AINewsnow

If this holds up, it is big: "We asked GPT-6 Astra to edit Qwen3.5-0.8B weights to improve math

This story is from 2026-11-02. It is preserved in the archive; the latest stories are on the live feed.

If this holds up, it is big: "We asked GPT-6 Astra to edit Qwen3.5-0.8B weights to improve math. It directly changed only 0.016% of weights, fixing 0.8B's reasoning loops & improving math up to 6x and even instruction following 3x, without gradients or training."

Read the full story at Ethan Mollick (X) ↗

Timeline · 1 report

  1. 2026-11-02 21:00 · Ethan Mollick (X)
    If this holds up, it is big: "We asked GPT-6 Astra to edit Qwen3.5-0.8B weights to improve math

More stories

  1. OpenAI to merge ChatGPT's Chat and Work tabs into a single desktop experience — TechCrunch AI
  2. OpenAI weighs rebranding data centers as 'compute campuses' amid growing public backlash — Techmeme
  3. MIT researchers use GPT-6 Astra to directly edit Qwen model weights, boosting math performance — Techmeme
  4. OpenAI signs four Abu Dhabi deals spanning energy, government and investment — Reuters AI
  5. Claude Code ecosystem expands with MCP security tools, sandboxing, and subscription reuse — DEV Community — AI
  6. OpenAI lowers funding target to $20 billion as investor caution grows — Financial Times AI
  7. Apple Intelligence to launch in China in December with Alibaba's Qwen model — SCMP China Tech
  8. AI chatbots weigh in on whether an AI bubble exists and when it might burst — Tom's Guide AI

Get the daily brief of stories like this at 6:30 every morning →