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

181–190 of 196 posts

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

#181

Post by lamine-yaml »

zxspectrum1982 wrote: post #167
fy20 wrote: post #162

Earlier quoted context omitted.

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…

IME Composer 2.5 is too dumb for any serious coding. Grok 4.6 is twice as expensive (but still much cheaper than Claude Opus) and it does a much much better job.

Composer has improved in last few months. I relied heavily on it last month as ran out tokens and composer free credits were available for use.

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

#182

Post by asimovDev »

ssalka wrote: post #118
Jtarii wrote: post #104

Earlier quoted context omitted.

The spotify desktop app is one of the worst pieces of software by a major company I have ever used.

Do you pay for Spotify? If so, I hope you never have to experience the dumpster fire that is their free version. Half the time you select a song to play it'll just start playing related tracks.

their free version wasn't particularly horrendous the last time I tried. I clicked play on a playlist and got an ad every maybe 3-5 songs and the ads were usually around 30 seconds. although my main issue is that they only had the same 2-3 ads to play for me throughout the weeks I used the free version so that got annoying.

as someone on the internet once said, it's good that no-one at Spotify realised that people would buy the subscription much faster if it was a crying baby soundbite playing every time instead of an advertisement

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

#184

Post by larodi »

ssivark wrote: post #109
larodi wrote: post #102

Earlier 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.

also:

- listing modes - this gate, other gate - canonical stuff etc.

would've been nice if Claude produces such output now and then. with 4 agents doing my stuff on a daily basis, I feel like vomiting at some point, not mere nausea, but disgust. damn Codex seems to fare better at this imho.

curiously I've tried many times to instruct it to not produce this nonsense, but _deus ex machina_ always finds a way around it. wonder if these "instructions" are actually treated as restrictions, rather than... mere obstacles. like - you can try to plumb a river, it always finds its way around plumbing.

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

#185

Post by larodi »

andrew_mason1 wrote: post #164
schainks wrote: post #61

It takes true corporate dedication to publish technical thought leadership on a page that actively fights your ability to read it.

I don't get why all your replies are on the AI language. Yeah the AI-isms suck and are obvious but is no one else bothered by how this page scrolls?

well author could've tried to read it himself, and figuring it reads as slop to ... like rewrite it by hand? how hard is this, I mean - I understand reasoning took place inside a box (like it does so when you query DuckDB or Excel spreadsheets and we're okay with it), but I don't understand why anyone would think it is okay to toss glossed random shit at everyone else, and pretend it is a high-profile high-stakes writing. this whole text is barely comprehensible. not that I didn't try...

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

#186

Post by jrm4 »

solenoid0937 wrote: post #131
jrm4 wrote: post #77

Earlier quoted context omitted.

Am I missing something? Unless you have infinity money, would it not be very stupid to pay for "precise greps?"

It's a few hundred tokens. If you are worried about a few hundred tokens you are in trouble, forget about "infinite money."

Oh, so "programmers" really ARE losing the plot.

You kids don't get it, it's not about the tokens, it's about the principle of the thing. No self-respecting real programmer would accept the loss of even a few tokens over programmatic efficiency and cleverness.

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

#187

Post by bspammer »

steveBK123 wrote: post #110
Jtarii wrote: post #104

Earlier quoted context omitted.

The spotify desktop app is one of the worst pieces of software by a major company I have ever used.

I timed how long it took to open Spotify and play a song on a $2500 Mac on low latency gigabit fiber internet. 15 seconds. Incredible stuff.

The app has gotten consistently slower, buggier, with worse UX for over a decade. In all that time, I can’t recall a single new feature I’ve actually found useful.

The app was done in 2011. They could make a massive improvement across the board with a single git reset --hard command.

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

#188

Post by lxgr »

astrange wrote: post #138
lxgr wrote: post #119

Earlier quoted context omitted.

Unlike an actual Bloom filter (which does not return false negatives), the cheaper model is still trusted to correctly recognize synonyms, equivalent functional constructions etc. One is strictly a performance optimization, the other is a speed/quality tradeoff. It might well be a very good one, but it’s a tradeoff nevertheless. The framing is misleading.

That's a Claude.

What is?

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

#189

Post by vintermann »

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.

As I understand this is something similar to "anchors", tools to let agents avoid reading whole files.

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

#190

Post by vintermann »

johnnythujone wrote: post #112
jampa wrote: post #18

Earlier quoted context omitted.

> I've never had an issue with Codex or Claude reading massive files Reading files isn't a problem they want to solve. The idea seems to be using a cheaper model to "scout" for the intended code, instead of an expensive one that reads all the things (and spends more tokens / thinks about them). I think this might be useful because Opus 5 especially tends to over-read. So this looks like an "LLM Bloom filter", telling…

I have a stage-gated workflow that prioritizes “premium” token efficiency (Fable.) and getting the most out of my subscription services. (Which boils down to Fable running carefully prompted deepseek-flash agent teams that defer back to the managing agent for any design decisions in most work.) As part of that workflow the manager uses cheap reconnaissance agents to burn their tokens in order to build relevant repo c…

It sounds like you're halfway to gas town already... Not saying that is definitively bad, but I have avoided this myself since I don't want to get bogged down in trying to figure out the optimal multiagent setup.
Post reply on HN