DEV Community

# llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Shouldn't AI Move From Cloud to Local Compute?

Shouldn't AI Move From Cloud to Local Compute?

Comments 1
9 min read
Why I Replaced Most of My AI Subscriptions With a Mac Mini Running Local LLMs

Why I Replaced Most of My AI Subscriptions With a Mac Mini Running Local LLMs

Comments
4 min read
Stop AI Hallucinations: How to Make Natural Language Testing Real with "Harness Engineering"

Stop AI Hallucinations: How to Make Natural Language Testing Real with "Harness Engineering"

Comments 1
9 min read
I built the same AI app with and without LangChain. Here's what I learned.

I built the same AI app with and without LangChain. Here's what I learned.

Comments
5 min read
The Hidden Economics of AI: What It Actually Costs to Run LLMs in Production (With Real Data)

The Hidden Economics of AI: What It Actually Costs to Run LLMs in Production (With Real Data)

Comments 1
6 min read
NVIDIA RTX Spark Superchip: Unified CPU–GPU Memory

NVIDIA RTX Spark Superchip: Unified CPU–GPU Memory

Comments 1
8 min read
Most RAG Problems Are Retrieval Problems. Here Are 8 Fixes That Worked for Me

Most RAG Problems Are Retrieval Problems. Here Are 8 Fixes That Worked for Me

Comments
4 min read
Two Pre-Registered Benchmarks for Audit-Native RAG: RAB (EU AI Act 10/12/19) + LRB (Time-Travel Retrieval)

Two Pre-Registered Benchmarks for Audit-Native RAG: RAB (EU AI Act 10/12/19) + LRB (Time-Travel Retrieval)

Comments
3 min read
Generating a multilingual llms.txt in Astro

Generating a multilingual llms.txt in Astro

Comments
3 min read
Anthropic's Fable 5 Block Is a Reminder to Pick the Smallest Model That Passes

Anthropic's Fable 5 Block Is a Reminder to Pick the Smallest Model That Passes

Comments
5 min read
Blocking Prompt Injection Before It Reaches Your LLM

Blocking Prompt Injection Before It Reaches Your LLM

Comments
5 min read
A Chinese 8B model beat the Western 8B models at Japanese RAG. I still wouldn't put it in the default deployment — and that distinction is the point.

A Chinese 8B model beat the Western 8B models at Japanese RAG. I still wouldn't put it in the default deployment — and that distinction is the point.

Comments
4 min read
Long context is not AI memory: a builder playbook for reliable AI apps

Long context is not AI memory: a builder playbook for reliable AI apps

Comments 1
4 min read
Why I quit SaaS AI observability tools and built a local proxy instead

Why I quit SaaS AI observability tools and built a local proxy instead

Comments
2 min read
RAG should never be your default

RAG should never be your default

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