From: JIT-LoRA: Just-in-Time Low-Rank Adaptation for Efficient Model Specialisation

What would a model’s learning curve look like if every answer left a measurable trace?

Treating dialogue as an observable experiment makes adaptation easier to inspect. It turns an abstract claim about learning into a sequence of testable behavioural changes.

Action

Log identical probe prompts before and after selected updates, then plot recall, refusal, latency, and drift over time.

Read the full exploration

What else is in this exploration

3 evidence blocks3 perspectives2 visualizations2 media resources4 rabbit holes

evidence

The reported JIT-LoRA evaluation achieved 61 correct recalls out of 105 tested facts.

evidence

The reported training run took 69.6 seconds for 180 steps on an M4 Max.

evidence

The JIT-LoRA system updates a running language model's LoRA weights during conversation.

Continue exploring

JIT-LoRA: Just-in-Time Low-Rank Adaptation for Efficient Model Specialisation

Evidence, perspectives, rabbit holes, and more