DEV Community

#llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Getting structured JSON out of five incompatible LLM APIs — and degrading when they ignore you

The parser as the real system contract

Getting structured JSON out of five incompatible LLM APIs — and degrading when they ignore you

7
Comments 13
5 min read
We Audited Our Agent Tool-Call Traces. Half Our Eval Data Was Garbage.

We Audited Our Agent Tool-Call Traces. Half Our Eval Data Was Garbage.

Comments
4 min read
KV Cache Is Eating Your VRAM — Here's How to Estimate It Before You Run Out

KV Cache Is Eating Your VRAM — Here's How to Estimate It Before You Run Out

Comments
6 min read
Gemma 4: Google's Lightweight Powerhouse — Run AI on Hardware You Already Own

Gemma 4: Google's Lightweight Powerhouse — Run AI on Hardware You Already Own

Comments
3 min read
GLM-4: The Chinese-English Bilingual Workhorse You Didn't Know You Needed

GLM-4: The Chinese-English Bilingual Workhorse You Didn't Know You Needed

Comments
3 min read
Preventing GPT hallucination in automated content pipelines: how I structure Make.com flows with data injection

Preventing GPT hallucination in automated content pipelines: how I structure Make.com flows with data injection

Comments
8 min read
I ran Claude Code on a local LLM for 4 hours — 7M tokens, $0 (would have cost $94)

I ran Claude Code on a local LLM for 4 hours — 7M tokens, $0 (would have cost $94)

Comments
2 min read
Cost accounting for diffusion image generation at $0.0008 per render

Cost accounting for diffusion image generation at $0.0008 per render

Comments
4 min read
The Human in the Loop Doesn't Scale. I Kept Him Anyway.

The Human in the Loop Doesn't Scale. I Kept Him Anyway.

1
Comments 2
6 min read
LLM Agents Are Now Finding Zero-Days: How AI is Autonomously Rewriting the Rules of Vulnerability Research

LLM Agents Are Now Finding Zero-Days: How AI is Autonomously Rewriting the Rules of Vulnerability Research

Comments
19 min read
Cleaning Background Noise and Scaling AI Scraping

Cleaning Background Noise and Scaling AI Scraping

1
Comments
1 min read
The Two-Channel Problem: Structure and Soul for Reliable Long-Horizon Agents

The Two-Channel Problem: Structure and Soul for Reliable Long-Horizon Agents

1
Comments 8
4 min read
LangGraph 워크플로우 템플릿 (v41)

LangGraph 워크플로우 템플릿 (v41)

Comments
3 min read
Most people starting with local LLMs jump straight to 4-bit quantization because it's fast and uses

Most people starting with local LLMs jump straight to 4-bit quantization because it's fast and uses

Comments
1 min read
RAG 시스템 실전 구축 (v40)

RAG 시스템 실전 구축 (v40)

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