Recipe ·

GPT-Rosalind

OpenAI developed GPT-Rosalind, a specialized large language model purpose-built for life sciences research with advanced biology knowledge and scientific reasoning capabilities.

Techniques inside

Median research → prod

1.7y

Fastest adoption

Slowest adoption

Ingredient list

#1Test-Time Compute Scaling
Invented by Google DeepMind · 2024-08 · Velocity 1.7y
“The model uses test-time compute scaling via multiple sampled reasoning paths and majority voting.”
reasoninghigh
#2Zero-Shot Chain-of-Thought
Invented by University of Tokyo · 2022-05 · Velocity 4y
“GPT-Rosalind can perform zero-shot chain-of-thought reasoning on biology tasks.”
reasoninghigh
#3Self-Consistency
Invented by Google · 2022-03 · Velocity 4y
“GPT-Rosalind uses self-consistency by sampling multiple reasoning paths and selecting the majority answer.”
reasoninghigh
#4Chain-of-Thought Prompting
Invented by Google · 2022-01 · Velocity 4y
“GPT-Rosalind uses chain-of-thought prompting to solve biology problems step-by-step.”
reasoninghigh

This recipe is part of the gentic.news Deployment Atlas. Every ingredient has an origin paper + evidence. Methodology is public. Dataset is CC BY 4.0.