DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
A Life in 150 Words, with AI

WeCoded 2026: Echoes of Experience đź’ś

A Life in 150 Words, with AI

1
Comments
6 min read
Detect Claude AI Code Marking: Why Chasing It Is a Distraction

Detect Claude AI Code Marking: Why Chasing It Is a Distraction

Comments
9 min read
Prompt caching cut my Claude API bill by 85%. Here's the exact setup.

Prompt caching cut my Claude API bill by 85%. Here's the exact setup.

1
Comments
5 min read
Your agent stops obeying your rules halfway through the session. Here's the structural reason — and the fix.

Your agent stops obeying your rules halfway through the session. Here's the structural reason — and the fix.

Comments
4 min read
From RAG to Skill Function: A New Architecture for Enterprise AI Knowledge

From RAG to Skill Function: A New Architecture for Enterprise AI Knowledge

Comments 2
4 min read
How I'm re-discovering computer science with LLM revolution

How I'm re-discovering computer science with LLM revolution

Comments
6 min read
MCP vs A2A: Model Context Protocol vs Agent2Agent

MCP vs A2A: Model Context Protocol vs Agent2Agent

4
Comments
8 min read
AI Fundamentals - Part 2: Why AI Gets Things Right... and Wrong

AI Fundamentals - Part 2: Why AI Gets Things Right... and Wrong

Comments
6 min read
AI Fundamentals - Part 1: From Prompt to Response

AI Fundamentals - Part 1: From Prompt to Response

Comments
7 min read
What Is Context Engineering?

What Is Context Engineering?

5
Comments
6 min read
Claude Code burns 5x more tokens before you type a word. Here's where they go.

Claude Code burns 5x more tokens before you type a word. Here's where they go.

1
Comments
3 min read
No AI Claim Without a Kill Condition: Falsifier-Driven AI Decisions

No AI Claim Without a Kill Condition: Falsifier-Driven AI Decisions

1
Comments 2
4 min read
Switching to GPT-5.6 in production: it's a schema, cache, and harness problem — not a model swap

Switching to GPT-5.6 in production: it's a schema, cache, and harness problem — not a model swap

Comments
3 min read
Streaming vs Batching LLM Responses: A Cost and Latency Analysis

Streaming vs Batching LLM Responses: A Cost and Latency Analysis

Comments
3 min read
Frontier LLMs Get 2 of 3 Tax Returns Wrong - Stop Letting Them Decide

Frontier LLMs Get 2 of 3 Tax Returns Wrong - Stop Letting Them Decide

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