'Like gene editing for neural networks': MIT researchers used GPT-6 Astra to edit Qwen's open weights directly, boosting math performance

VentureBeatView source article

Part of story

MIT researchers demonstrate LLMs can directly edit neural network weights

MIT researchers showed that large language models can read, interpret, and modify neural network weights directly, with GPT-6 Astra raising a smaller model's math performance from 7.9% to 48.1% by editing approximately 0.016% of weights.

Nov 2, 20262 sourcesRecursive self-improvement Large language models (LLMs)AI capabilities AI Research OpenAI Interpretability AI Models Neural Networks Proximal Policy Optimization GPT-6 Astra

MIT researchers demonstrate LLMs can directly edit neural network weights

Other sources for this story

Analytics India Magazine

'Like gene editing for neural networks': MIT researchers used GPT-6 Astra to edit Qwen's open weights directly, boosting math performance

Part of story

MIT researchers demonstrate LLMs can directly edit neural network weights

Other sources for this story

MIT Researchers Show LLMs Can Read and Edit Neural Network

'Like gene editing for neural networks': MIT researchers used GPT-6 Astra to edit Qwen's open weights directly, boosting math performance

Part of story

MIT researchers demonstrate LLMs can directly edit neural network weights

Other sources for this story

MIT Researchers Show LLMs Can Read and Edit Neural Network