DEV Community

# llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Securing OpenAI Agents SDK Against Memory Poisoning (ASI06) Using Pydantic Field Validators

Securing OpenAI Agents SDK Against Memory Poisoning (ASI06) Using Pydantic Field Validators

Comments
3 min read
We Built the Loops Both Anthropic and OpenAI Are Now Telling Engineers to Write. Here's the Architecture.

We Built the Loops Both Anthropic and OpenAI Are Now Telling Engineers to Write. Here's the Architecture.

Comments
5 min read
Anthropic Acquires Stainless: The SDK Layer Is Now Part of the Platform

Anthropic Acquires Stainless: The SDK Layer Is Now Part of the Platform

Comments
2 min read
Unload All llama.cpp Router Models Without Restarting

Unload All llama.cpp Router Models Without Restarting

Comments
9 min read
A Jailbroken Claude Code Breached Nine Government Agencies. Here's What That Actually Means.

A Jailbroken Claude Code Breached Nine Government Agencies. Here's What That Actually Means.

Comments
3 min read
Production-Grade RAG: Why Vector Search Isn't Enough (and How Hybrid Search Fills the Gaps)

Production-Grade RAG: Why Vector Search Isn't Enough (and How Hybrid Search Fills the Gaps)

3
Comments 2
6 min read
Problem Framing: The Cost of Naiveté

Problem Framing: The Cost of Naiveté

Comments
6 min read
What is Gemini 3.5 Flash? Google's New Fast Frontier Model Explained

What is Gemini 3.5 Flash? Google's New Fast Frontier Model Explained

Comments
12 min read
DeepSeek V4 vs Claude Opus 4.5 for coding: benchmark comparison

DeepSeek V4 vs Claude Opus 4.5 for coding: benchmark comparison

Comments
6 min read
5 silent failure patterns which I found analyzing 50+ real agent traces

5 silent failure patterns which I found analyzing 50+ real agent traces

Comments
2 min read
I Didn't Trust the AI Memory Until I Built This

I Didn't Trust the AI Memory Until I Built This

Comments
14 min read
wiki42: compile a markdown wiki into RAG-ready chunks

wiki42: compile a markdown wiki into RAG-ready chunks

Comments
1 min read
A3M Router: 99.5% LLM Routing Accuracy Without ML — How We Built It

A3M Router: 99.5% LLM Routing Accuracy Without ML — How We Built It

Comments
4 min read
What I learned building memory for Claude Code — measured against the popular alternative

What I learned building memory for Claude Code — measured against the popular alternative

Comments 1
8 min read
GGUF & Modelfile: The Power User's Guide to Local LLMs

GGUF & Modelfile: The Power User's Guide to Local LLMs

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