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

There 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.

I wish websites would stop messing with the scrolling behavior.

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.

It cuts token usage because they are using a different service with a different token budget for the reader/code writer tasks.

You can also just delegate this to subagents with Claude Code (though you have a more limited choice of models unless you swap the cheaper models via OpenRouter).

I'm OK using a dumb model as a smart grep, but the whole point of using the frontier models is using their intelligence for the hard stuff like coding.

It doesn't work well in practice.

Try it yourself, use a big model like Opus or Sol to implement everything by first making a plan using plan mode.

Then try distributing the task to a cheaper models like Luna Max or Gemini Flash 3.8.

During planning, the big model already reads the relevant files in context, while giving a smaller model a slice of work itself requires the big model to reason about the task distribution, review, etc.

So do you really save on tokens?

Side note: PLEASE DONT hijack scroll. Its just a bad bad thing to do. Please dont.

Oh dear, why does this website override scrolling behavior?

Isn't this already done in harnesses? I mean I see Terra or Sol uing Luna all the time for tasks when using copilot.

>The benchmarks

>Tested against a Java monorepo across four scenarios, measuring tokens Claude would consume reading files directly vs. consuming the bulk-reader's summary or writing code via the code-writer. Mean bulk-read savings were around a whopping 90%.

>The code-write scenario is harder to measure in tokens because without shunt, Claude both reads the reference files and generates the output as expensive output tokens. With shunt, the code goes straight to disk, Claude never sees it.

So nothing about accuracy or actual performance? At least run against DeepSWE bench or something.

Is not something already addressed by mcps like codegraph? https://github.com/CodeGraphContext/CodeGraphContext (without the need of extra third party api/costs)

Isn't this a somewhat standard multi-model setup? there's nothing ground breaking here, just delegate claude to plan -> smaller model for implementation.

Here is another technique to save tokens: allow the model to read a skeleton of the source code before reading the code, to give it an index into the code so it can read targeted chunks.

There is a tool that uses ripgrep and treesitter that does this [1], adapted from the maki coding agent.

[1]: https://github.com/ninjaxtools/treesitter-index

I sometimes get jumpscaped at the thought of older or less proven models used in enterprise settings. I understand the devex ergonomics argument; I'm not a fan of profiles concepts typically if trodding into delegation.

codegraph + context mode are all I need.

I cut my Claude Code token usage by 100% by writing the code myself.

If 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.

Not only does this study not control for quality of output, it doesn't even show a cost reduction. Its a very low signal article.

This is just offshoring but for models

Dang, not even Spotify care enough to not write AI slop articles.

We’re fucked.

STOP 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.

[flagged]

[flagged]

[flagged]

[flagged]

[dead]

[flagged]