Dave Willner

CoPE-B-S1 is the next step. It's open-weight under Apache 2.0, so you can self-host it and keep your users' content on your own infrastructure, and it uses Jev's JSON spec, so it's a drop-in swap. Model card and weights: huggingface.co/zentropi-ai/... Go build with it!

zentropi-ai/cope-b-s1 · Hugging Face huggingface.co

We just released a Zentropi skill that lets your AI agent build its own content classifiers. You describe what you want to catch, it writes the initial policy, benchmarks it on real samples, and ships a working labeler - accurate, cheap, and fast! Install it at github.com/zent…

GitHub - zentropi-ai/skills: Agent skills powered by the Zentropi content classification engine github.com

@samidh.bsky.social and I are releasing CoPE-B today, the next version of our policy-adaptive content classifier. It delivers at-or-better-than-frontier classification while being self-hostable, faster, and cheaper to run. Full writeup with benchmarks at blog.zentropi.ai/meet-…

Meet CoPE-B: Frontier-Quality Content Classification You Can Self-Host blog.zentropi.ai

We're shipping CoPE-B-S1, an open-weight decision model tuned for safety use cases. It's a significant step forward for our CoPE family of models in a few ways. A thread: blog.zentropi.ai/meet-cope-b-...

Meet CoPE-B-S1: A Decision Model Tuned for Safety blog.zentropi.ai

At TrustCon this year I talked about a technique we’ve developed for automatically optimizing content-moderation policies, using an inversion of the binocular labeling approach Zentropi had already pioneered. Today we're shipping the tool that technique became. blog.zentropi.a…

Optimizing our Policy Optimizers blog.zentropi.ai

Over the weekend Zentropi turned two! To celebrate, we decided to give a present to the T&S community - 2 trillion free tokens of CoPE-B-S1, our policy-steerable decision model The model is hosted by Parasail, with zero data retention. Details + how to get started: blog.zentro…

Our Birthday Present to the Trust & Safety Community blog.zentropi.ai

Tomorrow at 9:30 AM PST, @samidh.bsky.social is walking through how we think about decision models for safety - what it takes for a model to apply a written policy well and how that differs from general-purpose decision models. There's still time to register: www.eventbrite.co…

Decision Models for Safety eventbrite.com

Making impossible safety challenges tractable is a lot of why we built Zentropi. Today @vaishnavi.bsky.social shipped a great example of what that means in practice - a set of open-source self-harm and suicide policies for teens: quire.substack.com/p/what-it-takes-for-llms-to-…

[What it Takes] For LLMs to Make Age-Appropriate Content Policies Enforceable quire.substack.com