Parametric Hubris – Beating GPT-5 on SimpleQA with forced retrieval

Show HN: Parametric Hubris – Beating GPT-5 on SimpleQA with forced retrieval

Based, Parametric Hubris – Beating GPT-5 on SimpleQA with forced retrieval works in show hn launch.

Profile

Just finished reading "Parametric Hubris" by Martin Gehrken. It’s a fascinating deep dive into why frontier models hallucinate even when they have tools.The core thesis: Models suffer from "Parametric Hubris". They rely on their training data (lazy) instead of using search tools, even when browsing is enabled.Data: GPT-5 only triggers search in ~31% of prompts.The Fix: A pipeline called "Veritas" that forces 100% retrieval (no parametric memory allowed for answers).Results: Achieves 89.1% F-Score on SimpleQA Verified (vs 51.6% for GPT-5 and 72.1% for Gemini 3 Pro).Cost/Model: Built on Gemini 2.5 Flash Lite (cheapest model) for ~$0.002 per query.Trade-off: It’s slow (~115s per query), but acc

The company sits in the show hn launch segment, where it competes on its core product or service.

Its current recorded stage is Show HN launch.

Website: dev.thelastrag.de/veritas_benchmark