Viewing profile — alanfuNZ
alanfuNZ
HN member- Joined
- Sun, Oct 27, 2024, 4:46 AM UTC
- HN karma
- 2
- Public activity
- 7 items
- HN profile
- View on Hacker News ↗
About alanfuNZ
No profile information was provided.
Recent public activity
-
comment
Comment #49562359
Agree on the sandbox side. dagger or a microVM is the right blast-radius layer, and moving creds out of the environment entirely (service accounts, WIF, an egress proxy that inject…
-
story
Ask HN: How do you gate an autonomous coding agent's shell access?
I've been giving coding agents more autonomy lately, letting them run shell commands unattended for longer stretches, and I don't have a good answer for how people actually gate th…
-
comment
Comment #49371239
This only works in the case of working with databases, also a lot of the times people are not careful with the permissions that are given to these agents and they oftentimes touch …
-
comment
Comment #49338396
Also the intro of the readme was written by me, the rest was meant to just be something agents ingest and use to set up Doberman hahaha, didn't think anyone would read the full thi…
-
comment
Comment #49338388
Most of the other frameworks sit on the network peremiter and only inspects the prompts. The biggest competition right now that I see in the same lane Cisco's Defenseclaw which foc…
-
story
Show HN: Doberman: The AI watchdog that stops Claude from deleting your database
Landing Page: https://www.trydoberman.dev/ The Problem: AI guardrails only protect against 89% of dangerous commands. This may seem pretty good until you think of it as a lock that…
- story