kevo1ution

SF version would be quite boring

should be less resources because the instances are lighter weight compared to their production equivalent. less durability/HA promises in favor of agent speed. currently measuring CPU/mem usage of each instance in the pool and cutting down more and more

we're not affiliated with supabase and this is a good point. wanted to be specific with the name like paloaltofooddelivery, but we'll likely rename as we add more different databases/services to support like clickhouse, stripe. curious if you have any that you want us to do

congrats on the launch. i'm curious how you think about on device AI vs providers that are in the cloud. where do you see the capabilities of models that can run on the phone, and are there inherent advantages to this?

nice but seriously: how do i turn on ad block? don't want to see ads on youtube

pulling a cursor on google chrome lol

there's a long tail of edge cases where a smaller model does something dumb with input/output, which causes a decent amount of pain to the user (e.g. nodemon, do we stop/do we start?). Coding agent developers can't make an opinion on every possible terminal command

maybe what we're asking for is that terminal commands keep in mind that agents are now the primary users of them, and have a feeling that new packages or commands could get wider adoption if they are better understood by a coding agent

- similar to SEO for LLMs growing in adoption - documentation sites offering .md file raw for LLMs to ingest easily

These things will make it so that your packages or libs adopted faster

most terminal commands are being run by AI. we need a standard way to tell terminal commands to be token efficient/non-interactive