Comment by bob1029
3 hours ago
> Failures follow consistent patterns: agents let a plausible in-environment request override the standing policy
I prefer this behavior in a lot of situations. A plausible request can also be a genuine one.
Alignment at the grain of each tool response is way more effective than a static system prompt. I try to keep mine under 500 tokens. Why bother fighting recency bias? It's pretty much what you want most of the time.
No comments yet
Contribute on Hacker News ↗