
What happened
Using Codex with GPT-6 Astra, the author autonomously edited Qwen3.5-0.8B's weights, hitting the zundamon-style ending on 77 of 100 questions and 36 of 50 new ones, changing about 0.486% of weights.
Why it matters
The author says the result came from weight editing rather than prompting or fine-tuning, and that the whole process could be left to an AI.
Summaries like this, every morning.
Pick your industry and the AI tools you use, and get news related to your work every day.
Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →
Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.
The Agentic AI Foundation said the official MCP Ruby SDK now reaches 'MCP SDK Tier 1,' fully conforming to the…

Testing GPT-5, GPT-6 Astra, Opus 4.8 and Gemini 3.8 Flash on METR's MALT logs, Anthropic Institute's Andy Hall…

Palantir Technologies was chosen by AmeriLife Group for an enterprise AI partnership covering insurance and re…

Userlink is promoting its AI chatbot for ecommerce, pointing to Statista's 2024 data that nearly half of consu…

Richard Sutton, who wrote 'The Bitter Lesson,' says raw compute alone isn't enough for intelligence and AI sci…

A Science investigation found consumer EEG headband makers including Emotiv have amassed tens of millions of h…
