Forem

# llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
I Built Routiform After Hitting Every Limit with 9router and OmniRoute

I Built Routiform After Hitting Every Limit with 9router and OmniRoute

Comments
4 min read
The $400M AI FinOps Gap: Why Cost Visibility Isn't the Same as Cost Control
Cover image for The $400M AI FinOps Gap: Why Cost Visibility Isn't the Same as Cost Control

The $400M AI FinOps Gap: Why Cost Visibility Isn't the Same as Cost Control

Comments
8 min read
Claude Code Is Burning Your API Budget: The Model Routing Architecture That Fixes It

Claude Code Is Burning Your API Budget: The Model Routing Architecture That Fixes It

Comments
7 min read
YAML vs Markdown vs JSON vs TOON: Which Format Is Most Efficient for the Claude API
Cover image for YAML vs Markdown vs JSON vs TOON: Which Format Is Most Efficient for the Claude API

YAML vs Markdown vs JSON vs TOON: Which Format Is Most Efficient for the Claude API

Comments
17 min read
GLM 5.1 just dropped — 754B open-weight MoE model under MIT license. here's how to run it

GLM 5.1 just dropped — 754B open-weight MoE model under MIT license. here's how to run it

Comments 2
3 min read
How to Fine-Tune GPT-4o-mini on Your Own Guardrail Failures (50 Lines of Python)

How to Fine-Tune GPT-4o-mini on Your Own Guardrail Failures (50 Lines of Python)

Comments
6 min read
Best Claude Code Gateway for Multi-Model Routing
Cover image for Best Claude Code Gateway for Multi-Model Routing

Best Claude Code Gateway for Multi-Model Routing

Comments
5 min read
The 5 Levels of RAG Maturity: How to Know When Your RAG Is Actually Production-Ready
Cover image for The 5 Levels of RAG Maturity: How to Know When Your RAG Is Actually Production-Ready

The 5 Levels of RAG Maturity: How to Know When Your RAG Is Actually Production-Ready

4
Comments
8 min read
Simplifying the AI Testing through Evaliphy
Cover image for Simplifying the AI Testing through Evaliphy

Simplifying the AI Testing through Evaliphy

1
Comments
5 min read
My AI pipeline had a 1M token context window. The output still got worse.

My AI pipeline had a 1M token context window. The output still got worse.

Comments
2 min read
AI Model Pricing Is a Mess — Here Is How We Track It

AI Model Pricing Is a Mess — Here Is How We Track It

1
Comments
2 min read
From ollama run to Tokens: What Really Happens When You Run an LLM Locally
Cover image for From ollama run to Tokens: What Really Happens When You Run an LLM Locally

From ollama run to Tokens: What Really Happens When You Run an LLM Locally

1
Comments
5 min read
Training Small LLMs to Edit Code Instead of Generating It
Cover image for Training Small LLMs to Edit Code Instead of Generating It

Training Small LLMs to Edit Code Instead of Generating It

Comments
4 min read
How to Add Cost-Aware Model Selection to Your AI Agent

How to Add Cost-Aware Model Selection to Your AI Agent

1
Comments
2 min read
"Attention Is All You Need" Paper tahun 2017 yang mengubah dunia kecerdasan buatan, dijelaskan tanpa perlu latar belakang teknis.
Cover image for "Attention Is All You Need" Paper tahun 2017 yang mengubah dunia kecerdasan buatan, dijelaskan tanpa perlu latar belakang teknis.

"Attention Is All You Need" Paper tahun 2017 yang mengubah dunia kecerdasan buatan, dijelaskan tanpa perlu latar belakang teknis.

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