31–40 of 169 posts
Here is another technique to save tokens: allow the model to read a skeleton of the source code before reading the code, to give it an index into the code so it can read targeted chunks. There is a tool that uses ripgrep and treesitter that does this [1], adapted from the maki coding agent. [1]: https://github.com/ninjaxtools/treesitter-index
STOP hijacking my scroll. I don't know why chrome even allow such behavior? And, I can't believe this is from official spotify.... What a joke.
Dang, not even Spotify care enough to not write AI slop articles. We’re fucked.
It doesn't work well in practice. Try it yourself, use a big model like Opus or Sol to implement everything by first making a plan using plan mode. Then try distributing the task to a cheaper models like Luna Max or Gemini Flash 3.8. During planning, the big model already reads the relevant files in context, while giving a smaller model a slice of work itself requires the big model to reason about the task distributi…
Dang, not even Spotify care enough to not write AI slop articles. We’re fucked.
Next sentence was also an AI juxtaposition. Done.
Dang, not even Spotify care enough to not write AI slop articles. We’re fucked.
Isn't this a somewhat standard multi-model setup? there's nothing ground breaking here, just delegate claude to plan -> smaller model for implementation.
Very standard in all coding harnesses/models I've worked with, with the bonus that everything listed in the "What doesn't work in Portal by Spotify" section still works. I've been watching Opus spin off work to Fable and Sonnet as appropriate all day.