This week was very hot because Google published Gemma, a smal-size LLM, and also Nvidia has a rush on stock market, with a evaluation around 2000 BILLIONS dollars. Last but not least, Mistral.ai published a service for its more advanced model, which can also run on-prem.

Read More

Generative artificial intelligence (GenAI) is artificial intelligence capable of generating text, images or other data using generative models, often in response to prompts.

Generative AI models learn the patterns and structure of their input training data and then generate new data that has similar characteristics. This similarity is probability-based.

At low level, these systems are based on Transformer deep-learning architecture and are called generative pre-trained transformer  (GPT) first defined in 2018 (for a complete description refer to Wikipedia)

Read More

Modern computer are very very very fast. C/64 was about 1Mhz and you can hangs it just throwing a 10.000 cycle in interpreted BASIC v2 language.

Read More

August throughts

Programming is like writing.

Code must be easy to read, and understand. For this reason I do not like very much technologies like:

Read More

I the last years I decided to put a stop on my RasperryPI2 and have a mini pc always on.

It is a very slow centrino with 2 CPU threads and 8Gb of RAM, a huble micro SATA SSD and works great with Debian Linux. I use it as a benchmark to understand if a project is worth studying: if the CPU Load stay low, the code is very well written.

Read More