Llm - DEV Community

Skip to content

DEV Community

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

TokenLat

Nov 11

Your agent isn't hallucinating — your rules never defined "I don't know"

#ai #llm #agents #testing

5 min read

Nov 10

From Attention to 3-Bit Caches: How LLMs Learned to Remember Less (MHA, GQA, MLA, MoE, Quantisation Explained)

#ai #llm #machinelearning #deeplearning

22 min read

Nov 10

AI Agents Need a Runtime, Not Another Framework

#llm #infrastructure #security #opensource

7 min read

Nov 10

LLMs Aren’t the Only Game in Town: A Beginner’s Guide to JEPA, Concept Models and Decision Models

#ai #llm #machinelearning #beginners

11 min read

Ramakrishnan Lokanathan for Daily Context

Nov 11

Give Your Agent a Fast Path

#ai #llm #agents #aie

3 min read

Chinmay Goyal for Daily Context

Nov 11

The Fastest LLM Call Is The One You Never Make

#ai #llm #agents

3 min read

Nov 11

LLMs Locally on Consumer Hardware — Part 10: How the Setup Evolved — A Timeline of What Changed and Why

#localllama #ai #llm #agents

3 min read

Rich Ng

Nov 11

Run Gemma 4 31B-it Uncensored on a 12GB GPU: Complete Local Vision & 256K Context Guide with llama.cpp, DeepSeek Harness & Hermes Agent

#ai #llm #machinelearning #tutorial

14 min read

Nov 11

Why Your LLM Agent Keeps Burning Tokens (and How to Cut It at the HTTP Layer)

#ai #llm #programming #opensource

3 min read

Nov 11

grep can't check the numbers in a Japanese LLM summary. Here is why, and a small fix.

#python #ai #llm #mcp

2 min read

Nov 11

Grounding AI-written marketing posts in real weather data, without letting the model make things up

#llm #ai #typescript #sqlite

7 min read

Nov 11

AlphaProof Code: A Developer's Checklist Before You Trust an AI-Verified Codebase

#ai #security #llm #opensource

4 min read

Nov 11

Max Reasoning Effort Is a Bad Default: More Thinking Can Make Your Model Worse

#ai #llm #machinelearning #programming

7 min read

Manohar Papasani

Nov 11

You are seeing XYZ issue in your ai responses, walk me through what you change in your process/pipeline to resolve it.

#aiinterview #genai #rag #llm

2 min read

yif wong

Nov 11

Comparing 7 Chinese frontier models through one API — a field guide, not a benchmark

#ai #llm #deepseek #api

5 min read

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