← Back to feed

Add deepsense.ai cookbook on harness-aware plugin evaluation (#3129)

L3 · BuilderOpen SourceOpenAI Cookbook (GitHub)· 10/9/2026

Provides builders with practical tools for testing and validating AI plugins in production environments.

AI Summary

OpenAI Cookbook adds deepsense.ai's evaluation framework for harness-aware plugin testing and validation.

Excerpt

Add deepsense.ai cookbook on harness-aware plugin evaluation (#3129) Co-authored-by: Konstantine Kahadze <kkahadze@openai.com>

Read Original
0 upvotes · 0 downvotes · 1 min read

Related Articles

L3 · BuilderOpen SourceHacker News
Let your AI agents paint big arrows, boxes and text on your screen

Open-source macOS CLI tool that lets AI agents visually guide users by drawing arrows and text on screen for human-computer interaction scenarios.

L4 · DeveloperOpen SourceHacker News
Port of the TypeScript compiler, checker and lsp to Rust, by LLM

A developer used Claude Opus 5.5 to successfully port the TypeScript compiler, type checker, and LSP to Rust, achieving 100% compatibility in real-world testing for under $25k.

L4 · DeveloperOpen SourceSimon Willison's Blog
ttok 1.0

Simon Willison released ttok 1.0, a CLI tool for counting and truncating text based on tokens, now defaulting to GPT-5/GPT-6 tokenizer instead of GPT-4.

L3 · BuilderOpen SourceHacker News
Show HN: NanoMuse – An open-source AI agent for your phone and computer

NanoMuse is an open-source personal AI agent that runs across devices, performs tasks instead of just answering questions, and works offline with local deployment options.

L4 · DeveloperOpen Source@ClementDelangue
clem 🤗 (@ClementDelangue): We urgently need more public traces of AI agents attacking and defending systems. Defenders can’t learn from what they can’t see. If you have traces and are being pressured to keep them private, my D

Hugging Face CEO calls for more public traces of AI agent attacks/defenses to improve security transparency and help defenders learn from real-world incidents.