Overview
News
Technologies
Salaries
Products
People
Growth
Financials
Overview
We are building a new class of interpretable AI systems and foundation models that humans can reliably debug, trust, and understand.
News
Introducing Clarity
Clarity is the first inherently interpretable AI platform, now available by invitation as a research preview.
Read more
Report
Alignment Without Retraining: Auditing and Controlling Steerling-8B
We show how Steerling-8B can suppress toxic and memorized content at inference time without finetuning, and trace model outputs directly to their training data sources.
Read more
Report
Discovering Human-understandable Concepts in Steerling-8B
We show how to extract novel and human-understandable concepts from the recently released Steerling-8B model.
Read more
Report
Steering Interpretable Language Models
We demonstrate reliable, fine-grained control over language model generation by directly injecting, suppressing, and composing human-interpretable concepts at inference time.
Read more
Report
Steerling-8B: The First Inherently Interpretable Language Model
We release Steerling-8B, an 8B-parameter causal diffusion language model that is interpretable by construction - its predictions are routed through concepts you can measure, audit, and control.
Read more
Report
Pro access
Upgrade to see all 6 mentions
Upgrade to a paid plan to read every media mention of this company - funding news, awards, product launches and press releases from all the outlets writing about it.
Every media mention and press release
Funding news, awards and product launches
Fresh coverage from every outlet writing about the company
Upgrade now
Cancel anytime. Secure checkout. Instant activation.