Viewing profile — jensbontinck
jensbontinck
HN member- Joined
- Thu, Mar 05, 2026, 3:43 PM UTC
- HN karma
- 2
- Public activity
- 10 items
- HN profile
- View on Hacker News ↗
About jensbontinck
Recent public activity
-
comment
Comment #47272587
[dead]
-
comment
Comment #47272567
[dead]
-
comment
Comment #47272474
[dead]
- story
-
comment
Comment #47265880
[dead]
-
comment
Comment #47265328
This is why governance has to be external to the model. If you ask the model "are you sandboxed?" it will confabulate an answer. If you rely on the model to self-enforce safety rul…
-
comment
Comment #47265310
Yes, but most are doing it wrong. The common approaches I've seen: 1. Policy-only ("don't paste sensitive data into ChatGPT") — doesn't work, people do it anyway 2. Network-level b…
-
comment
Comment #47263823
This is a solid draft. glad to see it building on SPIFFE/WIMSE and OAuth rather than inventing new identity primitives. The "agents are workloads" framing in Section 3 is exactly r…
-
comment
Comment #47263727
A few patterns we've found effective deploying agents to production: 1. Proxy-based governance. Route all LLM traffic through a governance layer. The agent never holds API keys dir…
-
comment
Comment #47263247
This is exactly right. We went down this path and the practical implementation ends up looking like capability tokens. short-lived, cryptographically signed credentials that encode…