Google's NotebookLM now runs its own cloud computer with code execution and agent-based research
Quick Answer
Google's NotebookLM has been upgraded to run on Gemini 3.5 Flash, featuring its own cloud computer for code execution and autonomous source retrieval via Google Search.
Quick Take
In internal tests, this new system outperformed its predecessor 78.2% of the time, significantly enhancing research capabilities.
Key Points
- NotebookLM now utilizes Gemini 3.5 Flash for enhanced performance.
- The tool features a dedicated cloud computer for executing code.
- It can autonomously find sources using Google Search.
- Internal tests show a 78.2% improvement over the previous version.
Source Excerpt
Google is giving NotebookLM a major upgrade. The research tool now runs on Gemini 3. 5 Flash, has its own cloud computer for code execution, and can find sources on its own via Google Search. In internal tests, the new system beat the previous version up to 78. 2 percent of the time.
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from The Decoder
See more →
An AI model programmed nonstop for 19 days on a single MirrorCode task that cost $2,600 to run
Epoch AI's MirrorCode benchmark reveals Claude Opus 4.7 as the leader with a 56% solve rate, reconstructing a 16,000-line toolkit in 14 hours. Despite this, all models tested struggle with the most complex tasks, highlighting limitations in current AI capabilities. The single task consumed $2,600 over 19 days, raising questions about cost-effectiveness in AI development.
