What I have found gripping

• Tools integrating with the framework LangChain include Anthropic, Google, OpenAI, AWS, Microsoft etc.

• In LangChain, agents use a language model to choose a sequence of actions to take

• Running the command python -m pip install -r requirements.txt in an integrated terminal installs dependencies based on a file named requirements.txt

• Garbage collection in Ruby is a memory management system

What I have read

• Agents (in LangChain)

• Ruby Garbage Collection | Memory Management, Dan Moore

• module GC (Rdoc documentation)

What I have listened to

#17 – Lyse : « Les traditions, les cultures, ça nous conditionne », Joyeux Bazar

Featured quote

Whether you’re deploying to Heroku, a virtual machine, or Kubernetes, your application will have a finite amount of memory. If your application sees appreciable traffic or processes a large amount of data, you might see the dreaded NoMemoryError. You might also notice performance impacts as garbage collection happens. Or you might see memory bloat, as more and more memory is required by your application. — Dan Moore

Further reading and resources

In English

• Garbage collect in ruby? (StackOverflow)

• AI: the world is finally starting to regulate artificial intelligence – what to expect from US, EU and China’s new laws, Alina Patelli (Senior Lecturer in Computer Science, Aston University)

In French

• L’intelligence artificielle va-t-elle tuer ou sauver les médias ?, Laurence Devillers (Professeur en Intelligence Artificielle, Sorbonne Université)

Thanks for reading Sandra’s Weeknotes!