stand

This weekend Ghent was the place to be. 
If you like food: Gent Smaakt is a culinary event and it was great to stroll around in the city streets in the evenings. During the day it was DrupalCamp Ghent. 

 
🍊 At the booth, you could find 100% fresh pressed oranges, limes and grapefruits, no Artificial Ingredients (AI).  

collage

AI is breaking Open Source

🔓 For me the best session was Merlijn Sebrechts' "AI is Breaking Open Source." He talked about open source and its current challenges with the rise of AI (like LLama3). His explanations of GenAI pipelines and OSA definitions were critical for understanding the broader impacts on the open source community. 
He told us to share: LLAMA 3 IS NOT OPEN SOURCE according to Open Source Initiative (OSI)!  

 
According to the fineprint, 

  • LLAMA 3 can not be used by sex workers 

  • The indian government is not alllowed to use LLAMA 3 (700 mio users limit)  

  • You can not train other models if you’re using LLAMA 3 (in other words it’ only for META).  

 

And Open Source should be about democratizing technology, making it available to ALL!  He also explained when an AI is really Open Source (preferred form). 

Merijn

Merlijn also explained the GenAI pipeline and the important deliverables.  

Main training 

  • Data 

  • Training code 

  • Model code 

 

Finetuning 

  • Finetuning data 

  • Finetuning code 

 
Prompting 

  • Prompt tuning 

 

He also explained there is a OSA definition (V0.0.8). that is best explained here: https://opensource.org/deepdive/drafts/the-open-source-ai-definition-draft-v-0-0-8  

In short:  

  • you can use it for any purpose 

  • You’re able to study it’s components 

  • You’re able to modify it’s components 

  • You can share it with or without modifications  

  • You have access to it’s preferred form. 

 
He also has some great ideas on how a trust based system could help a lot, and shortly mentioned the AI bill of materials.  This is a good use of your time if you’re interested in Open source licenses and AI. 

https://www.drupalcamp.be/en/drupalcamp-ghent-2024/session/ai-breaking-open-source  

cookies

We hate cookies

🍪 In "We Hate Cookies," Dr Philippe De Ryck  gave us a lot of interesting technical information:  
 

  1. Don’t forget to remove Dangling CNAME records (obvious but still relevant) 
    1. Check the correct cookie attributes (he nicely explains the importance of each of these
    2. Httponly  
    3. __secure/__host. / 
    4. Samesite 
  2. I learned that github.io is a Top level domain, for security reasons (like .be or .com or .govv.uk) . And you could have this too (but only if it’s really really needed).  
  3. He also explained that by the end of 2024 third party cookies will be finished. This willhave a lot of impact. Collateral damage:  
    1. Cross site Iframe widgets 
    2. Cross site API calls 
    3. Oauth (silent) 

If you want to test your application, test it in Safari or Brave, they already do this.  I strongly recommend all web developers out there to check the session!  

https://www.drupalcamp.be/en/drupalcamp-ghent-2024/session/we-hate-cookies

faq

Do you still have a FAQ? You're doing it wrong!

🔎 I presented about Retrieval Augmented Generation “Do you still have a FAQ? You're doing it wrong.”. 

I explained the Feedback Loop of FAQ and how to get the FAQ out of it.  
 
In other words: how to remove some inefficiencies in your company (and how FAQ is the symptom). This is only possible thanks to new technology and changing expectations.  

I have a more detailed post about how RAG works here: https://www.calibrate.be/nl/rag  
but if you want a in depth explanation, ping me. 

All in all Drupalcamp was again a big success. Thanks to Calibrate (platinum sponsor) and the organisation Drupal Belgium.

Want to know how RAG works?