Distilling GPT-5.1: Training an Open-Source Student with an Azure LLM Teacher
Large models are powerful, but expensive to run, slow to iterate, and hard to ship. Distillation lets you transfer intelligence from a hosted Azure GPT-5.1 model into a lightweight open-source student that you fully control. In this talk, I’ll show how to generate structured teaching data, design effective prompts and evaluation loops, and fine-tune a smaller model that preserves quality while cutting cost and latency. Walk away with a practical recipe for bringing enterprise-grade reasoning into models you can deploy anywhere.
AI Augmented Coaching for Rugby: Computer Vision Solutions for Safer Play
In this session we walk through a coaching solution that assists decisions using standard rugby footage. After auto-calibrating the pitch and setting up real-time tracking, we surface clear coaching cues: defensive line shape drifting or dog-legging, pods arriving late or stacking incorrectly, over-kicking and poor chase spacing, and slow ruck speed or missed folds. Those signals drive AI enhanced visuals for post game coaching feedback. In parallel we highlight possible injury or concussion risk with non-diagnostic alerts such as collision intensity spikes, head-contact likelihood from contact-zone masks, stumbles or slow-to-rise behaviour, and unusual workload patterns.
Decision Making in the Face of Uncertainty
Decision making in the face of uncertainty is one of the hardest things to do. In this pre-compiler session, we'll borrow methods from machine learning, statistics, trading and computer science to compose a methodology which will allow you to make the best decision possible given the evidence you have to hand, and to also hedge against you being wrong. Whether you're a "techie" or a "civilian" everyone can benefit from learning this important methodology
NDC Oslo 2024 Sessionize Event
SQLBits 2024 - General Sessions Sessionize Event
DDD North 2024 Sessionize Event
CodeMash 2020 Sessionize Event
NDC Oslo 2019 Sessionize Event
CodeMash 2019 Sessionize Event
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top