DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Jev vs Laya: The Same AI Idea, One Closed and One Open

Jev vs Laya: The Same AI Idea, One Closed and One Open

7
Comments
5 min read
My local 7B thinks "kill a Python process" is a violent crime — and my regex beat it

My local 7B thinks "kill a Python process" is a violent crime — and my regex beat it

Comments
4 min read
Human-in-the-Loop Validation for AI-Generated Financial Models

Human-in-the-Loop Validation for AI-Generated Financial Models

Comments
8 min read
Choosing the Right LangChain Memory: A Practical Guide for Developers

Choosing the Right LangChain Memory: A Practical Guide for Developers

Comments
3 min read
Why Does RAG Miss Information That's Clearly in the Document?

Why Does RAG Miss Information That's Clearly in the Document?

15
Comments 1
5 min read
Clean JSON Extraction with Ollama and Python

Clean JSON Extraction with Ollama and Python

1
Comments
3 min read
Readers took my MCP schema study apart. Here's what they found.

Readers took my MCP schema study apart. Here's what they found.

3
Comments 2
6 min read
What Retrieval Still Hasn't Decided

What Retrieval Still Hasn't Decided

2
Comments 8
11 min read
I built an LLM tuner. Benchmarking it proved me wrong four times.

I built an LLM tuner. Benchmarking it proved me wrong four times.

Comments
5 min read
What is a KV cache in LLM inference? (and why it, not the weights, limits your throughput)

What is a KV cache in LLM inference? (and why it, not the weights, limits your throughput)

Comments
3 min read
He Says He Co-Invented ChatGPT. His New AI, Jev, Won't Write a Word

He Says He Co-Invented ChatGPT. His New AI, Jev, Won't Write a Word

Comments
10 min read
We Asked 330 Models a Question in Korean. Half of Them Answered in the Wrong Alphabet.

We Asked 330 Models a Question in Korean. Half of Them Answered in the Wrong Alphabet.

Comments
4 min read
LLM - Day 1 - Intro

LLM - Day 1 - Intro

Comments
3 min read
Jev: one judgment call, or twelve dimension scores? I measured both on three classification tasks

Jev: one judgment call, or twelve dimension scores? I measured both on three classification tasks

Comments
9 min read
Best Hardware for Local LLMs in 2026: Mac vs NVIDIA vs AMD, One Formula for Every Row

Best Hardware for Local LLMs in 2026: Mac vs NVIDIA vs AMD, One Formula for Every Row

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