest other prompts