97% of recent conference papers have replication issues; Gricea platform launches to fix it
DanielKhashabi · x · 2026-09-22
Recent conference papers on AI's impact reportedly show a 97% replication problem rate, undermining cumulative knowledge about AI's effects on humans.
Gricea, an open platform for conversational AI research, aims to address this:
- Visual flow builder with within/between-subject designs, randomization and branching
- Built-in LLM chat tasks with bias manipulation, RAG retrieval, streaming responses
- Granular event logging and interaction analytics for every message and click
- Versioned consent, masked replay, privacy-aware by design
- Public studies browseable and forkable as templates, open science by default
Related event: Johns Hopkins Open-Sources Gricea to Tackle AI Research Reproducibility(2 posts)→
More from Research
- Autonomous agent edits just 1,024 weights to lift Qwen3.5 0.8B from 7.4% to 37.4% on MATH-500 — VictorSanh · 2026-11-12
- Gait dataset labeled by encounter, spanning pre-op to 3 months post-TKA — zawthet · 2026-11-12
- Walking alignment measured 2.5-3.1° more neutral than X-ray, iPad gait study finds — zawthet · 2026-11-12
- MIT's Tegmark coins 'formal-washing': Signal protocol proof is far from complete — tegmark · 2026-11-12
- Signal formal verification hits 80%, Tegmark says Wired overstated completion — tegmark · 2026-11-12
- Category-theoretic framework asks: when does a physical system actually compute? — neurovium · 2026-11-12