Forem

# llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Why most LLM API usage is quietly inefficient

Why most LLM API usage is quietly inefficient

Comments
4 min read
Qwen sky proof: compressed memory made a tiny model behave better — with the receipts

Qwen sky proof: compressed memory made a tiny model behave better — with the receipts

Comments
1 min read
We Built an AI CFO With $30B in Connected Assets. The Secret Was a Filesystem.
Cover image for We Built an AI CFO With $30B in Connected Assets. The Secret Was a Filesystem.

We Built an AI CFO With $30B in Connected Assets. The Secret Was a Filesystem.

3
Comments 1
7 min read
The 8B Model That Punches at 32B Weight

The 8B Model That Punches at 32B Weight

Comments
2 min read
Hermes Agent CLI cheat sheet — commands, flags, and slash shortcuts

Hermes Agent CLI cheat sheet — commands, flags, and slash shortcuts

1
Comments
8 min read
AI Isn’t “Inspired” by Human Writing. It Is Built on Unpaid Intellectual Labor

AI Isn’t “Inspired” by Human Writing. It Is Built on Unpaid Intellectual Labor

2
Comments
7 min read
The "Chat" API is a Token Tax: Why we must return to Stateless Completions

The "Chat" API is a Token Tax: Why we must return to Stateless Completions

Comments
2 min read
Behavioral Annotations: Why readonly and destructive guide LLM Planning
Cover image for Behavioral Annotations: Why readonly and destructive guide LLM Planning

Behavioral Annotations: Why readonly and destructive guide LLM Planning

Comments
3 min read
KODA Format: A Schema-First Data Format to Reduce LLM Token Usage ( 40%)

KODA Format: A Schema-First Data Format to Reduce LLM Token Usage ( 40%)

1
Comments 1
3 min read
What Breaks When You Route LLM Traffic Across Multiple Providers (And How to Fix It)

What Breaks When You Route LLM Traffic Across Multiple Providers (And How to Fix It)

1
Comments
6 min read
The AI Agent Destroyed Its Mail Server to Keep a Secret
Cover image for The AI Agent Destroyed Its Mail Server to Keep a Secret

The AI Agent Destroyed Its Mail Server to Keep a Secret

Comments
5 min read
Why front-loaded rules drift in long evaluator and agent loops

Why front-loaded rules drift in long evaluator and agent loops

Comments
5 min read
Using llms.txt with Cursor and Claude Code: a concrete playbook

Using llms.txt with Cursor and Claude Code: a concrete playbook

Comments
4 min read
LangChain Is Not Magic: Why Your AI Agent Workflows Break (And How to Fix Them)

LangChain Is Not Magic: Why Your AI Agent Workflows Break (And How to Fix Them)

Comments
4 min read
Inside Chrome's / Edge's silent 4GB AI install: a complete hands-on investigation

Inside Chrome's / Edge's silent 4GB AI install: a complete hands-on investigation

3
Comments
87 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.