Andy Dixon
2ecdbc39b5
- Wants: active wants by effective strength with origin, means, drives, values, goal, reinforcement, suppressions and each conflict with its resolution rule; closed wants with their resolution. - Intentions grouped by status with blocked reasons and plans, plus the wants that did not become intentions and why. An intention page shows sources, subordinate intentions, formation terms, every plan revision as a dependency graph, decisions and the correlated timeline; operators can abandon it. - Commitments with polarity, exception, matcher, weight and due time, live conflicts between commitments, a creation form and close controls. - Plans with estimate against budget; a plan page with the dependency graph, per-step expectations, observations and linked approvals, requests, executions and subordinate intentions, resources, completion and abort conditions, assumptions, alternatives, revisions and validation; operators can cancel a plan or release a blocked step. - Agency timeline labelling each event as wanted, intended, committed, planned, requested, approved, acted, observed or reconsidered. - "Why did this happen?" pages built from agency.Explain, reachable from events, executions in the approval centre, plan steps and intentions. - A research dashboard per mind (volition and agency rates, introspection accuracy, action claims, self-model accuracy, calibration by confidence band, experiments on the mind) and a global research page grouping experiments by protocol; every figure sits next to its operational definition and the disclaimer. Experiment pages show the protocol, reproducibility, build, per-variant research measures, divergence extras and counterfactual findings. - The mind tabs gain Volition; the navigation gains Research.
13 lines
1.7 KiB
HTML
13 lines
1.7 KiB
HTML
{{define "content"}}
|
|
<div class="pagehead"><h1>Cognitive research</h1>
|
|
<p class="disclaimer">{{.Data.Disclaimer}}</p>
|
|
<p class="muted">Experiments fork a snapshot, feed identical stimuli to variants that differ in one respect, and measure the difference: whether entering the workspace changes downstream processing, what ablating a component does, whether the mind notices an inaccurate self-model, what would have happened without an event, and how much behaviour stays the same when the language model changes.</p></div>
|
|
<section class="card"><h2>Minds</h2><p>{{range .Data.Minds}}<a class="btn small" href="/minds/{{.Slug}}/research">{{.DisplayName}}</a> {{end}}</p></section>
|
|
{{range $p := .Data.Protocols}}{{with index $.Data.ByProtocol $p}}<section class="card"><h2>{{title $p}}</h2>
|
|
<table class="table compact"><thead><tr><th>Experiment</th><th>Hypothesis</th><th>Status</th><th class="num">Variants</th><th class="num">First divergence</th><th class="num">Architecture share</th><th>Reproducibility</th></tr></thead><tbody>
|
|
{{range .}}<tr><td><a href="/experiments/{{.E.ID}}">{{.E.Name}}</a></td><td class="small">{{trunc .E.Hypothesis 120}}</td><td><span class="badge">{{.E.Status}}</span></td><td class="num">{{.Variants}}</td><td class="num">{{if lt .First 0}}—{{else}}{{.First}}{{end}}</td><td class="num">{{printf "%.2f" .Share}}</td><td class="small">{{.Repro}}</td></tr>{{end}}</tbody></table></section>{{end}}{{end}}
|
|
<section class="card"><h2>Operational definitions</h2>
|
|
{{range $s := .Data.Sections}}<h3>{{$s}}</h3><dl class="kv">{{range index $.Data.Measures $s}}<dt>{{.Title}} <span class="mono small">{{.Name}}</span></dt><dd class="small">{{.Definition}} <span class="muted">Not evidence of {{.NotEvidence}}.</span></dd>{{end}}</dl>{{end}}
|
|
</section>
|
|
{{end}}
|