---
title: "Alex Alexapolsky (@metawake) | Hashnode"
description: "Python/LLM dev. Read the latest articles by Alex Alexapolsky on Hashnode."
url: "https://hashnode.com/@metawake"
---

@metawake

# Alex Alexapolsky

@metawake · Montenegro · Joined April 2025

Python/LLM dev

### [Detecting Policy Puppetry in LLM Prompts: A Simple, Transparent Approach](https://metawake.hashnode.dev/detecting-policy-puppetry-in-llm-prompts-a-simple-transparent-approach?utm_source=hashnode&utm_medium=feed)

There’s a lot of excitement these days about large language models (LLMs) and the new opportunities—and risks—they bring. As someone who’s spent a fair bit of time in the NLP and LLM trenches, I’ve seen firsthand how creative people can get when tryi...

3 min read · [metawake.hashnode.dev](https://metawake.hashnode.dev/detecting-policy-puppetry-in-llm-prompts-a-simple-transparent-approach?utm_source=hashnode&utm_medium=feed)

[Apr 27, 2025](https://hashnode.com/posts/detecting-policy-puppetry-in-llm-prompts-a-simple-transparent-approach/680e903110073cdd12f847ce)

### [Flexible Entity Extraction for NLP Pipelines: Introducing nergrep](https://metawake.hashnode.dev/flexible-entity-extraction-for-nlp-pipelines-introducing-nergrep?utm_source=hashnode&utm_medium=feed)

As an AI/NLP/ML platform engineer, I often need to prototype and iterate on text analytics pipelines. Entity extraction is a frequent, foundational step—whether I'm building quick R&D experiments or shaping components for production. I wanted a tool ...

4 min read · [metawake.hashnode.dev](https://metawake.hashnode.dev/flexible-entity-extraction-for-nlp-pipelines-introducing-nergrep?utm_source=hashnode&utm_medium=feed)

[Apr 26, 2025](https://hashnode.com/posts/flexible-entity-extraction-for-nlp-pipelines-introducing-nergrep/680ca71f4b73a5805d17392c)

### [Best Practices for Prompt Modifier Shaping: Navigating Model Behavior and Responsiveness](https://metawake.hashnode.dev/best-practices-for-prompt-modifier-shaping-navigating-model-behavior-and-responsiveness?utm_source=hashnode&utm_medium=feed)

Some models resist the formatting, length, or tone modifiers we give them. But what if that's not a bug, but a feature we can work around? Context and Purpose In recent experiments, we explored how prompt modifiers influence the length, style, and st...

3 min read · [metawake.hashnode.dev](https://metawake.hashnode.dev/best-practices-for-prompt-modifier-shaping-navigating-model-behavior-and-responsiveness?utm_source=hashnode&utm_medium=feed)

[Apr 21, 2025](https://hashnode.com/posts/best-practices-for-prompt-modifier-shaping-navigating-model-behavior-and-responsiveness/6806cb9e403605ff50929e8f)

### [Prompt Shaping: Measuring the Impact of Prompt Modifiers on Output Size and Format](https://metawake.hashnode.dev/prompt-shaping-measuring-the-impact-of-prompt-modifiers-on-output-size-and-format?utm_source=hashnode&utm_medium=feed)

What if you could guide large language models (LLMs) to output shorter, clearer, or more structured responses just by adjusting the prompt? This experiment set out to answer a simple yet valuable question: Can we shrink or reshape LLM output just by...

4 min read · [metawake.hashnode.dev](https://metawake.hashnode.dev/prompt-shaping-measuring-the-impact-of-prompt-modifiers-on-output-size-and-format?utm_source=hashnode&utm_medium=feed)

[Apr 21, 2025](https://hashnode.com/posts/prompt-shaping-measuring-the-impact-of-prompt-modifiers-on-output-size-and-format/6806c1fdcb20e95f737f1d9f)

### [Semantic Prompt Compression: Reducing LLM Costs While Preserving Meaning](https://metawake.hashnode.dev/semantic-prompt-compression-reducing-llm-costs-while-preserving-meaning?utm_source=hashnode&utm_medium=feed)

View the open-source project on GitHub The Challenge: Every Token Costs In the world of Large Language Models (LLMs), every token comes with a price tag. For organizations running thousands of prompts daily, these costs add up quickly. But what if w...

3 min read · [metawake.hashnode.dev](https://metawake.hashnode.dev/semantic-prompt-compression-reducing-llm-costs-while-preserving-meaning?utm_source=hashnode&utm_medium=feed)

[Apr 14, 2025](https://hashnode.com/posts/semantic-prompt-compression-reducing-llm-costs-while-preserving-meaning/67fd96a9831f9366b9c9355f)
