DEV Community

#llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Your Agent's Memory Is a Dataset Nobody Is Curating

Your Agent's Memory Is a Dataset Nobody Is Curating

Comments 1
5 min read
Chunking: the most underrated decision in your RAG pipeline

Chunking: the most underrated decision in your RAG pipeline

2
Comments
6 min read
Rate Limits Are a Product Problem in Multi-Model AI Apps

Rate Limits Are a Product Problem in Multi-Model AI Apps

Comments 1
3 min read
Why Claude Loses Users to Cheaper AI Tools

Why Claude Loses Users to Cheaper AI Tools

2
Comments 2
3 min read
Claude Code hooks looked like they stopped firing on MCP tools — it was my own hook crashing"

Claude Code hooks looked like they stopped firing on MCP tools — it was my own hook crashing"

Comments 4
10 min read
Four times the system was wrong about itself

AI self-reports are just text reads

Four times the system was wrong about itself

5
Comments 9
7 min read
GhostSplice Isn't a Jailbreak, It's a Reminder That LLMs Can't Do Access Control

GhostSplice Isn't a Jailbreak, It's a Reminder That LLMs Can't Do Access Control

1
Comments
3 min read
Your LLM Fallback Probably Isn't a Fallback

Your LLM Fallback Probably Isn't a Fallback

1
Comments 1
4 min read
Building a Diversifi Memory Agent on Qwen Cloud

Building a Diversifi Memory Agent on Qwen Cloud

Comments
6 min read
Stop Comparing GPU Clouds Only by $/hour

Stop Comparing GPU Clouds Only by $/hour

Comments
10 min read
GPT vs Claude vs DeepSeek на одних задачах: регулярка, рефакторинг, SQL

GPT vs Claude vs DeepSeek на одних задачах: регулярка, рефакторинг, SQL

1
Comments
1 min read
The 20-minute check I run before swapping an agent to a new model

The 20-minute check I run before swapping an agent to a new model

Comments 1
3 min read
How to test your LLM app for prompt injection: promptfoo vs garak vs Giskard vs PyRIT vs sentinel-scan-cli

How to test your LLM app for prompt injection: promptfoo vs garak vs Giskard vs PyRIT vs sentinel-scan-cli

1
Comments 1
5 min read
Claude 3.5 Sonnet is the New Default Workhorse

Claude 3.5 Sonnet is the New Default Workhorse

Comments
3 min read
Durable Memory: Why Vector Databases Aren't Enough

The write-side problem highlighted in comments

Durable Memory: Why Vector Databases Aren't Enough

34
Comments 24
5 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.