tensward

In most harness it's already built in not to print the secrets, you can use also services like AWS secretes or 1password that allow using temporary access

I just don't let AI write any unit tests, only e2e tests, if you allow it to write unit test you end up with 5000 tests for each button, it's useless and takes a lot of resource.

AI now can do very accurate and trustworthy e2e tests, and this is how your end users will use the product anyway, but you can run a lot of scenarios in parallel and fix bugs faster than before, the approach of testing need to change imo

I think we are already there, we need to decide which control we want to keep, but I think testing the product through main use cases and letting AI test edge cases already solve most of your issue, you can fix bugs faster than before so the approach of how code is delivered have to change

Yeah like someone willingly pay for office 365

Wonder how it would feel because the details shown seems a bit slow to edge device use

Depends on your use case, overall most of the time it's not worth it, regular pay per token are heavily subsidised right now and hard to match, but for non coding use cases some models work great and you can host them yourself, but again it require a but more of a hustle

As part of my previous job I tried to deploy a local model on a client's environment, then I learned about the balancing act called inference optimisation, is was a huge headache back then and it gave me the idea to create Tesnward - a local AI inference optimisation tool - Tensward detect your environment and help you optimise inference, it runs completely local

check it out! https://github.com/Tensward/tensward