|
|
|
|
|
by bhaak
18 days ago
|
|
Who ensures it followed the specs? The more context an LLM gets, the more likely it will start to ignore instructions. If the LLM runs a context compression, all bets are off. There's a reason Anthropic upped the context to 1M tokens to reduce the chance of this from happening. |
|
The human. But only if you care about verification.