Skip to content

DEV Community

# llm

👋 Sign in for the ability to sort posts by relevant, latest, or top.

Ravi Patel

Jun 8

The hidden cost of streaming LLMs: caches you can't use, bills you don't expect, and complexity you don't need

#llm #streaming #costoptimization #ux

11 min read

Jun 4

Unlocking the Power of RAG Systems with LangChain and Vector Databases

#ai #llm #python

3 min read

Jun 3

Switching our LLM-as-judge from 5-class to binary in CI: the patterns we kept

#ai #llm #ci #machinelearning

3 min read

soy

Jun 3

AirLLM Shrinks 70B LLMs to 4GB VRAM; DPO & Supermemory Boost Open Models

#ai #llm #selfhosted

3 min read

Jun 8

From Chatbots to Personal AI Agents: The Infrastructure Developers Actually Need

#llm #ai #agentskills

18 min read

Md Jamilur Rahman

Jun 17

GLM 5.2: Zhipu's Open-Weight Frontier Model With 1M Context

#news #ai #llm #opensource

5 min read

Mindtrovert Labs

Jun 4

RAG pilots fail when the sources are not ready

#ai #llm #rag #productivity

2 min read

Andrii Krugliak

Jun 3

The most expensive bug in an AI agent is the one it's confident about

#discuss #agents #ai #llm

3 min read

Anikalp Jaiswal

Jun 4

AWS Optimizes Starts, Adaptive Worms Rise, and LLM Memory Gets Local

#ai #technology #llm #programming

2 min read

Jun 3

# Enterprise RAG’s Biggest Risk: Answers That Look Correct but Aren’t

#rag #ai #devops #llm

7 min read

BOSS_METALLIQUE

Jun 3

I built a circuit breaker for LLM agents after seeing someone lose $200 overnight

#ai #python #llm #opensource

6 min read

Ben Habif Rudnik 🇨🇱🇮🇱🇺🇦

Jun 4

From Commerce to E-Commerce to MCP-Commerce: The Third Wave

#agents #ai #llm #mcp

3 min read

Learn AI Resource

Jun 3

Stop Spending $500/Month on API Calls: Build Your Own LLM Pipeline

#ai #llm #productivity #devops

3 min read

Jun 3

Over-editing is a token tax: GPT-5.4 ships 6.5x more diff per fix than Claude Opus 4.6, and your bill notices

#llm #opensource #ai #costtracking

2 min read

Marcelo Cabral Ghilardi

Jun 3

Rodei IA de 35B na minha GPU velha e me surpreendi!

#ai #gpu #llm #quantizacao

4 min read

👋 Sign in for the ability to sort posts by relevant, latest, or top.