DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
vLLM Quickstart: High-Performance LLM Serving

vLLM Quickstart: High-Performance LLM Serving

Comments
18 min read
how we prevent ai agent's drift & code slop generation

how we prevent ai agent's drift & code slop generation

43
Comments 18
3 min read
LLM Steering: From Prompting Tricks to Activation Control

LLM Steering: From Prompting Tricks to Activation Control

1
Comments 1
6 min read
Model Context Protocol (MCP) — Integrating AI LLMs with Modern DevOps Systems

Model Context Protocol (MCP) — Integrating AI LLMs with Modern DevOps Systems

Comments
3 min read
I Run LLMs on a 768GB IBM POWER8 Server (And It's Faster Than You Think)

I Run LLMs on a 768GB IBM POWER8 Server (And It's Faster Than You Think)

1
Comments
6 min read
The Compiler Never Used Sarcasm: Why AI Feels Unsafe to the Neurodivergent Coder

The Compiler Never Used Sarcasm: Why AI Feels Unsafe to the Neurodivergent Coder

57
Comments 11
6 min read
I Built an AI Companion on Telegram That Actually Remembers You

I Built an AI Companion on Telegram That Actually Remembers You

2
Comments 1
3 min read
The era of more personal computing

The era of more personal computing

Comments
8 min read
The Tiny Sliders That Power AI (and Why There Are Trillions of Them)

The Tiny Sliders That Power AI (and Why There Are Trillions of Them)

Comments
6 min read
How to Deploy Alpaca’s MCP Server Remotely On Claude Mobile App

How to Deploy Alpaca’s MCP Server Remotely On Claude Mobile App

Comments
8 min read
I Built 86 AI Applications in One Year. Here's My Brutal Self-Audit.

I Built 86 AI Applications in One Year. Here's My Brutal Self-Audit.

1
Comments
9 min read
Writing for humans is no longer enough. Writing for AI is now part of the job

Writing for humans is no longer enough. Writing for AI is now part of the job

Comments
5 min read
What’s Actually Making Your LLM Costs Skyrocket?

What’s Actually Making Your LLM Costs Skyrocket?

1
Comments
2 min read
I built codex-monitor so I could ship code while I slept

I built codex-monitor so I could ship code while I slept

3
Comments 4
6 min read
How a Developer Built Eternal Contextual RAG and Achieved 85% Accuracy (from 60%)

How a Developer Built Eternal Contextual RAG and Achieved 85% Accuracy (from 60%)

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