Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Portal by Spotify cut my Claude Code token usage by 90%

engineering.atspotify.com

Post reply on HN
Print view View original

81–90 of 168 posts

Re: Portal by Spotify cut my Claude Code token usage by 90%

#82

Post by dotancohen »

pmdr wrote: post #57

I wish websites would stop messing with the scrolling behavior.

After seeing a few comments about scrolling on that page, curiosity got the better of me and I dared open TFA.

I found no problem scrolling. Either Firefox on Android doesn't support whatever trickery they are doing, or they reverted it.

Re: Portal by Spotify cut my Claude Code token usage by 90%

#85

Post by bluGill »

landr0id wrote: post #78
pmdr wrote: post #57

I wish websites would stop messing with the scrolling behavior.

I used to date a girl who was a designer and had to plead with her that breaking behaviors I'm used to is not a positive UX. "But it adds motion" was the classic reply.

The question is, are we doing this page for the sake of art or are we doing this for the sake of spreading and sharing information? These are two different domains with different requirements as to how the page works.

There is nothing wrong with art. It is a great thing, I hope to see more art in the world. However, if the goal is sharing information, which is supposedly the goal of a fairly large number of websites, art needs to be secondary to sharing that information. And then those things that add motion, whatever: you're adding art and harming the real purpose.

Re: Portal by Spotify cut my Claude Code token usage by 90%

#86

Post by andai »

So it's giving summaries to the main agent instead of source code? Is that it?

> If Claude needs to make edits based on the analysis, it still has to read the specific section directly.

Yeah iirc the sysprompt tells it that it must always (re-)read a file before editing it. I noticed this because I customized Claude Code to just read all source at startup (if the project was only a few thousand lines of code). And it would still read the stuff it had already read! Because the system prompt explicitly told it to...

Re: Portal by Spotify cut my Claude Code token usage by 90%

#87

Post by bluGill »

shevy-java wrote: post #72

> By 2028, AI coding costs are expected to blow past the average developer's salary. A quarter of engineering leaders already burn $200–$500 per developer per month on tokens. Wasn't the AI promise to save costs? So it was a lie.

We can't know if it's a lie or not until we know what the productivity difference is.

Measuring productivity is, of course, a hard problem and I'm going to leave this completely out of this comment.

Re: Portal by Spotify cut my Claude Code token usage by 90%

#88

Post by CuriouslyC »

shubhamjain wrote: post #23
solenoid0937 wrote: post #2

So 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.

> So this is just delegating certain work to dumber models? I certainly wouldn't use Gemini 2.5 Flash (!!?) for code writing as suggested. Why not, though? I started using OpenCode + GitHub Copilot, but I burned through my Claude Sonnet quota in just three days. I switched to GPT-5.4-mini, which uses far fewer tokens, and it’s often just as good as Sonnet. I think optimizing token usage is a good exercise. We often a…

This is true, but with the newer generation of models you don't want to do this yourself, they're really good at orchestrating and triage. Run Fable or Astra on low/medium, and tell them to come up with a plan then direct subagents using a weaker model (I like GPT 5.6 terra medium) to implement and verify, and review their work.

Re: Portal by Spotify cut my Claude Code token usage by 90%

#89

Post by ramraj07 »

Artimus wrote: post #46
ramraj07 wrote: post #45

Earlier quoted context omitted.

Pretty sure claude code already delegates reading a large codebase to haiku subagents.

As of July, the explore agent inherits the parent model, capped at opus. So fable and opus use opus to explore. Sonnet uses sonnet. I replaced my built in explore agent with one hardcoded to sonnet low effort. https://github.com/anthropics/claude-code/issues/72940

Im now fascinated by how exactly Bcherny generated that message using claude. Like is the entire issue resolution automated, or still guided in someway?
Post reply on HN