[aimanbenbaha]

I don't think RAG will survive this time

[inertiatic]

4.8b words on English Wikipedia. Knowledge cutoff of 6 months. A valid use case is to search across Wikipedia and ground your answers. Trivially proves that RAG is still needed.

[drusepth]

RAG still has lots of benefits for anyone paying per input token (e.g. over APIs).

[azinman2]

Not to mention latency

[acchow]

This is only for the small model. The medium model is still at 1M (like Gemini 2.5)

Even if we could get the mid models to 10M, that's still a medium-sized repo at best. Repos size growth will also accelerate as LLMs generate more code. There's no way to catch up.

[gesman]

RAG gets bigger as everyone else gets bigger. Flooding prompts with garbage is not a sound strategy...