Forem

# llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
I Benchmarked the Voice AI Stack in May 2026: What Actually Holds Up in Production
Cover image for I Benchmarked the Voice AI Stack in May 2026: What Actually Holds Up in Production

I Benchmarked the Voice AI Stack in May 2026: What Actually Holds Up in Production

Comments
12 min read
DeepClaude Merges Two AI Models Into One Agent Loop
Cover image for DeepClaude Merges Two AI Models Into One Agent Loop

DeepClaude Merges Two AI Models Into One Agent Loop

Comments
6 min read
RAG - Chunking

RAG - Chunking

Comments
3 min read
XML Tags Don't Help Short Prompts — Here's When They Actually Matter (2026)

XML Tags Don't Help Short Prompts — Here's When They Actually Matter (2026)

Comments
4 min read
Building an MCP server — lessons from thunderbit-mcp
Cover image for Building an MCP server — lessons from thunderbit-mcp

Building an MCP server — lessons from thunderbit-mcp

Comments 1
8 min read
ProxyFace: Give Your AI a Face & Emotions (100% Local, Zero Telemetry)

ProxyFace: Give Your AI a Face & Emotions (100% Local, Zero Telemetry)

Comments
2 min read
Prompt Engineering: Getting the Best Results from AI Language Models

Prompt Engineering: Getting the Best Results from AI Language Models

1
Comments 1
1 min read
AI Agents as Economic Actors: The Infrastructure Layer for Autonomous Commerce
Cover image for AI Agents as Economic Actors: The Infrastructure Layer for Autonomous Commerce

AI Agents as Economic Actors: The Infrastructure Layer for Autonomous Commerce

Comments
5 min read
I read 31 pages of Anthropic prompting guidance so you don't have to — here's what actually changes with Claude 4.7

I read 31 pages of Anthropic prompting guidance so you don't have to — here's what actually changes with Claude 4.7

Comments
4 min read
DeepSeek V4, `llama.cpp` Q4_K_M, & Ollama Ryzen APU Guide Boost Local LLM

DeepSeek V4, `llama.cpp` Q4_K_M, & Ollama Ryzen APU Guide Boost Local LLM

Comments
3 min read
Beyond Keywords: Mastering HyDE for Smarter Retrieval đź§ 
Cover image for Beyond Keywords: Mastering HyDE for Smarter Retrieval đź§ 

Beyond Keywords: Mastering HyDE for Smarter Retrieval đź§ 

Comments
4 min read
LangChain ChromaDB Metadata Priority Injection — RAG Poisoning Vulnerability

LangChain ChromaDB Metadata Priority Injection — RAG Poisoning Vulnerability

Comments
1 min read
Debugging confidently wrong answers from LLM-powered features
Cover image for Debugging confidently wrong answers from LLM-powered features

Debugging confidently wrong answers from LLM-powered features

Comments
4 min read
AI Cited a URL That Didn't Contain the Claim. I Built the Tooling to Measure How Often
Cover image for AI Cited a URL That Didn't Contain the Claim. I Built the Tooling to Measure How Often

AI Cited a URL That Didn't Contain the Claim. I Built the Tooling to Measure How Often

1
Comments
16 min read
Model Showdown Round 3: Ditching Ollama in Favor of llama.cpp

Model Showdown Round 3: Ditching Ollama in Favor of llama.cpp

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