The challenge [with RAG] is that most corner-cutting solutions look like they’re working on small datasets while letting you pretend that things like search relevance don’t matter, while in reality relevance significantly impacts quality of responses when you move beyond prototyping (whether they’re literally search relevance or are better tuned SQL queries to retrieve more appropriate rows). This creates a false expectation of how the prototype will translate into a production capability, with all the predictable consequences: underestimating timelines, poor production behavior/performance, etc.
Recent articles
- My Lethal Trifecta talk at the Bay Area AI Security Meetup - 9th August 2025
- The surprise deprecation of GPT-4o for ChatGPT consumers - 8th August 2025
- GPT-5: Key characteristics, pricing and model card - 7th August 2025