NVIDIA Kumo Forecast Merges Pretrained Transformers with Historical Pattern Retrieval for Time-Series Predictions
NVIDIA's new time-series forecasting model combines a 340M-parameter Transformer encoder with retrieval-augmented patterns and built-in interpretability.
Goodfire researcher's neural network interpretability claim reshapes AI safety discourse
A 26,000-word blog post by Nick Cammarata arguing LLMs are more interpretable than assumed has triggered industry-wide debate on AI transparency and control.
Genomic AI Models Hit the Interpretability Wall
Foundation models trained on DNA sequences excel at prediction but fail at explanation, leaving biologists unable to understand why their forecasts work.