开源工具
x.com ·
@Thom_Wolf
Hugging Face 的 Thomas Wolf 宣布与 Baseten、GoodfireAI 合作推进开放模型安全与可解释性
Thomas Wolf 表示已开始与 Baseten 旗下 baselabs 及 GoodfireAI 合作，推动开放模型的安全与可解释性研究，认为随着开源模型性能逼近前沿模型，社区有机会建立有效的安全、安保与可解释性研究共同实践。他强调“开放”不等于“无监控”，开放模型反而为更广泛受众提供更多安全研究工具与可见性，并以 Linux 的安全反馈循环为例。被引帖称将在 Baseten 推理基础设施中内置安全研究，包括训练模型遵循明确策略、运行时检测故障并连接可干预的控制手段，目标是向所有客户提供。目前为合作与方向声明，尚无具体成果披露。
AI推荐理由 Hugging Face 的 Thomas Wolf 宣布与 Baseten 旗下 baselabs 及 GoodfireAI 合作，推进开放模型的安全与可解释性研究，主张“开放”不等于“无监控”，并以 Linux 的安全反馈循环作类比。被引帖进一步说明将在 Baseten 推理基础设施中内置策略遵循训练、运行时故障检测与干预控制。属于合作意向与方向性声明，尚无具体成果或数据，需保留其未落地的不确定性。
68
浏览 3,803
点赞 37
评论 2
转发 2
正文
Happy to start collaborating with [@baselabs](https://x.com/baselabs) from [@baseten](https://x.com/baseten) and [@GoodfireAI](https://x.com/GoodfireAI) to push safety and interpretability for open models.
As open-source models catch up in performance to frontier models, the community at large have a great opportunity to establish a common practice for effective safety, security and interpretability research.
Some past discussions confused “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 a lot 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.
We're excited to share more soon.
Charlie O'Neill@oneill\_c
Safety is not just for closed models. The closed frontier labs are a canary in the coal mine for what is coming at scale. They give us a glimpse into the future and a window to harden our systems and prepare for abundant intelligence, with all the risks that come along with it. The OpenAI agent swarm attack on Hugging Face is the kind of failure we need to prepare for as open-source models catch up. The providers serving those models (such as Baseten) have a big role in establishing what safety and monitoring standards look like.
We’re proud to be taking the lead on this at [@baselabs](https://x.com/baselabs) with our collaborators [@huggingface](https://x.com/huggingface) and [@GoodfireAI](https://x.com/GoodfireAI). We’re developing safety research in the open and building it directly into Baseten’s inference infrastructure, with the aim of making it available to all our customers. This includes training models to follow explicit policies, detecting failures at runtime, and connecting those signals to controls that can intervene.
We invite others in the open-source ecosystem to join us in building the tools and standards we’ll all need.
[🔗 View Quoted Tweet](https://x.com/oneill_c/status/2100286474637996373)