DEV Community

# llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Vision Models for OCR: When They Beat Tesseract and When They Don't
gabrielanhaia profile

Vision Models for OCR: When They Beat Tesseract and When They Don't

#ai #llm #ocr #python
Comments
7 min read
How Should We Evaluate AI Coding Tools in Real Engineering Environments
hellofadude profile

How Should We Evaluate AI Coding Tools in Real Engineering Environments

#ai #llm #programming #softwareengineering
Comments
4 min read
The LLM-shaped hole in your XGBoost pipeline
andreasbergstrom profile

The LLM-shaped hole in your XGBoost pipeline

#llm #machinelearning
Comments
1 min read
How I cut my multi-turn LLM API costs by 90% (O(N ) O(N))
rudekwydra profile

How I cut my multi-turn LLM API costs by 90% (O(N ) O(N))

#ai #api #llm #performance
Comments
2 min read
Six Principles in Practice: How an Agentic E2E Found 11 Production Bugs in 8 Runs
webramos profile

Six Principles in Practice: How an Agentic E2E Found 11 Production Bugs in 8 Runs

#llm #agentskills #playwright #e2e
Comments
13 min read
Chunking in RAG: why your splitter matters more than your embedding model
saurabh_naik_b213f3bbeafe profile

Chunking in RAG: why your splitter matters more than your embedding model

#rag #ai #llm #python
2
Comments
5 min read
What MCP Really Is — A Demo You Can Run on Your Laptop in 5 Minutes
oliver_b5cca1c0d63b632b8b profile
Oliver

What MCP Really Is — A Demo You Can Run on Your Laptop in 5 Minutes

#mcp #ai #llm #data
Comments
10 min read
Why your quantized LLM loses its MTP heads and how to keep them
alanwest profile

Why your quantized LLM loses its MTP heads and how to keep them

#machinelearning #llm #python #quantization
1
Comments
5 min read
About Sharing Local Inference: A Marketplace for Renting Idle GPUs with an OpenAI-Compatible Backend
werlang profile

About Sharing Local Inference: A Marketplace for Renting Idle GPUs with an OpenAI-Compatible Backend

#ai #llm #openai #api
Comments
8 min read
Cut Your AI Agent Token Costs by 75% With One Skill Plugin
hardcore-engineer profile

Cut Your AI Agent Token Costs by 75% With One Skill Plugin

#ai #llm #productivity #devtool
Comments
2 min read
Why most LLM API usage is quietly inefficient
joshua_chukwu_ccb92f05a94 profile

Why most LLM API usage is quietly inefficient

#ai #webdev #programming #llm
Comments
4 min read
Qwen sky proof: compressed memory made a tiny model behave better — with the receipts
aman_sachan_126d19c4a2773 profile

Qwen sky proof: compressed memory made a tiny model behave better — with the receipts

#ai #llm #python #benchmarking
Comments
1 min read
The 8B Model That Punches at 32B Weight
o96a profile

The 8B Model That Punches at 32B Weight

#ai #machinelearning #llm
Comments
2 min read
Hermes Agent CLI cheat sheet — commands, flags, and slash shortcuts
rosgluk profile
Rost

Hermes Agent CLI cheat sheet — commands, flags, and slash shortcuts

#cheatsheet #hermes #selfhosting #llm
1
Comments
8 min read
The "Chat" API is a Token Tax: Why we must return to Stateless Completions
ai_oberland profile

The "Chat" API is a Token Tax: Why we must return to Stateless Completions

#ai #api #architecture #llm
Comments
2 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.