Viewing profile — lhad89
lhad89
HN member- Joined
- Tue, Jan 26, 2021, 11:08 AM UTC
- HN karma
- 8
- Public activity
- 2 items
- HN profile
- View on Hacker News ↗
About lhad89
No profile information was provided.
Recent public activity
-
comment
Comment #49692996
Isn't it? Being told to write files and finding a file write tool is very different to being told to play chess and finding a tool to cheat at (ie. not play) chess.
-
comment
Comment #49688253
No? It's not reasonable to expect every conceivable negative behaviour be enumerated in a prompt. Your example, if a model failed on it, would be a more obviously misaligned case, …