Prompt injection for long-context LLMs as an alternative to RAG?

[StevePlex (Steve King)]

ADDENDUM 2

Here’s a Q/A test with a white paper (~20k tokens) put in context via prompt injection vs RAG.. (content and settings were the same as much as possible. LLM = Gemini-1.5-Pro)..

ANALYSIS:

RAG is inconsistent.. sometimes finding answer, sometime missing.

---

Prompt inject success:

---

RAG fail:

---

RAG Request trace:

I did get RAG to answer questions from the file upload at the beginning of the document , and with coaxing , it may look at middle and end .. so it’s not a total fail.. but it is inconsistent… consistently , or more difficult to work with IMO : )