---
title: "I deleted 70% of my AI instructions and Claude got smarter"
description: "5 source-backed AI claims from I deleted 70% of my AI instructions and Claude got smarter, with key statistics, context, and the original AI Adopters Club…"
url: "https://kbanc.com/claims-library/deleted-70-percent-ai-instructions-claude-got-smarter"
source: "https://aiadopters.club/p/i-deleted-70-of-my-ai-instructions"
date: "2026-08-03"
topics: ["strategy", "implementation", "tools"]
generated: "2026-09-19"
---

# I deleted 70% of my AI instructions and Claude got smarter

By Kamil Banc | August 3, 2026

## Claims

1. **Anthropic's 80% Deletion Test**: Anthropic deleted more than 80% of its coding tool's instructions without any drop in test scores.
2. **Author's 70% Instruction Cut**: The author deleted 70 percent of personal Claude instructions and reported noticeably smarter, more useful output.
3. **Conflicting Rules Confuse Models**: Conflicting rules, like documenting appropriately versus never adding comments, force the model to arbitrarily choose.
4. **Three Instruction Storage Layers**: Claude instructions live across three separate locations: general settings, project files, and skill definitions.
5. **Skills Load On Demand**: Skills only load into context when actively called, so idle skills cost nothing extra.

## Evidence

### Quote
> "Would a brilliant new colleague, who already knows my field, still need to be told this?" - Kamil Banc

### Key Statistics
- **80%+**: Share of instructions Anthropic removed from its Claude Code tool, with test scores remaining unchanged.
- **70%**: Portion of personal AI instructions the author cut, which reportedly made Claude's responses sharper.
- **~66%**: Estimated share of instructions cleared out when applying the 'brilliant new colleague' filter to a typical prompt set.
- **10 seconds**: Suggested time to spend per instruction line when deciding whether it still needs to be kept.

## Context
The methodology centers on a single diagnostic question—whether a knowledgeable new hire would still need a given instruction—applied across three distinct layers where Claude stores context: general settings, project-level files, and skills. Practitioners are advised to delete instructions wholesale rather than trim them, then reintroduce only what proves necessary through a week of normal use, adding items back solely after a problem repeats rather than after a single incident. This mirrors Anthropic's own internal practice of stripping instructions to zero and rebuilding line by line to test actual utility. The approach distinguishes between corrective instructions—meant to patch mistakes models no longer make—and preference instructions like tone, audience, or style, which remain essential and should not be cut. The caveat that newer model versions show longer system prompts suggests the deletion trend may not be as uniformly aggressive as headline figures imply.

## Source
- Original: [I deleted 70% of my AI instructions and Claude got smarter](https://aiadopters.club/p/i-deleted-70-of-my-ai-instructions)
- Cite: kbanc.com/claims-library/deleted-70-percent-ai-instructions-claude-got-smarter