Harnesses for Generalisation

Presentation Link#

The seventy-second MeetUp of the Machine Learning Singapore Group, was titled : “MLSG - Open Models & Harnesses”, and we went into the latest in Harness research, as well as addressing the upsurge in interest in Open Models that we’ve witnesses since our last MeetUp.

My Presentation#

My talk was titled “Harnesses for Generalisation”. My original plan was just to trace the flow of work from the authors of DSPy to the “Harnesses for Generalisation” blog post - but events dictated that I add content about the launch of Prime Agent, and mention the recent changes at Google HQ…

Overall, I used the following outline :

• Looking at a flow of work:

  • DSPy
  • Recursive Language Models
  • Harnesses for Generalisation

• BONUS : Prime Agent launch

• In the news…

• Wrap-up & QR-code

Slides#

The slides for my talk, which contain links to all of the reference materials and sources, are here :

If there are any questions about the presentation please ask below, or contact me using the details given on the slides themselves.

Other Presentations#

The MeetUp also featured:

Sam Witteveen giving a talk about the “The State of Open Models”:

• NVIDIA’s recent letter about why Open models matter

  • companies (including Google) co-signing

• Recent open models : BIG and small

• Model choice : Agent usage, Coding and All-Rounders

Acknowledgements#

Many thanks to the Google team, who allowed us to use Google’s Developer Space, and generously provided food for our audience.