DEV Community

#llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Everyone is hardening the structure. Nobody is passing down the why.

Everyone is hardening the structure. Nobody is passing down the why.

1
Comments 13
3 min read
RAG pilots fail when the sources are not ready

RAG pilots fail when the sources are not ready

Comments
2 min read
The most expensive bug in an AI agent is the one it's confident about

The most expensive bug in an AI agent is the one it's confident about

Comments
3 min read
AWS Optimizes Starts, Adaptive Worms Rise, and LLM Memory Gets Local

AWS Optimizes Starts, Adaptive Worms Rise, and LLM Memory Gets Local

Comments
2 min read
# Enterprise RAG’s Biggest Risk: Answers That Look Correct but Aren’t

# Enterprise RAG’s Biggest Risk: Answers That Look Correct but Aren’t

Comments
7 min read
The Prompt Quality Report: What 1,018 Scored Prompts Reveal

The Prompt Quality Report: What 1,018 Scored Prompts Reveal

1
Comments
2 min read
I built a circuit breaker for LLM agents after seeing someone lose $200 overnight

I built a circuit breaker for LLM agents after seeing someone lose $200 overnight

1
Comments
6 min read
I Built an LLM Filter That Prefers Silence Over Slop, and the Eval Harness That Keeps It Honest

I Built an LLM Filter That Prefers Silence Over Slop, and the Eval Harness That Keeps It Honest

Comments
4 min read
Can You Build an Alternative to LLMs? 8 Months, ~200 Failed Experiments, One Wall. 2

The wall of transferable causal transition

Can You Build an Alternative to LLMs? 8 Months, ~200 Failed Experiments, One Wall. 2

11
Comments 8
9 min read
From Commerce to E-Commerce to MCP-Commerce: The Third Wave

From Commerce to E-Commerce to MCP-Commerce: The Third Wave

Comments
3 min read
Your LLM bill has two sides. Build the ledger that shows both.

Your LLM bill has two sides. Build the ledger that shows both.

1
Comments
5 min read
Your LLM fused the two columns you asked for — and the eval marked it wrong

Your LLM fused the two columns you asked for — and the eval marked it wrong

Comments
3 min read
AI Governance for Engineering Teams: Guardrails, Budgets, and Audit Logs That Actually Scale

AI Governance for Engineering Teams: Guardrails, Budgets, and Audit Logs That Actually Scale

69
Comments 9
10 min read
Over-editing is a token tax: GPT-5.4 ships 6.5x more diff per fix than Claude Opus 4.6, and your bill notices

Over-editing is a token tax: GPT-5.4 ships 6.5x more diff per fix than Claude Opus 4.6, and your bill notices

Comments
2 min read
My AI journey

My AI journey

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