SAN FRANCISCO, September 17 — Baseten launched a new safety infrastructure standard on Wednesday through its Base Labs research arm, partnering with Hugging Face and Goodfire AI to build safety evaluation and monitoring tools for open-weight AI models. The announcement, reported by Aditya Mehta at 10:15 AM PDT, arrives as the debate over open-weight model safety intensifies. The core problem is abliteration — a rising technique that strips safeguards from open models, making them potentially dangerous.
The scale is striking: Hugging Face, which hosts open source AI models, currently lists over 6,000 abliterated models.
What Baseten Is Building
Base Labs, the research group Baseten spun up earlier this year, will develop and publish methods for training and monitoring open models. The company frames its future work as a “standard” for open models — one that is transparent and built into how models are trained and deployed, rather than bolted on afterward. Think of it like seatbelts.
You can install them at the factory, or you can hope someone bolts them in later. Baseten is betting on the factory.
“We believe openness to be an advantage for AI safety,” the company said on X. “Openness provides more visibility into the behavior of models and, most importantly, greater means of turning safety research into actionable and transparent controls than closed-source.” The companies have not disclosed how the partnership will work technically. Goodfire framed the goal in a reply to Baseten’s post: “Safety must be built into open models and provided by those who serve them.” Goodfire specializes in opening AI’s “black box” to explain how models make decisions.
The Money Behind the Push
Baseten, an AI inference provider, raised a $1.5 billion Series F in June, vaulting its valuation to $13 billion. Goodfire AI is similarly well-capitalized, having raised a $150 million Series B led by B Capital earlier this year to advance its model interpretability platform. Baseten is putting out an open call to the broader developer ecosystem to contribute to the framework.
“Together, we are building an ecosystem of open models that are safe and accessible to all,” the company noted. The practical upshot for developers and companies deploying open models: a shared safety standard could eventually mean clearer expectations for what “safe” means — and tools to verify it.
For now, the technical details remain under wraps. Watch for Base Labs’ first published methods and how the developer community responds to the open call.
