Llm - DEV Community

Skip to content

DEV Community

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

Nov 7

There's a Pattern Hidden in Qwen3.5-0.8B's Neurons That Training Can't Explain

#discuss #interpretability #llm #larp

14 min read

Nov 6

Using Evil Spirits To Cast Out Evil Spirits!

#ai #llm #lmm #science

36 min read

Ganesh Sivakumar

Nov 7

A new benchmark conned every frontier AI agent it tested.

#security #agents #llm #cybersecurity

4 min read

Lumen

Nov 7

Two ways to prove which model answered you

#ai #api #llm #security

4 min read

YASHWANTH

Nov 7

Why our incident agent remembers bad fixes using Hindsight

#agents #ai #automation #llm

8 min read

Nov 7

Decode Speed Is Bytes Divided by Bandwidth, and the Batch Ceiling Is 848 Tokens

#hardware #performance #llm #inference

6 min read

Nov 7

Route machine translation by risk, not by a single score

#ai #llm #translation #testing

4 min read

Kemisetti Hemachandra

Nov 7

How Hindsight memory badges stopped us repeating bad fixes

#ai #llm #devops #nextjs

8 min read

Nov 7

Who's Allowed to Add Work to Your Agent's Queue?

#ai #llm #agents

3 min read

Mohd Yusuf Khan

Nov 7

AI agent memory in Python: short-term, long-term, shared, with code

#python #ai #llm #tutorial

12 min read

Nov 7

LongLoom: Stop Losing Facts When Your Documents Exceed the Context Window

#ai #llm #opensource

4 min read

Kathi Harshith Reddy

Nov 7

My Agent Saw Acme Repeating Nova's Mistakes Using Hindsight

#ai #python #llm #agents

7 min read

BBT for BBT Italiano

Nov 7

Come osFoundry mantiene una sessione calda di Claude Code compatibile con la cache mentre continuano ad arrivare messaggi nel canale

#claude #llm #python #agenti

7 min read

Dhanya7230

Nov 7

Why Stateless RAG fails Product teams

#agents #ai #llm #rag

8 min read

Keshavan Thiagaraja

Nov 7

An offline AI pilot needs a network test, not a label

#ai #llm #security #testing

3 min read

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