Back to blog

Dev Diary #12 - A fistful of fixes


On Tuesday, we opened up the platform for anyone to use! We're excited to see what you build with Glaive, and we're looking forward to hearing your feedback. The past month has been a lot of prep-work for a public launch including a lot of stability and bug fixes. Usually we would go a little more in-depth on the features we've been working on, but since the last month has been all over the place here is a long list of everything that's happened.


  • Reworked sources to use the edit system, this allows for sources changes to work naturally with the dataset versioning system.
  • Integrated with Stripe for billing.
  • Rebuilt data-generation pipeline from the ground up. Datasets are now better quality and about 10x larger.
  • Buffed up clustering so it is now much faster and has a better spread of categories.
  • Made our build systems much more reliable.
  • Tweaked model training to work better with larger datasets.
  • Re-enabled Llama3 support.
  • Completed migration off Kubernetes.
  • Added retries to clustering.
  • Fixed broken API Key authentication.
  • Moved sign-in/sign-up pages onto the main site.
  • Lightened up dark mode.
  • Removed old FDG graph for keyphrases.
  • Blocked mobile devices from using the platform but made it work on tablets.
  • Added tooltips across the platform.
  • Hundreds of other bug fixes across the frontend and backend.