DEV Community

Ian L. Paterson profile picture

Ian L. Paterson

Public company CEO running LLMs as primary dev environment. 200+ memory lessons, 10 topic files, overnight agent orchestration. Cybersecurity by day, AI automation by night. www.ianlpaterson.com

Joined Joined on  Personal website https://www.ianlpaterson.com
Building llama.cpp from source on a Dell Precision T5820 with an RTX 3090 Ti (after seven power cycles)
ianlpaterson profile

Building llama.cpp from source on a Dell Precision T5820 with an RTX 3090 Ti (after seven power cycles)

#ai #llm #gpu #linux
Comments
16 min read

Want to connect with Ian L. Paterson?

Create an account to connect with Ian L. Paterson. You can also sign in below to proceed if you already have an account.

Create Account
Already have an account? Sign in
Anti-detect browser benchmark 2026: 7 stealth tools, 31 Cloudflare targets, 651 verdicts
ianlpaterson profile

Anti-detect browser benchmark 2026: 7 stealth tools, 31 Cloudflare targets, 651 verdicts

#webdev #python #security #programming
Comments
16 min read
Three Months of Speed-Up Experiments on a 3090 Ti: Autoregressive DFlash MTP for Qwen3.6-27B
ianlpaterson profile

Three Months of Speed-Up Experiments on a 3090 Ti: Autoregressive DFlash MTP for Qwen3.6-27B

#ai #llm #gpu #performance
Comments
18 min read
LLM Benchmark Rankings 2026: 15 Models Tested on 38 Real Coding Tasks
ianlpaterson profile

LLM Benchmark Rankings 2026: 15 Models Tested on 38 Real Coding Tasks

#ai #llm #programming #benchmarking
Comments
28 min read
Inference Arbitrage: How I Route 200+ Daily LLM Calls Across Five Models
ianlpaterson profile

Inference Arbitrage: How I Route 200+ Daily LLM Calls Across Five Models

#ai #llm #devops #python
Comments
10 min read
Stop Claude Code from Lobotomizing Itself Mid-Task
ianlpaterson profile

Stop Claude Code from Lobotomizing Itself Mid-Task

#ai #claudecode #productivity #programming
Comments
7 min read
The LLM Kept Saying “Fixed.” For Three Months, It Wasn’t.
ianlpaterson profile

The LLM Kept Saying “Fixed.” For Three Months, It Wasn’t.

#ai #llm #testing #programming
Comments
7 min read
How I Track Claude, Codex, and Gemini Quotas from One Script
ianlpaterson profile

How I Track Claude, Codex, and Gemini Quotas from One Script

#ai #llm #productivity #bash
Comments
6 min read
OpenClaw: 13 Errors, $1.50/Month, and an AI Team That Doesn’t Need the Cloud
ianlpaterson profile

OpenClaw: 13 Errors, $1.50/Month, and an AI Team That Doesn’t Need the Cloud

#applesilicon #lmstudio #localllm #openclaw
Comments 2
15 min read
loading...