Thanks ccheney, I think I found the issue and fixed it. Sorry again for folks running into issues, really appreciate folks interested enough to follow along and help troubleshoot as well
Yes, the prompt that I am using does bias towards buying because I am specifically asking it to make a recommendation on a stock to buy and the holding period.
Data gets pulled from the Alpaca News API in the morning, then it gets sent to all three models. You can see a summary of the prompt used to determine the recommendations here: https://news.ycombinator.com/item?id=42560034
It currently makes up to recommendations, since not all stocks support fractional shares (I'm only doing $5 per trade). As part of the buy recommendation, a holding period is suggested as well.
Once the holding date is reached, that is when the sell order happens.
Would love to answer any other questions you may have.
I don't have a hard set maximum hold date, but planning on running at least buys for a year. I will re-evaluate consistently to see if it is still useful to keep up and running.
Yeah, I don't expect anything super novel to come out of this or have any unrealistic expectations. This is mostly a fun and unscientific project I'm using to learn and build some skills and thought some HN folks would find some fun in it.
Another good suggestion I could implement is measuring against something like VOO, if all the money was invested in that instead of these individual trades.
None of the stocks have been sold yet, this is just day 2, so once some sales happen, then performance will be better measured. If you scroll down, you can see the unrealized performance.
3. Time-Bound Precision:
Instead of vague "3-6 months" holding periods, I require exact hour calculations tied to specific catalysts like:
- FDA approval dates
- Earnings releases
- Product launches
- Conference presentations
4. Quality Controls:
- Must be valid NYSE/NASDAQ symbols
- Diverse across sectors/market caps
- Conviction level scoring (1-10)
- Each pick needs unique thesis + catalyst
- JSON output format for consistency
The key is combining structured analysis with creative discovery - pushing the AI to look beyond obvious choices while maintaining some analytical rigor.
I tried releasing an iOS sticker pack app that had an actual use case (allowing you to markup and annotate iMessage conversations). I was hoping would give some passive income. Had a good first day and then dropped off a cliff.
Couple of key differences. CUPS is serving mainly as a platform to help you order coffee at a cafe. We use a certified Q Grader to grade every drink and cafe that shows up in the app. As far as I can tell, CUPS does not rate the cafes or drinks, simply acts as a portal to buy drinks.