DEV Community

Mark k profile picture

Mark k

I compare AI models, tools, and architectures to help teams choose based on use case and tradeoffs.

Location United States Joined Joined on 

Education

MBA in Technology Management

Work

AI Strategy Consultant and Model Selection Advisor

How We Cut Inference Latency by 60% Migrating to Next-Gen Reasoning Models (Case Study)

How We Cut Inference Latency by 60% Migrating to Next-Gen Reasoning Models (Case Study)

Comments
5 min read

Want to connect with Mark k?

Create an account to connect with Mark k. You can also sign in below to proceed if you already have an account.

Already have an account? Sign in
How to Build a Specialized AI Stack for Developer Productivity (Step-by-Step Guide)

How to Build a Specialized AI Stack for Developer Productivity (Step-by-Step Guide)

Comments
5 min read
Deep Research vs. AI Search: Architecture Decisions for the Information Overload Age

Deep Research vs. AI Search: Architecture Decisions for the Information Overload Age

Comments
6 min read
Why We Banned Single-Model Workflows: A 30-Day Experiment with DALL·E 3, Ideogram, and Imagen

Why We Banned Single-Model Workflows: A 30-Day Experiment with DALL·E 3, Ideogram, and Imagen

Comments
7 min read
When Models Stop Being Black Boxes: A Hands-on Dive into Modern AI

When Models Stop Being Black Boxes: A Hands-on Dive into Modern AI

Comments
6 min read
When an AI Recommends Deprecated Pandas APIs — a postmortem

When an AI Recommends Deprecated Pandas APIs — a postmortem

Comments
3 min read
When a refactor tool renames half the project: inconsistent variable naming across files

When a refactor tool renames half the project: inconsistent variable naming across files

Comments
3 min read
When code suggestions use deprecated Pandas APIs

When code suggestions use deprecated Pandas APIs

Comments
3 min read
When code suggestions push deprecated Pandas APIs: a postmortem

When code suggestions push deprecated Pandas APIs: a postmortem

Comments
3 min read
When Generated Tests Pass but Miss the Bug: A Case of False Confidence from AI Test Generation

When Generated Tests Pass but Miss the Bug: A Case of False Confidence from AI Test Generation

Comments
3 min read
When Generated Tests Pass But Miss the Bug: Lessons from AI-Written Test Suites

When Generated Tests Pass But Miss the Bug: Lessons from AI-Written Test Suites

Comments
3 min read
When an LLM Renames Things: Inconsistent Variable Naming During Multi-file Refactors

When an LLM Renames Things: Inconsistent Variable Naming During Multi-file Refactors

Comments
3 min read
When AI Refactors Break Naming: a case of inconsistent variable renames across files

When AI Refactors Break Naming: a case of inconsistent variable renames across files

Comments
3 min read
When Stack Traces Lie: How LLMs Misread Exceptions and Lead Debugging Astray

When Stack Traces Lie: How LLMs Misread Exceptions and Lead Debugging Astray

Comments
3 min read
Context drift and hidden errors in long AI-assisted coding sessions

Context drift and hidden errors in long AI-assisted coding sessions

Comments
3 min read
When long conversations drift: hidden errors in AI-assisted coding

When long conversations drift: hidden errors in AI-assisted coding

Comments
3 min read
loading...