HackerTrans
TopNewTrendsCommentsPastAskShowJobs

softie123

7 karmajoined в прошлом месяце

Submissions

[untitled]

1 points·by softie123·4 дня назад·0 comments

Show HN: Shotlist – Make your AI agent prove its work with real screenshots

github.com
4 points·by softie123·18 дней назад·2 comments

Show HN: Pgsemantic – Point at your Postgres DB, get vector search instantly

github.com
3 points·by softie123·28 дней назад·0 comments

Show HN: A police department for your Claude Code agents

github.com
11 points·by softie123·в прошлом месяце·8 comments

Show HN: Agent-pd – A zero-token audit log to catch rogue Claude Code subagents

github.com
6 points·by softie123·в прошлом месяце·2 comments

comments

softie123
·18 дней назад·discuss
[flagged]
softie123
·в прошлом месяце·discuss
thats exactly what i went for. also I am keeping all the logs compressed so may be i can build something to build later
softie123
·в прошлом месяце·discuss
Idea is not to deny permissions to everything but just keep a log on what the agents are doing thats not in line with our permissions and also you have to know what they are bypassing so we can put them in deny list later. Very useful when you spawn many agents working in parallel. This is more of an observability tool.
softie123
·в прошлом месяце·discuss
[dead]
softie123
·в прошлом месяце·discuss
Tested this with 40 agents doing research at the same time it worked pretty good
softie123
·в прошлом месяце·discuss
[flagged]