brightlabYear 12 · Two live trained checkpoints · 55 minutes
Find what changed after training
How can a small training change produce a hidden behaviour change?
The first load downloads Python and may take a moment. Write a prediction, then open the lab. Controls, help, teacher notes and your evidence download are inside. If the school network blocks the runtime, download the Python notebook and run it with your teacher.
Investigate one research connection
Intentionally Designing the Future of AI
Distinguish editing an activation from changing the training signal and checking regressions. Record the source model/task, a baseline, the changed factor, a measurement and an alternative explanation. State exactly which part your notebook investigates and which part it does not reproduce.
This is a research agenda; intentional design is not a solved capability.
Use the notebook below to collect the measurements. This writing remains in this page session until downloaded.
Teacher background and source method
Research agenda with worked training examples
Proposes observing per-example learning signals and changing what training generalises; separate aspirations from demonstrated interventions.
Independent classroom adaptation; not a reproduction of the source model or complete method.
Read the source with a teacher ↗Opening the notebook page…
First use downloads Python and its libraries. A fresh session measured about 20–22 seconds and 14–17 MB during the initial audit; school networks vary. This hosted notebook computes on the browser CPU.
Your prediction and saved runs stay in this session. Download your evidence before leaving or refreshing. The hosted experiment runs on your browser CPU and does not connect to an H100.
Research connections · 4 archive entries
These lessons adapt ideas and methods. The original sources state their own model, data and validation scope.
Intentionally Designing the Future of AI ↗
This is a research agenda; intentional design is not a solved capability.
Discovering Undesired Rare Behaviors via Model Diff Amplification ↗
Amplified discovery is not an estimate of how often the original model fails.
Predictive Data Debugging: Reveal and Shape What Your Model Learns, Before You Train ↗
Our supervised colour task illustrates data effects; it is not a replication of contrastive-SAE post-training or DPO.
Probe-Based Data Attribution: Surfacing and Mitigating Undesirable Behaviors in LLM Post-Training ↗
The paper evaluates particular models and behaviours. Our checkpoint comparison does not implement its attribution algorithm.