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

Reading SEC filings using LLMs

beatandraise.com

Post reply on HN
Print view View original

71–78 of 78 posts

Re: Reading SEC filings using LLMs

#71

Post by Terretta »

nnechm wrote: post #48
Terretta wrote: post #47

Earlier quoted context omitted.

This product would be a fantastic honeypot for front running researcher interest in particular investments. I don't see anything in your privacy policy that gives me comfort my (even anonymized) interest in a particular firm isn't feeding your own signals. Even if your policy promised it, I'd want to see technical controls implemented, since incentive to leverage information on searching would be so high.

Hi, Thanks for bringing that concern up. I shall keep it in mind and change it based on feedback from customers if it is an issue. Typically, people search for a company after a price move rather than before. And these are searches on publicly available data, ie data that is not proprietary and already filed with the sec. Needless to say, none of the chat traffic is used or will ever be used to feed any trading signa…

> Typically, people search for a company after a price move rather than before.

People search for a company for a reason, generally to inform a thesis towards buying or selling, and regardless of their thesis, there will generally be a price move when they act.

> And these are searches on publicly available data, ie data that is not proprietary and already filed with the sec.

Of course. But the information that someone is interested is not public, so you are crowdsourcing indication of interest.

Effectively you have a leading indicator (however soft) for order flow.

> Needless to say, none of the chat traffic is used or will ever be used to feed any trading signals for anyone.

Point is, it's not "needless" to say, it's "needful". And something other than "trust me" would be in order.

Re: Reading SEC filings using LLMs

#72

Post by andreev_io »

i_like_pie1 wrote: post #65
alxdrlitreev wrote: post #49

We've recently made COFIN AI — an AI based on ChatGPT that reads hundreds of pages of SEC filings such as 10Ks and 10Qs and checks investor calls to assist you with investment research and strategy evaluation. Pretty much similar (almost the same) to something you did. Check this out: https://cofinapp.com Let me know what you think!

asked 3 questions 1st question = got the ticker wrong. asked about company A - gave info on B 2nd question = please give info on A. it says sure 3rd question = please give info on A. pops a modal asking to pay

Shoot me a message at ilya@andlabs.co.uk. Happy to give you a free subscription.

We also just dropped our price to $1.99 per month from the previous $49.99.

Enjoy.

Re: Reading SEC filings using LLMs

#73

Post by nnechm »

Terretta wrote: post #71
nnechm wrote: post #48

Earlier quoted context omitted.

Hi, Thanks for bringing that concern up. I shall keep it in mind and change it based on feedback from customers if it is an issue. Typically, people search for a company after a price move rather than before. And these are searches on publicly available data, ie data that is not proprietary and already filed with the sec. Needless to say, none of the chat traffic is used or will ever be used to feed any trading signa…

> Typically, people search for a company after a price move rather than before. People search for a company for a reason, generally to inform a thesis towards buying or selling, and regardless of their thesis, there will generally be a price move when they act. > And these are searches on publicly available data, ie data that is not proprietary and already filed with the sec. Of course. But the information that someo…

Thank you for the advice, will implement accordingly.

Re: Reading SEC filings using LLMs

#74

Post by thisisit »

hef19898 wrote: post #15
nnechm wrote: post #2

I have been working on getting ChatGPT to answer questions that equity research analysts, investors would like to get from SEC filings. The application uses a combination of hybrid text search and LLMs for completion and does not rely much on embedding based distance searches. A core assumption underlying this is that LLMs are already pretty good and will continue to get better at reading texts. If provided with the…

I once had a collegue who used ChatGPT to sumarize our then employer's SEC filings. Results were, well, putting it mildly, mixed. Best case was a slightly less biased version of the "shareholder letters" (read: propaganda pieces) published around the same time. What ChatGPT completey missed was stuff like omissions (I'll kind of give it a pass here, how can software analyse the absence of something without having acc…

I think the challenge with using ChatGPT to summarize or read factual data lies in the probabilistic nature of LLM outputs. So, your experience is what you should expect from LLMs. Though my understanding of OPs answer is that instead of using OpenAI to read documents directly they use OpenAI to generate queries to read the document instead.

Re: Reading SEC filings using LLMs

#76

Post by hbcondo714 »

Great to see this and the other SEC Filing LLMs in the comments here. I run a freemium SEC Filings website at https://Last10K.com to help investors read 10K/Qs more efficiently. Earlier this year, we partnered with https://edgar-gpt.ai for summarizing 10K/Qs. The summaries[1] when clicked on, would then scroll to and display the actual verbiage in the SEC Filing.

This feature stayed on the site for a couple months but ultimately we mutually decided to remove it since the traction didn't meet the costs. I'm open to revisiting this topic all in the name of making verbose financial disclosures easier to understand for all of us.

[1] https://last10k.com/chatgpt.png

Re: Reading SEC filings using LLMs

#77

Post by i_like_pie1 »

nnechm wrote: post #67
i_like_pie1 wrote: post #65

Earlier quoted context omitted.

asked 3 questions 1st question = got the ticker wrong. asked about company A - gave info on B 2nd question = please give info on A. it says sure 3rd question = please give info on A. pops a modal asking to pay

I am assuming this is on Cofin and not on beatandraise.com, if so, please let me know, I shall fix it. You have 20 chats etc.

you are right. i made a mistake. its cofin and i commented on wrong post.

messed with yours and had a good experience = false alarm

Re: Reading SEC filings using LLMs

#78

Post by unparagoned »

nnechm wrote: post #25
andylynch wrote: post #24

Earlier quoted context omitted.

Are you pulling out the inline XBRL or taking a different approach? I'm curious to hear others' practical experience with it good or bad.

I am not using inline XBRL, instead relying on gpt's ability to read tables.

How exactly do you do that. Are you passing the raw HTML, or just the extracted text?
Post reply on HN