HN user
To be fair, it started out as a set of ML notes and code snippets to piece together LLM applications. Its popularity resulted in more feature requests and contributions later on. Without a good up-front architecture (or spending time thinking about it), no wonder it starts making creaking noise.
My personal preference is Llama Index by Jerry Liu. It excels at clearer docs + better abstraction.
First of all, thanks for building it and as a user, the product is solid that matches the needs well. Note that I used 'matches' not 'solves' as the problem itself is so messy and difficult that a product like this could help but fundamentally it requires two people working together, which is super hard.
My way of somehow hacking it is to come in with low or no expectation. There are otherwise tons of great people on YC co-founder matching site, and almost all conversations I've had were excellent. Even if it didn't help me find a cofounder, I still rate the product highly.
Had a look at those lists you made, impressive. I will hit you with an email to start the converstion, I'm based in London as it looks like you are too?
Doing a trial project together is a wise move as entering into a partnership to build a business requires a leap of faith; whatever you could rely on to derisk would help. I'm in a similar position right now, maybe we could connect and see if there's any common ground?
In that context it means when a bank is regulated in one of the countries in the single market (UK in EU), it can operate without regulatory concern in all the countries there. It is understandable that certain operations will inevitably be moved to a city in the heart of EU instead of staying in London.
Nice work. Some suggestions from my personal experience using Strava:
* Most runs are training runs so they carry their purposes instead of full-effort race simulation therefore predications based on training runs are usually a bit off.
* Having said that, Strava supports tagging runs which are races; not sure if the API can expose the tags but it would be useful to do a past race based prediction.
* Other than race time predictions, another area of interest is to evaluate training quality. A Chrome plugin, StravistiX does some of it but I'd like to see more such as using VDOT based on Jack Daniels' running formula which have their meanings in training.