DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Sub-Agent Architectures: Patterns, Trade-offs, and a Kotlin Implementation

Sub-Agent Architectures: Patterns, Trade-offs, and a Kotlin Implementation

Comments
11 min read
The Anatomy of an AI Agent: Memory, Tools, Planning, and Execution Explained

The Anatomy of an AI Agent: Memory, Tools, Planning, and Execution Explained

3
Comments
6 min read
Why Faster First Tokens Matter More Than Total Response Time

Why Faster First Tokens Matter More Than Total Response Time

Comments
10 min read
We Spent a Week Evaluating a Context Compression Tool, Then Killed It

We Spent a Week Evaluating a Context Compression Tool, Then Killed It

Comments 1
6 min read
Designing a Tool Architecture for AI Agents — Base Tools, Toolkits, and Dynamic Routing

Designing a Tool Architecture for AI Agents — Base Tools, Toolkits, and Dynamic Routing

1
Comments
3 min read
Why AI Needs an External Cognitive Layer Beyond Memory

Why AI Needs an External Cognitive Layer Beyond Memory

1
Comments
3 min read
Best AI Models for Coding in 2026: Claude, GPT-5, Gemini, and DeepSeek Compared

Best AI Models for Coding in 2026: Claude, GPT-5, Gemini, and DeepSeek Compared

Comments
5 min read
LLM Agents Need a Nervous System, Not Just a Brain

LLM Agents Need a Nervous System, Not Just a Brain

3
Comments
3 min read
I Built a Skill Reviewer. Then I Ran It on Itself.

I Built a Skill Reviewer. Then I Ran It on Itself.

5
Comments
5 min read
We Scanned 12 Popular MCP Servers. Here's What We Found.

We Scanned 12 Popular MCP Servers. Here's What We Found.

1
Comments
5 min read
How ChatGPT Actually Predicts Words (Explained Simply)

How ChatGPT Actually Predicts Words (Explained Simply)

2
Comments
2 min read
I Eliminated Layout Jitter From LLM Streaming — Here's How

I Eliminated Layout Jitter From LLM Streaming — Here's How

16
Comments
4 min read
I Tried Duplicating Layers in Qwen 3.5 to Reduce Hallucinations — Here's What Actually Happened

I Tried Duplicating Layers in Qwen 3.5 to Reduce Hallucinations — Here's What Actually Happened

1
Comments
5 min read
The OpenClaw ecosystem is exploding. I mapped the key players actually gaining traction.

The OpenClaw ecosystem is exploding. I mapped the key players actually gaining traction.

6
Comments 1
1 min read
Why LLM Rate Limits and Throughput Matter More Than Benchmarks

Why LLM Rate Limits and Throughput Matter More Than Benchmarks

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