NJL3000·2 か月前·議論Two points:-What remains unsolved is what should an Agent reasonably have access to in what context and for how long (etc).Probabilistic code that can run far faster than human driven code, we don’t have a great model yet. We all should spend our energy there…- Separating / putting controls on the FS resource is no different than putting the agent behind a firewall / allow-deny list.It doesn’t invalidate running a sandbox in a sandbox to have better security.
NJL3000·5 か月前·議論I was planning to have worktrees bind mounted systematically, but agree it’s not super clean atm at scale (yet)
NJL3000·5 か月前·議論A pair of containers felt a bit cheaper than a VM:https://github.com/5L-Labs/amp_in_a_boxI was going to add Gemini / OpenCode Kilo next.There is some upfront cost to define what endpoints to map inside, but it definitely adds a veneer of preventing the crazy…
NJL3000·7 か月前·議論This is a great idea of using a BERT model for DLP at the door. Have you thought integrating this into semantic router as an option leaving the look-ahead ? Maybe a smaller code base ?
NJL3000·11 か月前·議論It’s in the works… been meaning to do a show HN moment to see if it flies or I Fall on my face..
-What remains unsolved is what should an Agent reasonably have access to in what context and for how long (etc).
Probabilistic code that can run far faster than human driven code, we don’t have a great model yet. We all should spend our energy there…
- Separating / putting controls on the FS resource is no different than putting the agent behind a firewall / allow-deny list.
It doesn’t invalidate running a sandbox in a sandbox to have better security.