|
|
|
|
|
|
by crazyedgar
1142 days ago
|
|
|
This is my experience too. While I'd really love the Open Source models to catch up, currently they struggle even with dead-simple summarization tasks: they hallucinate too much, or omit essential points. ChatGPT don't often hallucinate when summarizing, only when answering questions. |
|
|