Skip to content

Forem

# llm

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

Apr 24

Building LLMs for Bharat: What 6 Months of Rural AI Deployment Taught Us

#ai #machinelearning #india #llm

4 min read

Cover image for GPU cloud servers for AI workloads: how to choose the right instance and deploy without waste

May 7

GPU cloud servers for AI workloads: how to choose the right instance and deploy without waste

#ai #cloud #infrastructure #llm

15 min read

soy

Apr 23

Qwen 3.6, llama.cpp Speculative Decoding, Deepseek TileKernels for Local AI on Consumer GPUs

#ai #llm #selfhosted

3 min read

Javier Castillo

Apr 23

I built a new file format to cut AI token costs by 70% — here's how it works

#ai #data #llm #performance

5 min read

Apr 24

Doby: How I Cut Claude Code's Navigation Tokens by 95% with a Spec-First Workflow

#architecture #claude #llm #productivity

1 min read

Francisco Ferreira

Apr 23

I evaluated the leaked system prompts of the biggest AI coding tools. Here's what I found.

#promptengineering #llm #ai #webdev

4 min read

Cover image for LocalForge: I built a self-hosted LLM control plane with intelligent routing and LoRA finetuning

Muhammad Ali Nasir

Apr 23

LocalForge: I built a self-hosted LLM control plane with intelligent routing and LoRA finetuning

#python #ai #llm #agents

2 min read

Apr 23

48 Hours After Publishing: Second-Order Injection Field Notes

#security #llm #ai #cybersecurity

2 min read

Apr 23

The Actual Cost of Self-Hosting Your LLM (Nobody Does This Math First)

#llm #ai #devops #sre

4 min read

Apr 23

A Minimal ~9M Parameter Transformer LLM Trained from Scratch

#challenge #ai #opensource #llm

2 min read

Cover image for LLM Observability tool

unni mana

Apr 25

LLM Observability tool

#showdev #java #llm #monitoring

1 min read

Cover image for AI Duel on Building Retro RPG Quest Journal

YASHWANTH REDDY K

Apr 23

AI Duel on Building Retro RPG Quest Journal

#vibecodearena #hackerearth #ai #llm

3 min read

Apr 23

Qwen3.6-Plus Benchmark: It Is Trying to Finish the Job, Not Just Win Chat Scores

#agents #ai #llm #performance

5 min read

Joel Alan

Apr 23

Context Compression and Persistent Memory Design for Terminal AI Assistants

#agents #ai #cli #llm

7 min read

David

Apr 23

qwen3.6-27b scores 77.2% on SWE-bench. the dense model is winning against MoE.

#ai #llm #opensource #coding

3 min read

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