una cosa que estoy viendo es que algunos frikis de la IA/data science se están quedando atrás porque creen que los sistemas son menos potentes de lo que ya son
que si bases de datos vectoriales, que si embeddings que si...
no necesitas nada de eso
coge toda tu información, divídela en archivos de texto con nombres informativos y metadatos para que sea fácilmente indexable por grep/ls etc... y deja que el agente se encargue del resto
no necesitas nada más
I'm focusing on the ownership angle here. Sure, we can automate Prs reviews all the way down to finding issues ...
my real question is: does anyone on your team actually know what's in there?
Any advice on dealing with PR overflow?
@steipete thanks for your talk today at Telefonica :)
there were some real issues with the it part i was unable to make you a question if you dont mind
👇
We're running into a real problem here. PRs have always been a bit of a bottleneck for us, but right now it's serious.
we're opening PRs as fast as ever, and I feel like we're losing ownership in the process.
My take is that the PRs is the moment where a human can actually gain some ownership? But maybe that's the wrong instinct and we should just let it go?
🩹 clawpatch 0.1.0 is live:
Clawpatch maps codebases into semantic feature slices, reviews them for bugs and quality issues, and records explicit fix attempts with validation.
You'll be surprised how much this will find.
npm install -g clawpatch
https://t.co/8xIcXuojse