DEV Community

#llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Temperature, top-p, and sampling: controlling LLM randomness

Temperature, top-p, and sampling: controlling LLM randomness

1
Comments
3 min read
The context window: an LLM's working memory and its limits

The context window: an LLM's working memory and its limits

1
Comments
3 min read
Fine-tuning vs RAG vs prompting: pick the right lever

Fine-tuning vs RAG vs prompting: pick the right lever

1
Comments
3 min read
Tokenization: why an LLM can't count the R's in strawberry

Tokenization: why an LLM can't count the R's in strawberry

1
Comments
3 min read
Stop Paying Full Price: Orchestrate Claude's 50% Off Batch API with Spring Batch and Virtual Threads

Stop Paying Full Price: Orchestrate Claude's 50% Off Batch API with Spring Batch and Virtual Threads

Comments
2 min read
Prompt engineering that actually works (and what does not)

Prompt engineering that actually works (and what does not)

1
Comments
3 min read
Let Claude Code Improve Itself Unattended — An Autopilot That Uses Cost to Stop Runaways

Let Claude Code Improve Itself Unattended — An Autopilot That Uses Cost to Stop Runaways

Comments 1
5 min read
AI Agent Architecture Patterns That Actually Survive Production

AI Agent Architecture Patterns That Actually Survive Production

14
Comments 3
12 min read
Stuffing the Context Window Is Making Your Agent Dumber: What the Research Says

Stuffing the Context Window Is Making Your Agent Dumber: What the Research Says

1
Comments 1
5 min read
What happens when you ask 8 AI models the same buying question every month

What happens when you ask 8 AI models the same buying question every month

Comments
3 min read
Claude vs ChatGPT in 2026: Which One for Real Work?

Claude vs ChatGPT in 2026: Which One for Real Work?

Comments
6 min read
🦌 Mrigashira AI — Making Local AI Accessible to Everyone

🦌 Mrigashira AI — Making Local AI Accessible to Everyone

Comments
2 min read
Egregor: Локальный консилиум ИИ для комплексного аудита смарт-контрактов и кода

Egregor: Локальный консилиум ИИ для комплексного аудита смарт-контрактов и кода

5
Comments
1 min read
GLM-5 vs MiniMax M3: Open Models Got Serious

GLM-5 vs MiniMax M3: Open Models Got Serious

Comments
7 min read
Which LLM should I actually code with? I built a small benchmark to find out

Which LLM should I actually code with? I built a small benchmark to find out

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