Viewing profile — webpolis
webpolis
HN member- Joined
- Mon, Oct 23, 2023, 3:09 PM UTC
- HN karma
- 0
- Public activity
- 22 items
- HN profile
- View on Hacker News ↗
About webpolis
No profile information was provided.
Recent public activity
-
comment
Comment #47411937
[dead]
-
comment
Comment #47411922
[dead]
-
comment
Comment #47373335
[dead]
-
comment
Comment #47369122
[dead]
-
comment
Comment #47367504
[dead]
-
comment
Comment #47355633
[dead]
-
comment
Comment #47349442
Loop detection is the harder problem and almost nobody solves it well at the infra layer. The pattern you're describing — write, fail, "fix," regress — is fundamentally a semantic …
-
comment
Comment #47348622
[dead]
-
comment
Comment #47345597
[dead]
-
comment
Comment #47339382
[dead]
-
comment
Comment #47339302
[dead]
-
comment
Comment #47339288
[dead]
-
comment
Comment #47337799
Browser plugins have a security problem that's easy to miss: the agent runs inside your existing browser profile. That means it has access to your active sessions, stored credentia…
-
comment
Comment #47335716
The hard part here isn't checkpointing the agent's conversation state — that's just a list. It's checkpointing the world state. If step 5 wrote rows to Postgres and step 7 called a…
-
comment
Comment #47335469
[dead]
-
comment
Comment #47329082
[dead]
-
comment
Comment #47326321
The keychain-per-agent model is the right instinct, but the threat model gets complicated fast. When five agents share a keychain process, a prompt injection in agent A can exfiltr…
-
story
Show HN: Cyqle – Multiplayer cloud desktops with AI agent sandboxing
Hey HN, I've been building Cyqle for a while — it's a shared cloud desktop you open in a browser tab and invite people into. Everyone gets their own cursor and keyboard. Think Goog…
-
comment
Comment #47316066
The macOS sandbox approach is clever, but there's an interesting philosophical split here: sandboxing constrains a local agent, whereas running agents in ephemeral cloud desktops r…
-
comment
Comment #47313818
[dead]
-
comment
Comment #44871531
As I started building agentic workflows, I found myself frequently creating, improving, and tweaking prompts by editing hardcoded strings and managing text files. I realized this p…
- story