If you actually did 10k queries a day with any free search service you'd quickly find yourself banned.
ChatGPT deep research does a lot of searches, but it's also heavily rate-limited even on paid accounts.
Building a search index, running a lot of servers, storing and querying all that data costs money. Even a cheap search API is gonna cost a bit for 10k queries if the results are any good.
Kagi charges me 15 USD and last month I've done 863 searches with it, more than worth it for the result quality. For me the Google API would be cheaper. I'm pretty sure Kagi would kick me out if I did 10k searches a day even if I'm paying for "unlimited searches".
A similar API from Bing costs between 15-25 USD for 1000 searches. Exa.ai costs 5 dollars for 1000 searches, and it goes up to 25 dollars if you want more than 25 results for your query.
Agree, the AI companies aren’t able to improve the base models so they’re pivoting to making add-ons like “agents” which seem to only be instructions atop the base models.
GHG emissions from boat transport are actually a very low % of the total GHG emissions from producing that food. Moving it across the country on a truck would certainly produce more emissions than shipping it by boat from abroad.
Yeah suggestions are way too obvious. I put cycling in as an interest and it gave me 4 different helmets to choose from… errr
I think in general that suggesting items for peoples hobbies is usually a bad idea because if someone is passionate about cycling they probably know the exact gear they want, me who knows nothing about this topic can’t choose a good gift.
It’s better to buy gifts you do know something about, eg if I’m really in to kitchen knives I could buy a nice knife for someone because everyone needs a good knife and I can choose a good one.
Thanks for the feedback! You're absolutely right, hobby related gifts can be tricky, especially for enthusiasts who have specific preferences. I'll work on refining the algorithm to focus on more universally appreciated gifts. Open to more ideas on improving the approach!