DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
LLM Smells: The Tells in AI Writing, and the Costlier Ones in AI Code

LLM Smells: The Tells in AI Writing, and the Costlier Ones in AI Code

Comments
5 min read
My commit message said "You've hit your session limit"

Local commit generation using Ollama

My commit message said "You've hit your session limit"

46
Comments 8
8 min read
Taxonomy Surgery, Cosine = 1.0000, and Making Routing Disappear into Infrastructure

Taxonomy Surgery, Cosine = 1.0000, and Making Routing Disappear into Infrastructure

3
Comments
5 min read
Securing AI Agents: Containment Over Trust

Securing AI Agents: Containment Over Trust

Comments 8
6 min read
SOC-in-a-Box: One LLM, Eight Hats, A Production-Bar AI SOC on a Single GPU

SOC-in-a-Box: One LLM, Eight Hats, A Production-Bar AI SOC on a Single GPU

Comments
11 min read
Why Self-Hosted Claude Code Was 15x Slower Than It Should Be

Why Self-Hosted Claude Code Was 15x Slower Than It Should Be

Comments
10 min read
Teaching a Reranker the Language of Security Tickets (+41% MRR@10)

Teaching a Reranker the Language of Security Tickets (+41% MRR@10)

Comments
9 min read
Three Chat Template Patterns That Silently Kill Your Prompt Cache

Three Chat Template Patterns That Silently Kill Your Prompt Cache

Comments
7 min read
Inference Optimization for the Rest of Us — KV Cache, Quantization, and Latency Tradeoffs

Inference Optimization for the Rest of Us — KV Cache, Quantization, and Latency Tradeoffs

1
Comments 2
5 min read
[Open-Source LLM Agent #3] Running a Whole RAG Agent Offline: LangGraph + Ollama + Embedded Qdrant (Zero API Keys)

[Open-Source LLM Agent #3] Running a Whole RAG Agent Offline: LangGraph + Ollama + Embedded Qdrant (Zero API Keys)

Comments
5 min read
KV cache quantization: what FP8/INT8 K and V actually buy you, and where they break

KV cache quantization: what FP8/INT8 K and V actually buy you, and where they break

1
Comments
8 min read
OpenClaw Windows Node, MemPalace & NVIDIA Cosmos Boost Local AI & Open Models

OpenClaw Windows Node, MemPalace & NVIDIA Cosmos Boost Local AI & Open Models

Comments
3 min read
Meta-Cognition Is the Future of AI Personalization — A 4-Quadrant Framework to Build It

Meta-Cognition Is the Future of AI Personalization — A 4-Quadrant Framework to Build It

3
Comments 2
5 min read
A practical way to use GPT, Claude, Gemini and DeepSeek through one OpenAI-compatible API

A practical way to use GPT, Claude, Gemini and DeepSeek through one OpenAI-compatible API

1
Comments
2 min read
Why Most AI Agent Projects Fail in Production

Why Most AI Agent Projects Fail in Production

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