engblogs

Predicting gene expression using AI and the Enformer architecture to improve understanding of genetic instructions and their influence on human health and development.

Using AI to predict gene expression and uncovering the instructions within non-coding DNA sequences.

Advancements in nowcasting the next hour of rain using state-of-the-art generative models and machine learning.

This blogpost discusses the research and advancement in Precipitation Nowcasting, specifically focusing on predicting rain within the next 1-2 hours using a state-of-the-art model and AI technology.

Transforming book summaries with human input for enhanced comprehension

Exploring the utility of emergent behaviors from curious exploration and the potential for skill retention in unsupervised reinforcement learning

Exploring the evolution of service architecture at SoundCloud with a focus on domain gateways.

The blogpost explores the importance of retaining emergent behaviors from curious exploration in maximizing the potential and usefulness of curiosity-based learning techniques.

Challenges in Detoxifying Language Models: This blogpost discusses the challenges in mitigating toxic language generation in language models and highlights the unintended consequences of detoxification.

Exploring methods to mitigate toxicity in language models and evaluating their effectiveness and limitations using classifier-based automatic toxicity evaluation.

Exploring model accuracy in replicating human misconceptions through TruthfulQA

Announcement of Helen Toner's inclusion in OpenAI's board of directors.