Llm Page 100 - DEV Community

Skip to content

DEV Community

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

Weaker models follow hidden log injections

Remdore

Nov 1

I hid instructions in my server logs to see which models would follow them

#ai #llm #security #digitalocean

6 min read

Lucas Henrique Alves Rosa

Oct 21

RAG: como conectar uma LLM aos dados da sua aplicação, e quando isso faz sentido

#ai #llm #rag

9 min read

Ward Ed

Oct 21

GPQA Diamond Has 198 Questions: What the Hugging Face Leaderboard's 115 Rows Can and Cannot Rank

#ai #opensource #llm #benchmark

14 min read

nab conn

Oct 21

How SentX's API Works: A Plain-English Walkthrough

#ai #api #llm

8 min read

Oct 22

I am building a practical AI agents course (LangChain first, then LangGraph), and the certificate has to be earned

#ai #langchain #python #llm

1 min read

Kirill Bespalov

Oct 21

DeepSeek V4.1 Flash on 8 B300: vLLM vs DeepInfer, 600K+ tokens/s

#ai #llm #machinelearning #performance

4 min read

Oct 21

KV Cache Offloading to NVMe: The Break-Even Bandwidth Math and Where It Does Not Pay Off

#ai #machinelearning #vllm #llm

14 min read

Oct 21

The Number Was a Version

#llm #gpu #selfhosted #performance

8 min read

Oct 21

Flip One Field: A Fairness Test That Beats Aggregate Parity

#llm #evaluation #fairness #python

2 min read

Sanskriti Harmukh for Vultr

Oct 22

Building a Llama.cpp Container Image

#docker #llm #ai #gpu

4 min read

Oct 21

EAGLE-4 does not run on a Mac. I measured MTP instead: +92% on one model, -19% on another

#ai #llm #macos #performance

11 min read

Nov 3

I ran the same multi-agent experiment twice. Half the conclusions flipped.

#ai #llm #agents #opensource

8 min read

Oct 21

AI System Design for Production

#ai #llm #production #systemdesign

9 min read

Hsiang Lee

Oct 21

We logged every major AI engine cited across 120 buyer questions. Official sites almost never made the list.

#ai #seo #llm

2 min read

Pogee.ai

Oct 21

Persona Drift: Why Your AI Character Slowly Stops Being Themselves

#ai #chatgpt #llm

8 min read

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