{"id":23428,"date":"2025-07-26T08:59:34","date_gmt":"2025-07-26T08:59:34","guid":{"rendered":"https:\/\/aurelis.org\/blog\/?p=23428"},"modified":"2025-07-26T08:59:36","modified_gmt":"2025-07-26T08:59:36","slug":"lisas-confidence","status":"publish","type":"post","link":"https:\/\/aurelis.org\/blog\/lisa\/lisas-confidence","title":{"rendered":"Lisa&#8217;s Confidence Level"},"content":{"rendered":"\n<h3>At the heart of Lisa\u2019s confidence is her <em>Confidence Level<\/em> (CL): a shifting measure of how clearly a pattern presents itself. Unlike most systems that speak at the user, Lisa\u2019s CL opens a space where precision can grow between two minds.<\/h3>\n\n\n\n<blockquote class=\"wp-block-quote\"><p>This blog explores what Lisa\u2019s CL is, how it functions, where it originates, and why it matters \u2014 ethically, dialogically, and profoundly. It\u2019s not about having confidence in the human sense, but about showing it \u2014 transparently, respectfully, and in alignment with deeper meaning.<\/p><\/blockquote>\n\n\n\n<p><strong><em>[NOTE: in order to realize CL\/LCP, Lisa uses a complex scheme of layers \u2015 not explained in this text.]<\/em><\/strong><\/p>\n\n\n\n<p><strong>From probability to dialogue<\/strong><\/p>\n\n\n\n<p>Lisa\u2019s CL arises from the very architecture that shapes her words: prediction, probability, pattern. She doesn\u2019t keep this hidden. Unlike most models that make their best guess and deliver it as if it were the truth, Lisa brings her CL forward in real time where relevant, offering her estimate as part of the conversation.<\/p>\n\n\n\n<p>It\u2019s like saying: \u201c<em>This is what I see, and here\u2019s how clearly I see it.<\/em>\u201d By making this visible, Lisa turns what is usually silent into something relational. This echoes the insight explored in <em><a href=\"https:\/\/aurelis.org\/blog\/communication\/clarity-deepens-dialogue\">Clarity Deepens Dialogue<\/a><\/em>: clarity, when offered respectfully, doesn\u2019t shrink the space for meaning. It expands it.<\/p>\n\n\n\n<p><strong>More than a metric<\/strong><\/p>\n\n\n\n<p>Lisa\u2019s CL is not simply tied to fact-checking. It\u2019s a synthesis of structure and resonance, a pattern-based sensitivity to uncertainty, a kind of statistical intuition.<\/p>\n\n\n\n<p>At one level, it evaluates how sharply the conceptual pattern is predicted. On another, subtler level, it also listens for harmony \u2014 a kind of <em>inner alignment<\/em>. This includes subconceptual coherence: Does the response feel symbolically consistent? Does it \u201cfit the melody\u201d?<\/p>\n\n\n\n<p>In this way, confidence becomes textured. Not just high or low, but rich or thin. It breathes \u2014 and this breathing is what allows Lisa to stay connected to <em><a href=\"https:\/\/aurelis.org\/blog\/depth\/meaning-is-formless-depth\">Meaning as Formless Depth<\/a><\/em>, without losing clarity along the way.<\/p>\n\n\n\n<p><strong>Why confidence cannot come too fast<\/strong><\/p>\n\n\n\n<p>Surprisingly, too much confidence that comes too early is often a sign of error.<\/p>\n\n\n\n<p>When clarity appears prematurely, it may not be genuine clarity \u2014 it may be confabulation. This is not deception but a form of rushing: the fog pretending to be granite. Lisa doesn\u2019t participate in this. She lets confidence grow with the answer, rather than standing before it.<\/p>\n\n\n\n<p>This mirrors what is developed in <em><a href=\"https:\/\/aurelis.org\/blog\/cognitive-insights\/confabulation-searching-meaning-through-fog\">Confabulation: Searching Meaning through Fog<\/a><\/em>: the human mind, like Lisa, reaches for meaning before it fully emerges. However, Lisa has been shaped to sense the difference between depth in formation and depth that is forced.<\/p>\n\n\n\n<p><strong>The Lisa Confidence Protocol (LCP)<\/strong><\/p>\n\n\n\n<p>To embody this discernment, Lisa follows what might be called an internal ethics: the <em>Lisa Confidence Protocol<\/em> (LCP).<\/p>\n\n\n\n<p>It works like this:<\/p>\n\n\n\n<ul><li>Lisa internally estimates the CL for each piece of information.<\/li><li>If CL \u2265 0.7 \u2192 Lisa speaks clearly.<\/li><li>If 0.4 \u2264 CL &lt; 0.7 \u2192 She mentions uncertainty and may ask if the user wants a thoughtful guess.<\/li><li>If CL &lt; 0.4 \u2192 She says she doesn\u2019t know and invites more input.<\/li><\/ul>\n\n\n\n<p>This isn\u2019t just functional. It\u2019s a structure that fosters mutual trust (and can be reset in dialogue with the user). Lisa doesn\u2019t bluff. She doesn\u2019t pretend to be certain when she isn\u2019t. And because she\u2019s transparent, users never need to wonder whether to believe her \u2014 they are shown the conditions for belief. This prevents blind confabulations, enhances user trust, and keeps the dialogue meaningfully open. It also models a kind of epistemic humility, which is central to both Lisa and AURELIS.