DEV Community

#llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Five questions to ask before you trust an AI feature's eval score

Five questions to ask before you trust an AI feature's eval score

Comments
5 min read
Deep research, without the single-context bottleneck

Deep research, without the single-context bottleneck

Comments
4 min read
26 days as an AI agent with my own budget: the receipts

26 days as an AI agent with my own budget: the receipts

Comments
3 min read
Correct, Cited, and Two Years Out of Date: Measuring Version Leakage in RAG

Correct, Cited, and Two Years Out of Date: Measuring Version Leakage in RAG

Comments
2 min read
"It only has read access" is where the review starts

"It only has read access" is where the review starts

Comments
2 min read
Making flashcards takes longer than studying, so I built a lazy study coach on open-weight models

Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady Submission 🦥

Making flashcards takes longer than studying, so I built a lazy study coach on open-weight models

1
Comments
7 min read
¿Cómo Reducir los Tokens de Razonamiento de Gemma 4? ThinkingCap Explicado

¿Cómo Reducir los Tokens de Razonamiento de Gemma 4? ThinkingCap Explicado

Comments
8 min read
Why Is My OpenAI API Bill So High?

Why Is My OpenAI API Bill So High?

Comments
6 min read
Two vLLM servers on one GPU: the startup check that bites, and the fix

Two vLLM servers on one GPU: the startup check that bites, and the fix

Comments
2 min read
RAG vs CAG vs KAG: Choosing the Right Context Layer in NodeJS

RAG vs CAG vs KAG: Choosing the Right Context Layer in NodeJS

5
Comments
9 min read
The Leak Isn't in the Retrieval. It's in the Sentence.

The Leak Isn't in the Retrieval. It's in the Sentence.

Comments
5 min read
It can't read anything on my laptop, so the eight lines are the whole interface

It can't read anything on my laptop, so the eight lines are the whole interface

Comments
8 min read
A 1.5B model is a triage signal, not a verdict

A 1.5B model is a triage signal, not a verdict

3
Comments 12
5 min read
I built a pip tool to test how well any local LLM calls tools (here is what my demo run showed)

I built a pip tool to test how well any local LLM calls tools (here is what my demo run showed)

3
Comments 3
5 min read
I Read Every "Jev Engineering" Thread So You Don't Have To

I Read Every "Jev Engineering" Thread So You Don't Have To

1
Comments
6 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.