# Baseten — Safety Infrastructure for Open Models

- Company: Baseten (baseten.co)
- Announced: not stated by the source (first seen 2026-11-06T18:26:27.503180+00:00)
- Category: safety-policy-update
- Coverage: not counted
- Announcement: yes
- Group: announcements
- Source: https://www.baseten.co/blog/safety-infrastructure-for-open-models
- Record: https://forck.live/items/32768-safety-infrastructure-for-open-models
- Subject: Baseten

Baseten and Base Labs are building safety evaluation and monitoring infrastructure for the open models Baseten serves, connecting safety research directly to the systems that train and serve those models. The company says open models are often wrongly confused with unmonitored ones, and argues that open weights give a broader audience the tooling and visibility to find and fix vulnerabilities. The effort covers three areas: training models to follow explicit policies and ask for help when a task cannot be completed legitimately, monitoring inputs, outputs, tool use and internal model states and tying those signals to permissions, isolation and pre-execution checks, and investigating failures to improve training or controls. Base Labs will develop and publish methods for training and monitoring, while Baseten integrates that work into its deployment infrastructure at runtime and offers it as a managed service. Baseten says the published methods and evidence will be testable by customers and outside evaluators, and invites the open-source community to contribute to safety evaluation protocols.

## Evidence

Verbatim from https://www.baseten.co/blog/safety-infrastructure-for-open-models:

> While safety research has been prominent in the AI field for some time, it has become a forefront topic in mainstream discussion this past week. We're hearing much more about these concerns from our friends and families outside the field, largely due to a very public Anthropic safety researcher exit, raising eyes on Anthropic's security report, the OpenAI/Hugging Face security incident, and various other security and safety concerns. We take these safety issues very seriously, and we are glad to see that safety has gone broadly and globally mainstream.
> 
> Open-source models occupy a lot of this safety discussion, where a lot of past discussion unfortunately confuses “open” with “unmonitored”. On the contrary, an open model provides much more tooling and visibility for safety research from a broader audience, which has led to many of the safety and security techniques we use today. Linux is a great example of this: open-source and secure deployment are not only compatible but heavily intertwined, as a properly secure system needs an extensive feedback loop of finding and fixing vulnerabilities.

---

Record: https://forck.live/items/32768-safety-infrastructure-for-open-models
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md
