DEV Community

Shouvik Palit
Shouvik Palit

Posted on

I Reduced AI Response Tokens by 44% Without Changing the Model

Teaching LLMs to Say Less Without Knowing Less

Every few weeks, a new model promises to be smarter, faster, or cheaper.

I started wondering if we were optimizing the wrong thing.

What if the same model could produce the same explanation using 40% fewer tokens?

That question became LELP-S+ (Less English. Less Prose.), a new mode I recently added to Sir Shortoken.


The Observation

Most technical explanations contain two different things:

βœ… Information

❌ Extra English

A typical response contains:

  • Repeated context
  • Transition sentences
  • Narrative glue
  • Extra examples
  • Elaborate phrasing

None of these are wrong.

But many aren't necessary.


The Idea

LELP-S+ keeps complete grammatical sentences while removing as much English as possible without removing information.

The rules are intentionally simple:

  • Every sentence introduces a new fact.
  • Remove repetition.
  • Remove narrative glue.
  • Split long sentences when it improves density.
  • Use simple symbols like β†’ where they naturally replace repeated words.
  • Never remove requested technical concepts.

The objective isn't shorter writing.

It's more information per token.


The Experiment

I evaluated LELP-S+ across four frontier models using the same five technical topics:

  • TCP congestion control
  • Virtual memory
  • B-trees
  • Raft consensus
  • Redis persistence

For each response, I compared token count against that model's own normal prose.

Average Token Savings

Model Average Savings
πŸ₯‡ GPT 44%
πŸ₯ˆ Gemini 36%
πŸ₯‰ Claude 32%
4️⃣ DeepSeek 30%

The Interesting Part

It wasn't accuracy.

Across 20 generated explanations, every model remained factually correct.

The real differentiator was compression discipline.

GPT consistently removed the most prose while preserving the technical explanation.

DeepSeek generally compressed well too, but occasionally expanded beyond the requested scope, adding extra sections that increased token count.

In other words, the biggest difference wasn't knowledge.

It was how aggressively each model was willing to remove unnecessary English.


Symbols Matter Too

One thing I didn't expect was how useful symbols became.

Instead of repeatedly writing phrases like:

  • leads to
  • results in
  • causes

a simple:

β†’
Enter fullscreen mode Exit fullscreen mode

often communicates exactly the same relationship.

One arrow doesn't save much.

Hundreds of repeated connectors across many technical explanations start adding up.

The goal isn't to replace English.

It's to use symbols where they're already universally understood.


Where LELP-S+ Fits

Sir Shortoken now supports six response modes:

  • Quick
  • Balanced
  • Deep
  • Bullets
  • Aggressive Bullets
  • LELP-S+

Think of them like this:

Mode Readability Compression
Deep ⭐⭐⭐⭐⭐ ⭐
Balanced ⭐⭐⭐⭐ ⭐⭐
LELP-S+ ⭐⭐⭐⭐⭐ ⭐⭐⭐
Bullets ⭐⭐⭐ ⭐⭐⭐⭐
Aggressive Bullets ⭐ ⭐⭐⭐⭐⭐

LELP-S+ sits between Bullets and normal prose.

It still reads like English.

It just uses a lot less of it.


Why This Matters

Most discussion around token efficiency focuses on:

  • Smaller models
  • Better prompts
  • Context compression
  • Caching

LELP-S+ explores a different question.

Can we compress the language itself instead of the model?

The model already knows the answer.

The experiment is whether it can express the same knowledge using substantially fewer words.


Try It

LELP-S+ is now part of Sir Shortoken, which is open source.

GitHub: https://github.com/shouvik12/sir-shortoken

I'm curious whether anyone else has experimented with compressing output language instead of just optimizing prompts or switching models.

It feels like there's still a surprising amount of efficiency hiding in how we ask LLMs to write.

Top comments (0)