Subject
18 entries
Automation
Bookmarks
Autoresearch Skill: autonomous skill optimization via eval loops
A Claude Code skill that autonomously optimizes other skills by running eval loops — binary scoring, targeted mutation, keep/discard decisions. Andrej Karpathy's training loop methodology applied to prompt engineering.
Zo: personal AI cloud computer for 24/7 execution
Zo is a personal AI cloud computer that runs autonomously 24/7 — manages email, books meetings, builds apps, handles files — via natural language text instructions. A personal cloud computer with full file access and multi-model AI.
I Built 6 AI Employees in 10 Minutes
A YouTube video demonstrating building 6 autonomous AI agents ('employees') in 10 minutes that run 24/7 without human intervention. Likely covers no-code or low-code agent orchestration tools and common automation patterns.
iauto: Low-Code LLM + RPA Automation Engine
iauto is a low-code automation engine that combines LLMs with RPA tools (Appium, Playwright) in YAML-defined workflows. Bridges AI reasoning with traditional robotic process automation for adaptive task execution.
Mazzle: Pipelines as Code for DevOps
Mazzle is a pipelines-as-code tool for building large, complicated, consistent environments — define infrastructure and build pipelines declaratively, run them as a server. An early-generation IaC-adjacent tool predating Terraform's dominance.
Lead Overload: AI Outbound Sales Calls
Lead Overload automates outbound sales calls using AI — an AI voice agent that makes sales calls at scale, qualifying leads and booking meetings without human SDRs. Part of the wave of AI-first sales automation tools that emerged in 2023.
Numbers Station: AI-Powered Data Stack Automation
Numbers Station is an AI co-pilot for data workers that automates data-intensive workflows — transformations, SQL generation, pipeline building — without requiring Python or engineering involvement. Targets the gap between BI tools and data engineering.
Automatic Prompt Engineer (APE)
Automatic Prompt Engineer (APE) is a research implementation that automatically generates and selects optimal prompts for LLMs using a generate-then-score approach. An early automated prompt optimization method predating DSPy.
SOANM — Shell Of A New Machine
SOANM (Shell Of A New Machine) is a minimal shell script for quickly configuring new environments — bootstrapping dotfiles and core tooling without a heavy framework. The anti-Ansible approach to machine setup.
Large Language Models Are Human-Level Prompt Engineers
Large Language Models Are Human-Level Prompt Engineers (APE) introduces an automated method for generating and selecting optimal prompts using LLMs themselves, matching or beating human-crafted instructions on 19 of 24 NLP tasks. It reframes prompt engineering as a program search problem, making manual iteration unnecessary.
My Smart Home 2021
A detailed writeup of a production Home Assistant smart home setup in 2021 — covering hardware choices, integrations, automations, and lessons learned. A useful reference for anyone building a serious self-hosted home automation system.
Kibitzr: Self-Hosted Web Page Monitoring
Kibitzr is a self-hosted web monitoring and notification tool — watch pages for changes, parse content with CSS/XPath, run bash/Python transforms, and route alerts to Slack or email. Configured in YAML and deployable on minimal hardware.
Sommelier Finance — Automated DeFi Strategy Platform
Sommelier Finance is a DeFi protocol that uses off-chain computation (Cosmos-based co-processor) to automate Uniswap v3 liquidity position management — rebalancing concentrated liquidity ranges without requiring constant manual intervention.
ThetaGang: Options Premium Collection Bot
ThetaGang is an open-source Python bot for Interactive Brokers that automates theta-positive options strategies — selling covered calls and cash-secured puts to collect premium. Designed for passive income from options rather than directional trading.
LazyPredict: Fit All scikit-learn Models in One Line
LazyPredict fits and evaluates all scikit-learn classifiers or regressors on a dataset with a single call, returning a sorted comparison table. A fast baseline scanner for figuring out which model family is worth investing in before tuning.
Automated Science, Deep Data, and the Paradox of Information
Oscillatory Thoughts blog post on the paradox of automated science and deep data — arguing that as data volumes grow and pattern detection automates, we risk producing empirical findings we can't explain or falsify. A philosophical challenge to data-driven science.
Who Needs Photographers When You Have Robots?
NPR's 2012 piece on robotic camera systems deployed at the London Olympics, capable of shots no human photographer could position for. An early concrete case of automation entering creative/journalistic work at a professional level.
Bitponics: Automated Gardening for Brown-Thumbed Plant Killers
Bitponics was an Arduino-based automated gardening system that monitored pH, temperature, light, and humidity and sent alerts when plants needed attention. An early consumer IoT product applying sensor networks to home horticulture.