Forem

# llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
My Harness Is Not a Cage. It's an Org Chart.
Cover image for My Harness Is Not a Cage. It's an Org Chart.

My Harness Is Not a Cage. It's an Org Chart.

Comments
4 min read
Separating Agent Tool Calls from Authorization and Evidence

Separating Agent Tool Calls from Authorization and Evidence

Comments
10 min read
RAG vs. Fine-Tuning vs. Prompting: 2026 Strategic Guide
Cover image for RAG vs. Fine-Tuning vs. Prompting: 2026 Strategic Guide

RAG vs. Fine-Tuning vs. Prompting: 2026 Strategic Guide

Comments
4 min read
Separating Facts from Interpretations in Agent Knowledge Graphs

Separating Facts from Interpretations in Agent Knowledge Graphs

Comments
12 min read
How to Handle Proprietary Jargon in LLM-as-a-Judge Evaluations

How to Handle Proprietary Jargon in LLM-as-a-Judge Evaluations

Comments
4 min read
Building a Simple Exchange Rate MCP Server using FastMCP and AllRatesToday

Building a Simple Exchange Rate MCP Server using FastMCP and AllRatesToday

Comments
6 min read
Supervise a multi-agent setup with Local LLMs
Cover image for Supervise a multi-agent setup with Local LLMs

Supervise a multi-agent setup with Local LLMs

Comments
1 min read
AAEF v0.2.0: Model Output Is Not Authority
Cover image for AAEF v0.2.0: Model Output Is Not Authority

AAEF v0.2.0: Model Output Is Not Authority

Comments
5 min read
Confident and Wrong: We Tested 17 AI Models on Questions a Middle Schooler Could Answer

Confident and Wrong: We Tested 17 AI Models on Questions a Middle Schooler Could Answer

Comments 1
5 min read
Fixing Qwen 3.6 4090 llama.cpp Bug: 18 tok/s on My RTX 4090

Fixing Qwen 3.6 4090 llama.cpp Bug: 18 tok/s on My RTX 4090

Comments
8 min read
The right of an AI agent to stay silent
Cover image for The right of an AI agent to stay silent

The right of an AI agent to stay silent

Comments
8 min read
What 16 Parallel Claude Agents Built Around Themselves: Deconstructing Anthropic's C Compiler Experiment
Cover image for What 16 Parallel Claude Agents Built Around Themselves: Deconstructing Anthropic's C Compiler Experiment

What 16 Parallel Claude Agents Built Around Themselves: Deconstructing Anthropic's C Compiler Experiment

Comments
12 min read
One Open Source Project a Day (No. 48): karpathy/autoresearch —— Launching the Era of Self-Evolving AI Laboratories
Cover image for One Open Source Project a Day (No. 48): karpathy/autoresearch —— Launching the Era of Self-Evolving AI Laboratories

One Open Source Project a Day (No. 48): karpathy/autoresearch —— Launching the Era of Self-Evolving AI Laboratories

Comments
4 min read
Mamba vs. Transformers: Architecture Comparison

Mamba vs. Transformers: Architecture Comparison

1
Comments
5 min read
Why LLM Agents Fail: Four Mechanisms of Cognitive Decay and the Reasoning Harness Layer

Why LLM Agents Fail: Four Mechanisms of Cognitive Decay and the Reasoning Harness Layer

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