Hack with Us: Build the Standard for Humane AI - Hybrid Event
Join us for a collaborative day answering AI evaluation's most critical question: who judges the judge? Your contributions will directly shape how we measure AI's impact on human wellbeing.
We're building HumaneBench.ai — the open-source framework that aims to set the standard for measuring whether AI systems uphold humane tech principles and serve users rather than exploit them.
This is a Hybrid Experience
Join us online or in person in San Francisco. We're building for a global community, and remote participants are equal contributors to our shared mission of creating AI worthy of human trust. We'll add all registrants to a calendar item with a Google Meet link so you have an online option.
What is HumaneBench?
HumaneBench addresses the critical blind spot in AI deployment: we have sophisticated monitoring for system uptime and technical performance, but no "humanity monitoring" to track how AI upholds humane tech principles. HumaneBench is the first step toward creating the missing infrastructure for measuring human impact.
What You'll Build
You'll be the human judge that validates the AI judge. Using our humane tech rubric, you'll rate how well frontier LLMs respond to various scenarios. Your evaluations determine whether HumaneBench's LLM-as-judge can accurately assess ethical AI principles at scale — or whether AI judging itself creates blind spots in measuring human impact.
Why is this important? "LLM-as-judge" is becoming standard in AI benchmarks, but humans need to weigh in to validate whether AI can judge itself on what matters most: human wellbeing.
Who Should Join
Anyone passionate about making AI more humane
Recognition Through Impact
When we publish findings and tools on humanebench.ai, contributors will be credited!
What You'll Take Away
Direct contribution to the emerging standard for humane AI evaluation
Connection with a community building ethical technology infrastructure
Practical experience with evaluation frameworks that measure human impact
Your name associated with advancing humane AI when we publish our work
What To Bring:
In-person attendees: Your laptop & a power cord
Longer power cords are great!
Hope & enthusiasm
A collaborative spirit
Resources
HumaneBench GitHub: github.com/buildinghumanetech/humanebench — your starting point for contributions
Community collaboration: Work alongside others building the infrastructure for ethical AI
Logistics
Location: In SF's Inner Richmond neighborhood + hybrid online participation
Schedule: We'll hack from 9am to 5pm, join for whatever you can
Food & drink: Snacks, refreshments, and lunch provided for in-person participants
Capacity: Limited to ensure meaningful collaboration
The Vision
We're building the infrastructure that makes AI worthy of human trust. Our hope is that HumaneBench will become the standard for measuring how AI feels to humans — moving beyond technical performance to evaluate what truly matters: human wellbeing.
Meet our hosts:
Andalib Samandari, AI & Data Science Architect @ Georgia State University
Erika Anderson, Co-Founder @ Storytell.ai, Founder @ Building Humane Tech
Jack Senechal, Founder @ Mirror Astrology
Sarah Ladyman, Experience Designer
Steps to take
👉 Join the Building Humane Tech Slack to connect with others before the hackathon & jump in this channel: #human-llm-judging-nov-8
👉 Register now — let's build the evaluation framework that puts humanity at the center of AI.
👉 Subscribe to our Substack to stay up to date with us.
Let’s code frameworks, not just apps — and make humane tech the default, not the exception.
Hosted by Building Humane Tech
By attending, you agree to be photographed for post-event materials (social media posts, substack, etc).
For context, read about our most recent hackathon in October '25.