DEV Community

# llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
How to Build AI Agents That Actually Learn From Their Mistakes

How to Build AI Agents That Actually Learn From Their Mistakes

2
Comments
18 min read
Privacy-First Health AI: Running Llama-3 in Your Browser with WebGPU and WebLLM

Privacy-First Health AI: Running Llama-3 in Your Browser with WebGPU and WebLLM

2
Comments
4 min read
Claude Code's compaction discards data that's still on disk

Claude Code's compaction discards data that's still on disk

1
Comments
1 min read
LLM Self-Hosting and AI Sovereignty

LLM Self-Hosting and AI Sovereignty

Comments
13 min read
Stop Stuffing Entire Files into LLMs — I Built a Surgical Context Extractor for Python

Stop Stuffing Entire Files into LLMs — I Built a Surgical Context Extractor for Python

Comments
3 min read
How to Run an AI Benchmark That Doesn't Lie to You

How to Run an AI Benchmark That Doesn't Lie to You

Comments
4 min read
550 Hallucinations, Zero Discoveries: What Happens When You Force an LLM to Invent Mathematics

550 Hallucinations, Zero Discoveries: What Happens When You Force an LLM to Invent Mathematics

Comments
8 min read
How LLM Memory Actually Works in Production Systems

How LLM Memory Actually Works in Production Systems

Comments
4 min read
Building an AI-Powered Natural Language SQL Interface: An MVP Journey

Building an AI-Powered Natural Language SQL Interface: An MVP Journey

Comments
6 min read
Anthropic Just Published a Kill Chain for AI Model Theft. Let's Break It Down.

Anthropic Just Published a Kill Chain for AI Model Theft. Let's Break It Down.

Comments 4
7 min read
How Komilion's Request Routing Actually Works

How Komilion's Request Routing Actually Works

Comments
4 min read
Caching Strategies for LLM Systems – Part 4: Grouped-Query Attention for Scalable, Efficient Transformers

Caching Strategies for LLM Systems – Part 4: Grouped-Query Attention for Scalable, Efficient Transformers

Comments
3 min read
Claude's Context Compaction API: Infinite Conversations with One Parameter

Claude's Context Compaction API: Infinite Conversations with One Parameter

Comments
3 min read
PortKey Just Raised $15M — Here's What That Means for Your AI Costs

PortKey Just Raised $15M — Here's What That Means for Your AI Costs

Comments
3 min read
Why AI Agents Need to Think About Trust: Lessons from the MoltBook Security Incident

Why AI Agents Need to Think About Trust: Lessons from the MoltBook Security Incident

1
Comments
2 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.