111–120 of 133 posts
What great productivity gains are Spotify achieving in making their product worse?
The spotify desktop app is one of the worst pieces of software by a major company I have ever used.
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.
> 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…
There’s an added benefit that the manager’s focus on strategy and task decomposition before actually handling the user’s prompted task directly seems to be a very good way to interact with Claude’s Fable safeguards, and I haven’t had any refusals doing this.
And while I haven’t ran any numbers, I can get orders of magnitude more out of my claude subscription doing this, especially with deepseek-v4-flash being as good as it is for as cheap as it is.
Earlier quoted context omitted.
> Try it yourself, use a big model like Opus or Sol to implement everything by first making a plan using plan mode. When I do this, I can have it use cheap subagents with models like Luna to read the relevant files.
Do you have the cheap models summarize the files? How do they get the relevant information to the bigger models?
This should have been the entirety of TFA.
What great productivity gains are Spotify achieving in making their product worse?
The spotify desktop app is one of the worst pieces of software by a major company I have ever used.
Earlier quoted context omitted.
> "LLM Bloom filter" very good way to put it.
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.
imagine working at these shitty companies with their shitty wrapper tooling.
Earlier quoted context omitted.
The spotify desktop app is one of the worst pieces of software by a major company I have ever used.
My favorite part about the desktop app is the 1 second delay between when I click a playlist and when it actually loads.
What great productivity gains are Spotify achieving in making their product worse?
The spotify desktop app is one of the worst pieces of software by a major company I have ever used.
The Bloom filter framing is right. What made it work for me: the cheap model is only allowed to point, never to decide. Once it stopped judging anything and just returned file paths and line ranges, the quality complaints disappeared. The expensive model still does all the reading that matters, just on 10% of the bytes.
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.