DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Why I Use TRAE: Free LLMs, Stability, and 1M Token Context

Why I Use TRAE: Free LLMs, Stability, and 1M Token Context

Comments
3 min read
Cara pakai API Claude & DeepSeek dari Indonesia — bayar Rupiah via QRIS (tanpa kartu kredit)

Cara pakai API Claude & DeepSeek dari Indonesia — bayar Rupiah via QRIS (tanpa kartu kredit)

Comments
2 min read
Pydantic passed. Types matched. The downstream system still got garbage.

Pydantic passed. Types matched. The downstream system still got garbage.

Comments 1
3 min read
Tool Permission Matrix Builder & Validator: Structured, Visual Policy Management for AI Agent Teams

Tool Permission Matrix Builder & Validator: Structured, Visual Policy Management for AI Agent Teams

9
Comments 2
8 min read
LLM output validation: 5 patterns that actually work in production

LLM output validation: 5 patterns that actually work in production

Comments
6 min read
How I Found Out 52% of My Knowledge Graph Was Duplicates (and What I Did About It)

How I Found Out 52% of My Knowledge Graph Was Duplicates (and What I Did About It)

3
Comments 2
2 min read
Choosing the Right Model-Routing Threshold for Frontier Models

Choosing the Right Model-Routing Threshold for Frontier Models

1
Comments 1
3 min read
Building RAGEval: My Journey from Problem to Production Foundation in 2 Days

Building RAGEval: My Journey from Problem to Production Foundation in 2 Days

Comments 4
9 min read
How LLM agents confabulate infrastructure and data provenance

How LLM agents confabulate infrastructure and data provenance

Comments 6
9 min read
Don't use an LLM to decide what your AI agent is allowed to do

Soft intelligence vs hard enforcement

Don't use an LLM to decide what your AI agent is allowed to do

13
Comments 15
4 min read
Fine-tuning vs RAG: a decision framework with examples

Fine-tuning vs RAG: a decision framework with examples

Comments
6 min read
How to Stop Your LLM Agent From Looping Itself Into Oblivion

How to Stop Your LLM Agent From Looping Itself Into Oblivion

Comments
5 min read
I used LLMs to rewrite meta descriptions for 1,600 articles — honest results

I used LLMs to rewrite meta descriptions for 1,600 articles — honest results

Comments
5 min read
Using Qwen 3.6 Plus: Great but a Bit Expensive

Using Qwen 3.6 Plus: Great but a Bit Expensive

Comments
2 min read
Our AI Inference Bill Dropped 65% After We Stopped Treating Every Query the Same

Our AI Inference Bill Dropped 65% After We Stopped Treating Every Query the Same

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