Notifications
Clear all
Topic starter
06/06/2026 2:27 am
TL;DR: At HumanX 2026, Fireworks AI’s Rob Ferguson argued that open models are closing the performance gap with frontier systems while enterprise data remains the real competitive moat, with model ownership becoming more valuable as scale and cost pressures rise, according to WorkOS. The strategic question is no longer whether open models can compete, but whether organisations can govern the data and identity access behind them.
NHIMG editorial — based on content published by WorkOS: Rob Ferguson on Fireworks AI at HumanX 2026
Questions worth separating out
Q: How should security teams govern access to AI training data?
A: Security teams should treat AI training data as a privileged asset and apply least privilege, ownership, and review cycles to every identity that can read, export, or transform it.
Q: Why does enterprise data matter more than model architecture for AI strategy?
A: Enterprise data matters because general model capabilities are converging, while proprietary data remains the durable source of differentiation.
Q: What breaks when AI model ownership is separated from access governance?
A: Model ownership becomes superficial when the organisation cannot control who can feed, change, or exfiltrate the data behind the model.
Practitioner guidance
- Inventory every AI training data path Map each source that feeds model training or fine-tuning, including code repositories, document stores, and application data.
- Restrict privileged access to model weights and pipelines Limit who can download weights, modify training jobs, or change evaluation datasets.
- Apply lifecycle governance to AI development roles Review joiner, mover, and leaver controls for engineers, data scientists, and platform identities that touch AI systems.
What's in the full article
WorkOS's full article covers the operational detail this post intentionally leaves for the source:
- Interview context from HumanX 2026, including the questions and discussion flow with Rob Ferguson.
- The full progression of examples used to compare closed-source, open-weight, and enterprise-owned model strategies.
- More detail on the reasoning behind owning weights and how the speaker frames data-rich environments.
- The article's broader commentary on government structures, copyright, and labour mobility as model-development forces.
👉 Read WorkOS's interview on open models, AI ownership, and the data moat →
Open models and data moats: what it means for AI teams?
Explore further
06/06/2026 4:07 am
Open-model adoption turns data governance into identity governance. Once an enterprise uses its own data to specialise a model, the access problem is no longer abstract. The value now sits in systems that hold proprietary data, code, and weights, so identity controls determine whether that value stays bounded or becomes broadly reachable. Security leaders should read this as a governance shift, not a tooling trend.
A few things that frame the scale:
- The average estimated time to remediate a leaked secret is 27 days, despite 75% of organisations expressing strong confidence in their secrets management capabilities, according to The State of Secrets in AppSec.
- Our research also found that organisations maintain an average of 6 distinct secrets manager instances, creating fragmentation that undermines centralised control.
A question worth separating out:
Q: How can organisations know if their AI data moat is actually protected?
A: They should test whether the most valuable datasets are reachable only by the identities that genuinely need them, and whether those entitlements are reviewed when roles change. If many users, services, or vendors can reach the same data without clear purpose, the moat is already weakened. Governance must be measurable, not assumed.
👉 Read our full editorial: Open models are narrowing the AI gap, but data remains the moat
