Harness Engineering(github.com)

52 points by handfuloflight 3 months ago | 22 comments

Harness2 by Google Research – Recursive Agent Harnessing(github.com)

54 points by irthomasthomas 7 days ago | 13 comments

GitHub repository for Harness2, an open-source recursive agent harnessing framework from Google Research, licensed Apache-2.0.

Show HN: Browser Harness – Gives LLM freedom to complete any browser task(github.com)

93 points by gregpr07 6 months ago | 45 comments

LoRA Speedrun – a public wall-clock leaderboard for fine-tuning techniques(github.com)

124 points by Vineeth147 3 months ago | 23 comments

Anthropic's open-source framework for AI-powered vulnerability discovery(github.com)

504 points by binyu 4 months ago | 140 comments

GitHub repository from Anthropic with Claude skills for threat modeling, scanning, triage, and patching, plus an autonomous vulnerability scanning harness.

Show HN: Macros with a Behringer FCB1010 MIDI Pedalboard in macOS(github.com)

80 points by fretlessjazz 1 month ago | 19 comments

Show HN: Raven – The harness of harnesses, built for RSI(github.com)

49 points by cyfyifanchen 27 days ago | 39 comments

GitHub repository for Raven by EverMind-AI, a self-evolving multi-agent ecosystem billed as a 'harness of harnesses' for recursive self-improvement.

Brex’s Prompt Engineering Guide(github.com)

467 points by appwiz 3 years ago | 88 comments

GitHub repository from Brex containing a guide with tips and tricks for working with large language models like OpenAI's GPT-4.

Startup CTO's Handbook(github.com)

346 points by mooreds 3 years ago | 105 comments

GitHub repository for The Startup CTO's Handbook, a book on leadership, management, and technical topics for leaders of software engineering teams.

Beej's Guide to Git(beej.us)

894 points by mixto 1 year ago | 280 comments

Landing page for Beej's Guide to Git, a free online guide to the Git version control system offered in HTML and other downloadable formats.

The new skill in AI is not prompting, it's context engineering(philschmid.de)

832 points by robotswantdata 1 year ago | 467 comments

Blog post by Philipp Schmid arguing that context engineering, supplying LLMs with the right information and tools, matters more than prompting for AI agents.

Why harnesses matter for energy (and token) efficiency(neuralwatt.com)

46 points by ccgibson 9 days ago | 23 comments

A Neuralwatt news post arguing that the design of AI agent harnesses affects the energy use and token consumption of LLM workloads.