Skip to content

Forem

# llm

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

Cover image for Compilation for LLMs: Why a Language for Models Needs Native Code

delimitter

Apr 4

Compilation for LLMs: Why a Language for Models Needs Native Code

#rust #llm #programming #compiler

4 min read

Cover image for Why RAG Falls Short for Documentation Search (and What to Try Instead)

Alan West

Apr 4

Why RAG Falls Short for Documentation Search (and What to Try Instead)

#ai #rag #llm #python

5 min read

Mar 31

Show HN: Isartor – Pure-Rust prompt firewall, deflects 60-95% of LLM traffic

#showdev #llm #rust #security

1 min read

Cover image for Your Knowledge, Your Model — Part 2: Agents, Iatrogenics

Mar 31

Your Knowledge, Your Model — Part 2: Agents, Iatrogenics

#ai #architecture #agents #llm

4 min read

Rost

Mar 31

Remote Ollama access via Tailscale or WireGuard, no public ports

#hosting #selfhosting #llm #ollama

9 min read

Apr 4

The Tool Calling Problem: Why Most Agents Are Just Chatbots with Buttons

#ai #agents #llm #architecture

2 min read

Cover image for The Real Cost: Token Savings Calculator for Engineering Teams

delimitter

Apr 4

The Real Cost: Token Savings Calculator for Engineering Teams

#ai #programming #llm #computerscience

2 min read

Cover image for JIT vs Interpreters: Benchmarking LLM-Generated Code Execution

delimitter

Apr 4

JIT vs Interpreters: Benchmarking LLM-Generated Code Execution

#agents #llm #performance #python

3 min read

Cover image for Building Production-Ready Agentic AI Systems for Enterprise Software Delivery

Apr 4

Building Production-Ready Agentic AI Systems for Enterprise Software Delivery

#agents #ai #llm #softwareengineering

3 min read

Cover image for Hindley-Milner for LLMs: Type Inference Without Annotations

delimitter

Apr 4

Hindley-Milner for LLMs: Type Inference Without Annotations

#ai #computerscience #llm #programming

2 min read

instinctivelabs

Apr 4

Prompts Are Infrastructure. Here's What That Actually Means.

#ai #llm #productivity #programming

7 min read

Cover image for We built an LLM proxy that adds 47ms of latency. Here's every millisecond accounted for.

Apr 4

We built an LLM proxy that adds 47ms of latency. Here's every millisecond accounted for.

#ai #llm #architecture #backend

8 min read

Cover image for Claude Feels Slow. But Is Moving a Team to Open-Weight Models Actually the Fix?

Mar 30

Claude Feels Slow. But Is Moving a Team to Open-Weight Models Actually the Fix?

#ai #llm #opensource #performance

5 min read

Rinshad Kayilan Kajahussan

Mar 30

The Billion Dollar While Loop: Emergent Architecture in the Agentic AI Era

#ai #softwareengineering #architecture #llm

7 min read

Mar 31

Closing the knowledge gap with agent skills

#agents #ai #llm #softwareengineering

4 min read

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