Hacker Newsnew | past | comments | ask | show | jobs | submit | vwake's commentslogin

I am reading The dream of enlightenment by Anthony Gottlieb.

My goal is to read the history of ideas from Renaissance period till 2000s. Started with The Florentines by Paul Strathern. Then read The Clockwork Universe by Edward Dolnick. Now at the enlightenment era. It has been eye opening to read about the life and times of some of the great minds like Kepler, Galileo, Newton, Locke and more.


I’m building a watchlist for tracking pretty much any kind of datapoint - stocks, weather, air quality, macro indicators, and more:

https://curio-six-wheat.vercel.app/

It started as a curiosity while I was exploring some economic data. I wondered if there was a simple way to keep an eye on a particular datapoint over time, which led me to the broader question: could I have one watchlist for all the different numbers I’m interested in?

It started out as a weekend project. I’ve been finding it surprisingly useful to use myself these days, and I’m continuing to explore where it could go. Would love some feedback on it from the folks here!


Please make it work without a login, at least offer some free to use searaches so that we can see how it works.


Makes sense. I added login in order to reduce LLM calls and search cost as this is just a side project. I'll add it after a few searches. Thanks for the feedback!


Now you can try it out without providing your email ID :)


Are you considering making all charts extractable? So if I wanted to use a chart I could?

Also, it seems like a RAG on top of an LLM. Is that right?


On making charts extractable - that's a good point. I haven't thought about it so far. Curious about what you'd want here: the chart as an image, an embed, or the underlying data as a CSV?

On RAG - not quite. All datapoints are fetched from trusted sources via API or web search. An LLM interprets the question and then routes it to a source. I am not sure if RAG could fetch live datapoints.


6 days late but I'd suggest both. If you want people to use the website make the SVGs available so that people add them in their reports etc.


Thanks for getting back, I'll look into this one!


Do you detect correlations? Do you do forecasting?


Right now its limited to identifying the right data point and tracking it. I've recently added a followup feature which allows comparing with peers or with past values.

I want to explore both correlations and forecasting! Can you share more about where you feel they'll be useful? Thanks!


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: