[tenpoundhammer]

Paid for it and tried out the full experience, beats anything else I've tried by a wide margin.

My prompt,

"I'm considering buying stock in the company with symbol NU. The most important thing to me is answering the question, is the stock likely to rise in the future. Please help create a list of questions that will help me to understand the likely hood of this. Also please help to anwser those questions. Please highlight the global economic environment for the company. Any unique challenges and unique advantages. Finally let me know what others think of it"

Results: I know this stock well all though I'm not a pro. It nailed all of the relevant aspects and hits the analysis right on for everything I know about it. Pulled lot's of helpful resources and most importantly the information was timely enough to be relevant. The timely part is where other LLMS have failed miserably. I've gotten good analysis from other LLM products but they have always been way out of date which makes them useless.

[omdv]

My experience was different. I have a particular question, which I am yet to see any model to answer correctly and I just tried it out.

Q: "what are the major economic and earnings events next week and how they can affect SPX volatility and price?"

A: It gave a long and nicely formatted answer with clever visuals, using the right words about FOMC and inflation. Coherent reasoning overall, albeit quite shallow. But the economic and earnings calendars for next week are complete hallucinations, even the dates, so the whole analysis is nonsense:

Wed, Feb 21 Consumer Price Index (CPI)

Wed, Feb 21 EIA Crude Oil Inventories

Thu, Feb 22 Producer Price Index (PPI)

[toastau]

I think this is a pretty good answer. "Why?" could extend to the theory or more detail on the influences I guess. https://chatgpt.com/share/67b38dc9-d1b8-8000-bfca-c4db93f38e...

[rushingcreek]

Thank you! Really happy to know that it's working well for you -- we made the additional searches feature exactly for this type of use case.

[tenpoundhammer]

If you want more feedback, I work in software engineering and I'm happy to chat outside of HN.

[yieldcrv]

Very nice, I use LLMs to get a quick understanding of a publicly traded company too. I spent 30 minutes researching Kopin last night using Claude, as I heard they Kopin is a supplier in the $22bn IVAS contract, giving way more upside than Anduril. Starting from just that tidbit of information I got much more detail and had it make predictive models about future market caps, and negatives.

It was enough to give me timelines and risk reward models from a company I had never heard of. This used to take me many hours and a level of obsession that I find incompatible with being social. Verifying is fairly quick, but even if you aren't compelled to do that, now you can at least talk about the company in the associated trading communities and be further corrected or have your understanding challenged.

[clark-kent]

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

[sizzle]

Do you have to pay for this?

[fiiico]

This is amazing! Curious how it compares to openai deep research, did you try?

[tenpoundhammer]

I was not willing to pay $200 just to try deep research. But I'm happy to except donations if the people want a comparision :)

[jgalt212]

That's great to hear. LLMs are great when you can trust and verify, or the trust, but verify process is inexpensive. However, you can take get caught out in finance when you can't trust and verify.

[Eliezer]

If the LLM did anything besides try to explain the Efficient Market Hypothesis in response, it failed.

[vo2maxer]

If the LLM did anything besides try to explain the second law of thermodynamics, it failed.