Portal by Spotify cut my Claude Code token usage by 90%
161–170 of 180 posts
Re: Portal by Spotify cut my Claude Code token usage by 90%
#162So this is just delegating certain work to dumber models? I certainly wouldn't use Gemini 2.5 Flash (!!?) for code writing as suggested. I've never had an issue with Codex or Claude reading massive files, they're really good at precise greps.
The app would start using it for exploration tasks, and then as it improved it became the default for writing code and tests too. You can change it of course, but I find it does a pretty decent job if you have a large model directing it.
The parent model of course checks the work, but most of the time the handoff is good enough that no edits are needed.
It's also pretty fast and cheap, firing off a bunch of sub-agents to explore different parts of the codebase is a regular occurrence for the way I work.
Re: Portal by Spotify cut my Claude Code token usage by 90%
#163Re: Portal by Spotify cut my Claude Code token usage by 90%
#164It takes true corporate dedication to publish technical thought leadership on a page that actively fights your ability to read it.
Re: Portal by Spotify cut my Claude Code token usage by 90%
#165Earlier quoted context omitted.
It's not a great analogy, since Bloom filters are guaranteed to not have any false negatives, only false positives. That property would be very useful here, but I don't see how it would be achievable using LLMs.
still a great analogy even if not techincally equivalent
Re: Portal by Spotify cut my Claude Code token usage by 90%
#166Re: Portal by Spotify cut my Claude Code token usage by 90%
#167So this is just delegating certain work to dumber models? I certainly wouldn't use Gemini 2.5 Flash (!!?) for code writing as suggested. I've never had an issue with Codex or Claude reading massive files, they're really good at precise greps.
This is basically exaclty what Cursor started doing when Composer was first released. The app would start using it for exploration tasks, and then as it improved it became the default for writing code and tests too. You can change it of course, but I find it does a pretty decent job if you have a large model directing it. The parent model of course checks the work, but most of the time the handoff is good enough that…
Re: Portal by Spotify cut my Claude Code token usage by 90%
#168Earlier quoted context omitted.
"The seat license isn't what hurts, it's the tokens." not X, but Y... so this is very likely Opus 5 text, given timing and how it reads. has all the marks of it, one being very weird wording which makes it so hard to read the text.
...the remaining 10% of their Claude usage ;-) > modes are the load-bearing piece: Okay, this write-up is filled with Claudisms.
Re: Portal by Spotify cut my Claude Code token usage by 90%
#169Earlier quoted context omitted.
Try it on a flaky connection. Every menu (maybe any action of any kind?) makes a roundtrip to the server before displaying, with a very slow timeout. It's crazy how bad it is.
I think they've gotten worse about this as an organization over the last few years(?). Earlier this year an update to their mobile app introduced loading time, and resulting slowness, for opening menus that used to be ~instant. To me that smacks of once having known not to do that, but that knowledge having been lost (or priorities having shifted). More specifically, I'm talking about tapping the '...' on a track for…
Though I agree it should be.
Re: Portal by Spotify cut my Claude Code token usage by 90%
#170(fully vibe coded)