All activity
Wojtek Kuberskileft a comment
Cool stuff!
Collectif.aiWhere teams discover product insights - in minutes, not days
Wojtek Kuberskileft a comment
Good stuff!
Onboarding.StudyLearn user onboarding from the best SaaS products
Wojtek Kuberskileft a comment
We had long delayed building a developer portal with our team (we never felt we were big enough to justify the engineering effort). With Rely.io, I think we could get our software catalog fully mapped with all our assets (services, cloud resources, repos, deployments, etc) in minutes just by adding the AWS and Github integrations.
Rely.ioThe developer portal with an AI assistant you can speak with
Wojtek Kuberskileft a comment
Hey, I’m Wojtek, co-founder of NannyML and responsible for Product and Research. Support for regression is a big deal, especially from a Performance Estimation perspective. As far as I know, NannyML is the only product (OSS or not) that can estimate the performance of your models without ground truth. The core algorithm we developed for the Performance Estimation of Regression models (Direct...
NannyML Regression v0.8.0OSS Python library for detecting silent ML model failure
Detecting silent model failure. NannyML estimates performance for regression and classification models using tabular data. Alerts you when and why it changed. It is the only open-source library capable of fully capturing the impact of data drift on performance
NannyML Regression v0.8.0OSS Python library for detecting silent ML model failure
Wojtek Kuberskileft a comment
Hey, I’m Wojtek, co-founder of NannyML. I’m gonna share a bit of the “why” behind NannyML. NannyML was born out of a real customer need. I used to run an ML consultancy doing end-to-end ML. Lots of our customers were asking “Now that the model is deployed, how do I make sure it keeps on working well?” This was a problem we couldn’t build a custom solution for (waaay too much work). But after a...
NannyMLOSS Python library for detecting silent ML model failure
NannyML estimates real-world model performance (without access to targets) and alerts you when and why it changed. The performance estimation algorithm, confidence-based performance estimation (CBPE), was researched by core contributors.
NannyMLOSS Python library for detecting silent ML model failure