REFERENCE SEVEN DOMAINS
Every training concept, on one map.
Browse by domain. Scenes open the animated exhibits; entries are the distilled reference points.
Predictive self-supervision, Causal vs Masked LM, context windows, and the training step loop.
◈ SCENEInitialization & Nudging
How billions of parameters shift from Gaussian noise into structured representations.
◈ SCENECausal vs. Masked LM
Autoregressive generation vs bidirectional fill-in-the-blanks.
Forward logits -> Backward autodiff -> Optimizer step.
◈ SCENECausal Attention Masking
Zeroing upper-triangular scores to enforce unidirectional temporal flow.
◈ SCENEContext Window Math
Understanding O(N^2) memory scaling and KV cache growth.
Agent-native web · research mode
Experimental WebMCP · evolving community-group draft, not a W3C Standard or on the Standards Track.
Native status: Initializing. Registered: none
DOM → inferred capabilities · WebMCP → declared capabilities. Tools read real CUDA/Inference Atlas content. Calls may highlight temporary UI state. No backend or remote telemetry.
Local harness verifies application logic; it does not demonstrate native discovery or a browser agent.
Input schema
{
"type": "object",
"properties": {
"query": {
"type": "string",
"minLength": 1,
"maxLength": 300
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 10
}
},
"required": [
"query"
],
"additionalProperties": false
}Local log: last 100 calls while this panel is open. Inputs may contain personal text; review before sharing.
[]