▶ Videos →

📰 Dev.to · Eyoel Nebiyu

4 articles · Updated every 3 hours · View all reads

All Articles 129,303 Blog Posts 134,099 Tech Tutorials 33,413 Research Papers 25,155 News 18,290 ⚡ AI Lessons

# Why "drift_score = 0.0" Is Not Yet Evidence of Semantic Stability — and What Your n=251 vs cap=200 Mismatch Actually Costs by: Eyoel Nebiyu

Dev.to · Eyoel Nebiyu 📐 ML Fundamentals ⚡ AI Lesson 2mo ago

# Why "drift_score = 0.0" Is Not Yet Evidence of Semantic Stability — and What Your n=251 vs cap=200 Mismatch Actually Costs by: Eyoel Nebiyu

Repo under interrogation: Heban-7/Data-Contract-Enforcer Files in scope: report_final_pdf_ready.md,...

# What LoRA Actually Adapts and Why Higher Rank Doesn't Always Buy What It Looks Like It Should Explainer by: Eyoel Nebiyu

Dev.to · Eyoel Nebiyu 🧠 Large Language Models ⚡ AI Lesson 2mo ago

# What LoRA Actually Adapts and Why Higher Rank Doesn't Always Buy What It Looks Like It Should Explainer by: Eyoel Nebiyu

The question, anchored You noticed two things in your Week 10 Conversion Engine fine-tunes...

# Scaffolding-Driven vs Model-Driven Planning: Where Agent Systems Actually Break *By Eyoel Nebiyu*

Dev.to · Eyoel Nebiyu 🤖 AI Agents & Automation ⚡ AI Lesson 2mo ago

# Scaffolding-Driven vs Model-Driven Planning: Where Agent Systems Actually Break *By Eyoel Nebiyu*

Most teams building agent systems focus on improving prompts or improving workflow logic. In...

# Why `$0.0029` and `$0.0047` Can Both Be Right: Prefix Caching for API-Served LLM Judges *By Eyoel Nebiyu*

Dev.to · Eyoel Nebiyu 🧠 Large Language Models ⚡ AI Lesson 2mo ago

# Why `$0.0029` and `$0.0047` Can Both Be Right: Prefix Caching for API-Served LLM Judges *By Eyoel Nebiyu*

The question I was asked Abdulaziz asked a practical evaluation question: in the same...