miniblog.

← Back to all posts
Dec 28, 2020 at 03:18
Training a public machine learning model on private data can leak the original training data:
Privacy Considerations in Large Language Models
Privacy Considerations in Large Language Models
Posted by Nicholas Carlini, Research Scientist, Google Research Machine learning-based language models trained to predict the next word in a senten...

Related Posts

Dec 18, 2025 at 18:11
64
I find it odd that people recommend Docker for sandboxing agentic coding tools. Isn't it easier to just create a separate user account on the machine? It's an established security boundary, and viewing output is easy (just make the user's home directory world readable).
Aug 22, 2025 at 21:00
910
GNU Make defaults to a single worker, and newer build tools (e.g. ninja) default to the number of physical CPUs. I wish there was an option for 'leave me a little bit of my machine to do stuff'.
Jul 28, 2025 at 09:59
Make defaults to a single worker, and newer build tools (e.g. ninja) default to the number of physical CPUs. I wish there was an option for 'leave me a little bit of my machine to do stuff'.