close

DEV Community

# llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
The 5 Things Your LLM Benchmark Misses That Actually Decide the Winner

The 5 Things Your LLM Benchmark Misses That Actually Decide the Winner

Comments
7 min read
How to Use DeepSeek and Qwen API Outside China

How to Use DeepSeek and Qwen API Outside China

Comments
2 min read
RAG in production: the failure modes nobody warns you about

RAG in production: the failure modes nobody warns you about

Image 2
Comments 2
3 min read
The Open-Model Cost Chart Everyone's Sharing Is API Prices. Here's What Self-Hosting Actually Gets You (Measured)

The Open-Model Cost Chart Everyone's Sharing Is API Prices. Here's What Self-Hosting Actually Gets You (Measured)

Image 1
Comments
5 min read
LLM Gateway vs MCP Gateway: Understanding the New AI Infrastructure Stack

LLM Gateway vs MCP Gateway: Understanding the New AI Infrastructure Stack

Image 1
Comments 1
3 min read
"GLM-5.2 and the Open-Weight Tipping Point"

"GLM-5.2 and the Open-Weight Tipping Point"

Comments 1
2 min read
Context Rot: Why Your AI Coding Agent Gets Dumber Mid-Session (and How I Stopped It)

Context Rot: Why Your AI Coding Agent Gets Dumber Mid-Session (and How I Stopped It)

Comments
4 min read
Natural language drifts, LLMs are not an exception

Natural language drifts, LLMs are not an exception

Comments 1
1 min read
Vector Databases: Search by Meaning, at Scale

Vector Databases: Search by Meaning, at Scale

Image 1
Comments
1 min read
The Orchestration Bottleneck: Why Your Agent Infrastructure Needs Two Layers in 2026

The Orchestration Bottleneck: Why Your Agent Infrastructure Needs Two Layers in 2026

Comments
5 min read
Harvesting a regression test set from gateway logs with a plugin

Harvesting a regression test set from gateway logs with a plugin

Comments
4 min read
Use a flat-priced, auto-routing LLM API in Aider or Cline — one npx command

Use a flat-priced, auto-routing LLM API in Aider or Cline — one npx command

Image 1
Comments 1
2 min read
Unifying image inputs across three vision providers behind Bifrost

Unifying image inputs across three vision providers behind Bifrost

Comments
4 min read
Claude Code retries rate-limit errors for API keys, not for your Max plan

Claude Code retries rate-limit errors for API keys, not for your Max plan

Comments
4 min read
Two undocumented bugs in MCP Apps I found building a task panel for Claude

Two undocumented bugs in MCP Apps I found building a task panel for Claude

Image 1
Comments
4 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.