clark-kent

Why would Wakanda need their aid /s

They need to own up to their mistake sending PII to an analytics tool. They could have easily sent a uuid identifier for each user instead of email, name and organisation. Seems like a major blunder on their side.

SQS. For Ruby apps I use Shoryuken with SQS.

There is free trial and paid version.

How does it compare to https://decodeinvesting.com/chat ?

$974 million maybe!

Very interesting idea. I'm thinking about creating an AI portfolio manager (private) that invests for the long term.

Some things to watch out for:

- LLMs, by default, don't follow the best practices for trading or investing. Without careful constraints, they can ignore fundamental investment best practices. This is something I learned while building https://decodeinvesting.com/chat.

- I see Claude bought a penny stock SMX. This could be volatile, and the price could change significantly in 24 hours before the next execution at 9:30 am.

- The LLMs are day trading on some volatile securities; while LLMs could be good at day trading, unlike humans (we will find out), this setup has the disadvantage of only trading once a day.

The cutoff date for the data used to train the model is October 2023, but the AI Assistant can access historical, real-time market data, search, and browse the web. It's still not perfect, though.

That’s a YC job post not HN.

There is a lot of custom logic and proprietary data, including a custom LLM framework and an agentic workflow framework as well as an insight engine.

Not yet. I plan to see if we can offer value for technical analysis. We specialize in fundamental analysis.

It's just a research and analysis tool that automates the process of reading lots of SEC Filings and earnings call transcripts and checking the news and stock quotes back to back.

Just automates the research that users would do manually.

Red flags are things like significant drops in stock price, revenue, earnings, customer satisfaction, lawsuits, or changes in senior management.

You can specify the red flags, or the LLM will specify them for you don't include them.

You can also specify how often you want the LLM to monitor things for you.

We have offerings for both retail and institutions. Institutions can choose between on-prem solutions or a dedicated cloud deployment.

Both retail and institutions can also use for our SAAS solution. We don't share our user data with third parties.

I do review the AI interactions for the following reasons:

- To ensure the AI system (AI assistants and agents) meets expectations.

- Safety: To ensure the AI system is not generating false or misleading information.

- To understand how the AI system is performing and how to improve it.

We only look at when the stock is objectively "undervalued". I'm not saying the system will tell you that a stock like Palantir is undervalued because it has a bright future. No. This system only tells when a stock is objectively undervalued. There are a few ways to know this.

Here some examples:

- Market cap is less than book value.

- Market cap is less than free cash flow x 8

There are other ways, but these are some examples. Being undervalued doesn't mean its a good company, the trick is knowing why its undervalued and if that valuation is justified.

Can you try using https like https://decodeinvesting.com/chat/

It covers all the major stock exchanges worldwide, including NYSE, London Stock Exchange, Nasdaq, Hong Kong Stock Exchange, Euronext, and many more. In total, it covers 69 stock exchanges worldwide.

Doing RAG over financial data is ok for simple tasks. But if you want the Assistant to answer complex questions with a lot of context, and compare the metrics of multiple companies at once then just RAG over financial data will not be enough.

Our AI Assistant focuses on pulling the right data for each question over a large amount of data, then understanding and synthesizing it to provide nuanced insights.

Great suggestion! I will look into making watchlists and favorites completely free.

I will look into that. It should redirect to HTTPS. This will work https://decodeinvesting.com/chat

If you are already on AWS, then it's better to run llama3 using AWS Bedrook. With Bedrock, you only pay for what you use instead of paying for an always-on EC2 instance.

I recommend watching this https://www.youtube.com/watch?v=q1LnYLp-2qg

Very interesting. Do you mind sharing a link to the government website you refer to?

> Sam Altman, best known as a co-founder of startup accelerator Y Combinator and OpenAI — the nonprofit he started with Musk.

Did the human-in-the-loop fail to catch this on the AI generated article? Sam wasn’t a co-founder of YC accelerator.

Most stock market news comes from publicly available press releases, earnings call transcripts and 8k filings, I doubt they need to steal stories from news agencies.

Great work! I created something similar for analyzing earnings call transcripts with an LLM https://news.ycombinator.com/item?id=37231667.

I know this is an early release, but would be good to add an about us page to your site.

Have you tried employer/employee match making sites hired.com? Or try using a recruiter. That should be better than cold applying from company websites.

Your story is amazing and very inspiring.

> I was 90k in credit card debt and planning on foreclosing the company and declaring personal bankruptcy the same month we got acquired. At one point I recall having a major fight with my roommate at the time over him rounding down 30 cents on a bill we split.

I smiled and almost shed a tear reading this ^

Thats impressive. Do you mind sharing some tips that helped you scale your bootstrapped business to 4million profit?

Will Hurd is a liberal Republican. He supports Dreamers. Very early critic of Donald Trump.