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

Ask HN: Who's regularly using LLMs at work?

news.ycombinator.com

Post reply on HN
Print view View original

11–20 of 24 posts

Re: Ask HN: Who's regularly using LLMs at work?

#11

Post by scarface_74 »

wruza wrote: post #6

I use it for “introductory” programming, where it writes some script in an env I’m not familiar with and then I read the docs and clean all the bs it hallucinated into it. Often (but very not always) takes less time than learning-curveing it yourself. I also get sysadm and networking ideas from LLMs. Although here their imagination has no limits and you have to fact-check everything. They imagine cli/config options,…

I don’t know if this works in general. But when I find it hallucinating around AWS SDK or CLI calls, I ask it to “verify AWS SDK functions from the documentation”. The paid version will do a web search and then it’s usually right. I will sometimes just give it a link to the page with the documentation on it

Re: Ask HN: Who's regularly using LLMs at work?

#12

Post by sejje »

duxup wrote: post #10
sejje wrote: post #7

- I use them to create a vendor order each week. They take my voice and transcribe it into a list to text my sales reps. - I use them to OCR PDFs from my bank - I use them as a search/replace tool on CSVs - I use them to replace Google searches - I use them to code - I'm trying to use them to view (still frames from) cameras periodically I'll think of more uses, I'm sure. My work is very low tech and simple.

What do you do after you OCR the pdfs?

Turn it into CSV, sometimes transform it, confirm it's correct, paste it into my spreadsheet.

Re: Ask HN: Who's regularly using LLMs at work?

#14

Post by giaour »

My org has a bot that generates AI summaries of all internal pull requests, and it's honestly been pretty helpful to compare that (a fairly accurate guess of what the PR will do) against the PR author's description (a statement of what the PR is meant to do). The main thing I look for in PRs is an alignment of intentions and actions, so the AI summary helps, especially for large PRs.

Of course, some engineers have stopped writing PR descriptions since the bot will do it for them. But that means that the only people who can effectively review that PR are the ones who already know what it's supposed to do, which is generally a small pool.

This has been a pattern I've seen repeated with workplace AI: they make something hard a little bit easier, but in a way that will the underlying problem worse over time.

Re: Ask HN: Who's regularly using LLMs at work?

#15

Post by ivandorian »

We have been using this system to combat scammers. Our team developed and trained an in-house LLM to initiate and manage conversations with scammers across various platforms, enabling us to continuously gather their information. In our company, our primary responsibility is to extract this data and share the scammer details with both the relevant platforms (for example, Meta) and law enforcement agencies.

We transitioned from a team of manual chatters, to hard-coded conversational scripts to an LLM-driven approach. This change has allowed us to handle interactions more accurately and scale to a much larger number of conversations per day.

Less grandmas are falling victim to crypto scams. Thanks AI.

Re: Ask HN: Who's regularly using LLMs at work?

#16

Post by _1tem »

sejje wrote: post #12
duxup wrote: post #10

Earlier quoted context omitted.

What do you do after you OCR the pdfs?

Turn it into CSV, sometimes transform it, confirm it's correct, paste it into my spreadsheet.

Are you aware that AI-based OCR very often hallucinates? https://www.runpulse.com/blog/why-llms-suck-at-ocr

Re: Ask HN: Who's regularly using LLMs at work?

#18

Post by sejje »

_1tem wrote: post #16
sejje wrote: post #12

Earlier quoted context omitted.

Turn it into CSV, sometimes transform it, confirm it's correct, paste it into my spreadsheet.

Are you aware that AI-based OCR very often hallucinates? https://www.runpulse.com/blog/why-llms-suck-at-ocr

Yes. Hasn't been a problem yet for my bank pdfs.

As I said, I verify it. Since it's a total over many transactions, it's hard to hallucinate and then get the same total the bank sheet has.

Ya know?

Post reply on HN