Is not something already addressed by mcps like codegraph? https://github.com/CodeGraphContext/CodeGraphContext (without the need of extra third party api/costs)
Portal by Spotify cut my Claude Code token usage by 90%
51–60 of 182 posts
Re: Portal by Spotify cut my Claude Code token usage by 90%
#52So 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…
> and it’s often just as good as Sonnet. I think optimizing token usage is a good exercise. We often assume a model will be terrible, when it really isn’t.
“Often” doesn’t sound great. If the smaller model fails then I just wasted a lot of time and tokens.
Re: Portal by Spotify cut my Claude Code token usage by 90%
#53Dang, not even Spotify care enough to not write AI slop articles. We’re fucked.
I noticed
> The modes are the load-bearing piece:
Why do people write like LLMs? Maybe they delegate all the work to a LLM and don't have the time or the will to edit the copy. How about telling another LLMs to replace at least the most common LLM patterns with something human looking?
Re: Portal by Spotify cut my Claude Code token usage by 90%
#54There are a bunch of approaches that do this kind of thing to reduce token usage ("semble" came to mind, technically different but functionally similar) but their performance is usually mixed because the models haven't been RL tuned to use them as they have the default tool suite. Combine that with the incentive by Anthropic et al. to make you actually burn through as many tokens as possible and I don't see these kind of things becoming mainstream yet. Maybe once we reach a point where consumers actually care about cost (because LLMs have become commoditized) these cost-reduction approaches become relevant enough to actually finetune the model with them.
Re: Portal by Spotify cut my Claude Code token usage by 90%
#55STOP 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.
I swear. Put me off so bad I didn't even bother reading the rest of the article. It's even more infuriating that this is by a company this big
Re: Portal by Spotify cut my Claude Code token usage by 90%
#56If you want an expensive model to reason on your files, you need to give them your files.
If you think a cheap model is smart enough to filter information to give to your expensive model, you can save some money. If you think your cheap model is smart enough to format your expensive output, you can save some money.
In practice, this didn't work well until Qwen 3.8.
Qwen 3.6 and (abliterated) Gemma 4 were almost there but still making mistakes.
Re: Portal by Spotify cut my Claude Code token usage by 90%
#57I wish websites would stop messing with the scrolling behavior.
Re: Portal by Spotify cut my Claude Code token usage by 90%
#58codegraph + context mode are all I need.
Re: Portal by Spotify cut my Claude Code token usage by 90%
#59So 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…
My code being correct 99% of the and costing 5x more tokens is vastly preferable to my code only being correct 90% of the time and using fewer tokens.
Re: Portal by Spotify cut my Claude Code token usage by 90%
#60Isn't this already done in harnesses? I mean I see Terra or Sol uing Luna all the time for tasks when using copilot.