DEV Community

# llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
# Introducing Leangetic: a local-first compiler for cheaper AI agents

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

Comments
3 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
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
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
How AI Chat Platforms Actually Implement Content Moderation (and Why "Uncensored" Models Aren't Just "GPT Without Filters")

How AI Chat Platforms Actually Implement Content Moderation (and Why "Uncensored" Models Aren't Just "GPT Without Filters")

Comments
3 min read
8 of the World's Top-10 Open-Source LLMs Are Chinese. Here's How to Use Them All with One OpenAI-Compatible Key.

8 of the World's Top-10 Open-Source LLMs Are Chinese. Here's How to Use Them All with One OpenAI-Compatible Key.

Comments
3 min read
Structuring Raw Interaction Data in AI Agents using Weaviate Engram

Structuring Raw Interaction Data in AI Agents using Weaviate Engram

1
Comments
3 min read
What Actually Runs Well on a GTX 1080 Ti in 2026 (Measured)

What Actually Runs Well on a GTX 1080 Ti in 2026 (Measured)

Comments
3 min read
MiniMax M3 Ships Open-Weight 1M Context: MiniMax Sparse Attention (MSA)

MiniMax M3 Ships Open-Weight 1M Context: MiniMax Sparse Attention (MSA)

Comments
6 min read
Serving any LLM using a single command line with Flama

Serving any LLM using a single command line with Flama

5
Comments
9 min read
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
Email Triage Taxonomies for LLM Classification

Email Triage Taxonomies for LLM Classification

2
Comments
5 min read
I stopped trusting “same answers, fewer tokens” after watching an agent lose 1 field name and burn 3 hours

I stopped trusting “same answers, fewer tokens” after watching an agent lose 1 field name and burn 3 hours

Comments
7 min read
A Frontier Model Goes Dark: AI Week of June 16, 2026

A Frontier Model Goes Dark: AI Week of June 16, 2026

Comments
23 min read
How to Build Production-Ready Generative AI Development Services for Enterprise Applications

How to Build Production-Ready Generative AI Development Services for Enterprise Applications

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