DEV Community

# llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Why Your Agent Doesn't Know What Time It Is

Why Your Agent Doesn't Know What Time It Is

1
Comments
7 min read
Same Model, Different Environment, Different Results

Interface design shaping model reasoning

Same Model, Different Environment, Different Results

5
Comments 9
9 min read
Utility is all you need

Utility is all you need

15
Comments 2
8 min read
Text-to-SQL Failure Demo

Text-to-SQL Failure Demo

1
Comments
6 min read
Exclusive: China's DeepSeek trained AI model on Nvidia's best chip despite US ban, official says - Reuters

Exclusive: China's DeepSeek trained AI model on Nvidia's best chip despite US ban, official says - Reuters

Comments
6 min read
Why We Ditched Bedrock Agents for Nova Pro and Built a Custom Orchestrator

Why We Ditched Bedrock Agents for Nova Pro and Built a Custom Orchestrator

2
Comments 1
7 min read
Why the E8 lattice is the perfect quantizer for KV caches

Why the E8 lattice is the perfect quantizer for KV caches

1
Comments
2 min read
What Is Context Engineering and How to Apply It in Real Systems

What Is Context Engineering and How to Apply It in Real Systems

4
Comments
6 min read
Local AI in 2026: Ollama Benchmarks, $0 Inference, and the End of Per-Token Pricing

Local AI in 2026: Ollama Benchmarks, $0 Inference, and the End of Per-Token Pricing

1
Comments
6 min read
Google's Gemma 4 Explained: The Open-Source Agent Toolkit We've Been Waiting For

Google's Gemma 4 Explained: The Open-Source Agent Toolkit We've Been Waiting For

Comments 2
3 min read
How I Built a PII Tokenization Middleware to Keep Sensitive Data Out of LLM APIs

How I Built a PII Tokenization Middleware to Keep Sensitive Data Out of LLM APIs

9
Comments 4
5 min read
The 12 approaches I tested before finding one that works

The 12 approaches I tested before finding one that works

Comments
5 min read
I Benchmarked 5 File Editing Strategies for AI Coding Agents. Here's What Actually Works.

I Benchmarked 5 File Editing Strategies for AI Coding Agents. Here's What Actually Works.

2
Comments 3
2 min read
How I Built Persistent Memory for Claude Code

Uses all six Claude Code hooks

How I Built Persistent Memory for Claude Code

10
Comments 32
9 min read
RAG in the Wild: What I Learned After Two Weeks of Chunking Experiments

RAG in the Wild: What I Learned After Two Weeks of Chunking Experiments

Comments 2
7 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.