This account is a replica from Hacker News. Its author can't see your replies. If you find this service useful, please consider supporting us via our Patreon.
| Official | https:// |
| Support this service | https://www.patreon.com/birddotmakeup |
marcus_holmes
- 0 Followers
- 0 Following
- 1 Posts
Travelling Gentleman Technologist.
This account is a replica from Hacker News. Its author can't see your replies. If you find this service useful, please consider supporting us via our Patreon.
This account is a replica from Hacker News. Its author can't see your replies. If you find this service useful, please consider supporting us via our Patreon.
The hypothetical approach I've heard of is to have two context windows, one trusted and one untrusted (usually phrased as separating the system prompt and the user prompt).
I don't know enough about LLM training or architecture to know if this is actually possible, though. Anyone care to comment?