Forem

# llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
I was worried about the lack of security in shared .cursorrules, so I built a static analyzer to audit them.

I was worried about the lack of security in shared .cursorrules, so I built a static analyzer to audit them.

1
Comments
1 min read
When Your AI Elaborates, It Forgets to Count

When Your AI Elaborates, It Forgets to Count

Comments
2 min read
How to onboard to any codebase with AI in under 5 minutes using ContextEngine

How to onboard to any codebase with AI in under 5 minutes using ContextEngine

Comments
3 min read
Structured Outputs Are the Contract Your AI Agent Is Missing
Cover image for Structured Outputs Are the Contract Your AI Agent Is Missing

Structured Outputs Are the Contract Your AI Agent Is Missing

3
Comments
5 min read
We tracked 29 MCP pain points across 7 communities. Which one would you actually pay to fix?

We tracked 29 MCP pain points across 7 communities. Which one would you actually pay to fix?

1
Comments
4 min read
ARC-AGI-3 Changes What Agent Infrastructure Needs to Be

ARC-AGI-3 Changes What Agent Infrastructure Needs to Be

2
Comments 2
3 min read
Ollama in Docker Compose with GPU and Persistent Model Storage

Ollama in Docker Compose with GPU and Persistent Model Storage

1
Comments
10 min read
Ollama behind a reverse proxy with Caddy or Nginx for HTTPS streaming

Ollama behind a reverse proxy with Caddy or Nginx for HTTPS streaming

1
Comments
7 min read
The Routing Pattern: How Smart Teams Actually Use Fast vs Capable Models

The Routing Pattern: How Smart Teams Actually Use Fast vs Capable Models

Comments
2 min read
Why Hybrid Agentic AI Is the Future of QA
Cover image for Why Hybrid Agentic AI Is the Future of QA

Why Hybrid Agentic AI Is the Future of QA

Comments
4 min read
Amazon Bedrock Agents: Building an Industrial AI Assistant

Amazon Bedrock Agents: Building an Industrial AI Assistant

Comments
12 min read
Amazon Bedrock AgentCore Evaluations: LLM-as-a-Judge in Production

Amazon Bedrock AgentCore Evaluations: LLM-as-a-Judge in Production

Comments
12 min read
The End of Test-Driven Development: Best Practices for AI Agent-Driven Development with Formal Methods

The End of Test-Driven Development: Best Practices for AI Agent-Driven Development with Formal Methods

2
Comments
23 min read
I Fine-Tuned an LLM — And It Actually Worked

I Fine-Tuned an LLM — And It Actually Worked

Comments
2 min read
The Local AI Delegation Problem: Why Small Models Fail and How to Fix It

The Local AI Delegation Problem: Why Small Models Fail and How to Fix It

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