DEV Community

# llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
DiffusionGemma: How Google's New Open LLM Hits 1,000 Tokens/sec and Changes Inference Economics

DiffusionGemma: How Google's New Open LLM Hits 1,000 Tokens/sec and Changes Inference Economics

5
Comments
4 min read
5 Ways Prompt Injection Can Silently Compromise Your AI App

5 Ways Prompt Injection Can Silently Compromise Your AI App

Comments
4 min read
LLM KV Cache Optimization, Open Model Evaluation, & Agent Engineering Skills for Local Deployment

LLM KV Cache Optimization, Open Model Evaluation, & Agent Engineering Skills for Local Deployment

Comments
3 min read
I built a "boring" RAG demo over World Cup data — SQLite, sqlite-vec, and no framework

I built a "boring" RAG demo over World Cup data — SQLite, sqlite-vec, and no framework

Comments
4 min read
Prompt cache, finally typed: shipping llm-ports 0.1.0-alpha.19

Prompt cache, finally typed: shipping llm-ports 0.1.0-alpha.19

Comments
6 min read
Memory Poisoning: The Silent Threat to AI Agents (and How to Defend Against It)

Memory Poisoning: The Silent Threat to AI Agents (and How to Defend Against It)

Comments
2 min read
Why You Need to Become a Neuro-Punk Right Now

Why You Need to Become a Neuro-Punk Right Now

Comments
6 min read
Token Cost Optimization: How to Cut LLM Inference Spend Without Cutting Quality

Token Cost Optimization: How to Cut LLM Inference Spend Without Cutting Quality

1
Comments
5 min read
Model Context Protocol (MCP): Giao Thức Tương Lai Cho AI

Model Context Protocol (MCP): Giao Thức Tương Lai Cho AI

Comments
12 min read
Helicone is in maintenance mode. So I built the lightweight alternative I wanted.

Helicone is in maintenance mode. So I built the lightweight alternative I wanted.

Comments
2 min read
# Introducing Leangetic: a local-first compiler for cheaper AI agents

# Introducing Leangetic: a local-first compiler for cheaper AI agents

Comments
3 min read
Scaling an LLM Scoring Pipeline From One Job to 10,000 a Day

Scaling an LLM Scoring Pipeline From One Job to 10,000 a Day

Comments
5 min read
LLM-powered extraction kept silently corrupting my database. Here's what I built to fix it. tags: node, llm, opensource, api

LLM-powered extraction kept silently corrupting my database. Here's what I built to fix it. tags: node, llm, opensource, api

Comments
3 min read
Kong AI Gateway vs TrueFoundry: the honest version of this comparison

Kong AI Gateway vs TrueFoundry: the honest version of this comparison

Comments
7 min read
Every post my engine wrote hit 200 characters. Here is the fix.

Every post my engine wrote hit 200 characters. Here is the fix.

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