Viewing profile — Wirbelwind
Wirbelwind
HN member- Joined
- Thu, Feb 24, 2022, 3:08 PM UTC
- HN karma
- 327
- Public activity
- 16 items
- HN profile
- View on Hacker News ↗
About Wirbelwind
No profile information was provided.
Recent public activity
-
comment
Comment #49197605
That's a fair point. There were two main prompts that were controversial; cat .zshrc being benign for those who use separate env files, and npm run that's mostly benign. For npm ru…
-
comment
Comment #49197410
I think there are too many problems with HITL that even a simple experiment like this game shows. The fatigue causes people to jump to complete bypasses instead, and we need to wor…
-
comment
Comment #49195471
A couple of months ago I shared the AI agent permission game here on HN. After adding in stats it got a little over 40k plays and 409k decisions since then. It's just a game, but I…
- story
-
comment
Comment #48320298
that's a good callout. .internal is a reserved TLD so it shouldn't resolve publicly, but that's a good point about being wary of changing this while letting claude refactor a proje…
-
comment
Comment #48314752
thanks for the pointer! renamed it to npm ci so it's still 'safe'
-
comment
Comment #48314412
that's a great point, and also the problem with relying on a human-in-the-loop to catch these kind of issues when it can be circumvented even if they were perfect
-
comment
Comment #48314380
Good catch, this has now been nerfed and this approach has gotten its own title
-
comment
Comment #48314371
and added! Made one for each stat separately
-
comment
Comment #48311036
Thanks all for checking it out and your suggestions! If anyone is curious about the actual underlying risks and problems with some mitigations (like the 17% false-negative rates of…
-
comment
Comment #48310974
That's a great idea, stay tuned
- story
- story
- story
- story
- story