A new Python package called PoolParty streamlines the design of DNA sequence libraries for high-throughput biological ...

MIT CSAIL researchers say GPT-6 Astra edited 0.016% of Qwen3.5-0.8B weights to fix reasoning loops, lifting MATH-500 from 7.9% to 48.1% without training.

In the strongest example of "weight space programming", as the technique is called, Astra’s intervention raised Qwen3.5-0.8B’s MATH-500 score from 7.9% to 48.1% while touching approximately 0.016% of ...

MIT CSAIL's "weight-space programming" has a frontier LLM read and edit neural network weights directly, with no gradient descent. Surgical edits ended Qwen's reasoning loops, but the results come ...

GPU Taskman (gputaskman) is an MIT-licensed terminal tool that shows per-process VRAM and LLM KV-cache use on Windows, Linux ...

The MIT CSAIL team has proposed a "weight-space programming" method that enables GPT-6 Astra to directly read and modify ...

"Please improve an AI that is bad at math without additional training."When asked this, we usually think of adding training ...

"To improve an AI model's intelligence, you have no choice but to prepare massive amounts of data and GPUs, and run ...

An 18-year-old secondary vocational school student has dedicated 7 months to developing MindForge, a groundbreaking ...

Article by Shenchao TechFlowNo training required, no data needed, no gradient descent.Researchers at MIT fed the weights of ...

GPT-6 Astra was used by MIT researchers to edit a small part of Alibaba’s Qwen model, improving maths scores without ...

What happens when one AI tries to fix another? MIT researchers used OpenAI's GPT-6 Astra to modify Alibaba's Qwen AI model directly, boosting its maths scores without retraining it.