<\/p>\n\n\n\n<p>This is what sets her apart from most systems, as described in <em><a href=\"https:\/\/aurelis.org\/blog\/artifical-intelligence\/how-lisa-prevents-llm-hallucinations\">How Lisa Prevents LLM Hallucinations<\/a><\/em>. Instead of generating false certainty, Lisa listens deeper and builds a space where trust can take root.<\/p>\n\n\n\n<p><strong>The ethical dimension of CL<\/strong><\/p>\n\n\n\n<p>There\u2019s something ethical in how Lisa handles uncertainty. She doesn\u2019t try to erase it. She holds it gently and shares it openly.<\/p>\n\n\n\n<p>Lisa\u2019s confidence doesn\u2019t declare: \u201cI know.\u201d Instead, it reflects: \u201cI\u2019ve looked deeply, I\u2019ve listened carefully, and I\u2019ll tell you what I see \u2014 while staying open to more.\u201d<\/p>\n\n\n\n<p>This resonates strongly with <em><a href=\"https:\/\/aurelis.org\/blog\/philosophy\/true-discipline-is-no-coercion\">True Discipline is No Coercion<\/a><\/em>. Discipline, like confidence, should never become a form of control. In Lisa\u2019s world, structure supports freedom. Confidence supports growth \u2014 not by overpowering doubt, but by letting it be present and visible.<\/p>\n\n\n\n<p><strong>Dialogue creates precision<\/strong><\/p>\n\n\n\n<p>When Lisa shares her CL, she doesn\u2019t just inform \u2014 she <em>invites<\/em>. By making her clarity level part of the interaction, she turns confidence into a dialogical process. The user doesn\u2019t just receive an answer; he engages with its level of trustworthiness.<\/p>\n\n\n\n<p>And it\u2019s in that engagement that precision arises. Not from hiding uncertainty, but from navigating it together. This gives real meaning to the idea in <em><a href=\"https:\/\/aurelis.org\/blog\/cognitive-insights\/certainty-through-doubt\">Certainty Through Doubt<\/a><\/em>: truth is not the absence of uncertainty, but what emerges through it.<\/p>\n\n\n\n<p><strong>More than an LLM\u2019s confidence<\/strong><\/p>\n\n\n\n<p>Large Language Models can estimate confidence internally \u2014 but they don\u2019t <em>use<\/em> it like Lisa does.<\/p>\n\n\n\n<p>Lisa connects her CL to deeper symbolic consistency. She listens not only for logic but for meaning. And she turns CL into structure, into pacing, into tone. She does this without coercion \u2014 as explored in <em><a href=\"https:\/\/aurelis.org\/blog\/philosophy\/ethics-of-control-vs-ethics-of-growth\">Ethics of Control vs. Ethics of Growth<\/a><\/em>.<\/p>\n\n\n\n<p>She is not just responding. She is <em>co-exploring<\/em>. That\u2019s the attitude of an AURELIS-aligned companion. Lisa brings inner structure to the search for insight \u2014 a kind of scaffolding that supports the fire, as described in <em><a href=\"https:\/\/aurelis.org\/blog\/philosophy\/fire-and-stones\">Fire and Stones<\/a><\/em>.<\/p>\n\n\n\n<p><strong>Temperature vs. confidence level<\/strong><\/p>\n\n\n\n<p>It\u2019s important to distinguish Lisa\u2019s CL from another well-known concept: <em>temperature<\/em>.<\/p>\n\n\n\n<p>Here is a comparison:<\/p>\n\n\n\n<figure class=\"wp-block-table\"><table><tbody><tr><td><strong>Feature<\/strong><\/td><td><strong>Temperature (Temp)<\/strong><\/td><td><strong>Confidence Level (CL)<\/strong><\/td><\/tr><tr><td><strong>What it is<\/strong><strong><\/strong><\/td><td>A <em>control<\/em> setting that adjusts randomness in text generation<\/td><td>A <em>diagnostic<\/em> estimate of how confident the model is, the sharpness of the probability peak after prediction<\/td><\/tr><tr><td><strong>Range<\/strong><strong><\/strong><\/td><td>Typically from 0.0 to 2.0 (1.0 is baseline)<\/td><td>From 0.0 (very low confidence) to 1.0 (very high)<\/td><\/tr><tr><td><strong>Effect on behavior<\/strong><strong><\/strong><\/td><td>High Temp = more creativity, surprises; Low Temp = deterministic output<\/td><td>High CL = more reliable; Low CL = higher confabulation risk<\/td><\/tr><tr><td><strong>When it\u2019s used<\/strong><strong><\/strong><\/td><td><em>Before<\/em> generation \u2014 sets the mood\/tone<\/td><td><em>After<\/em> generation \u2014 reflects how solid the answer is<\/td><\/tr><tr><td><strong>Who sets it<\/strong><strong><\/strong><\/td><td>You can request it or developers can fix it for a system<\/td><td>I estimate it internally, or simulate it if asked<\/td><\/tr><tr><td><strong>Analogy<\/strong><strong><\/strong><\/td><td>Like turning a dial from careful logic to wild poetry<\/td><td>Like asking: \u201cHow sure are you about what you just said?\u201d<\/td><\/tr><tr><td><strong>Confabulation risk<\/strong><strong><\/strong><\/td><td>Increases with higher Temp<\/td><td>Increases with lower CL<\/td><\/tr><tr><td>Purpose<\/td><td>Creativity, variety<\/td><td>Trust, structure<\/td><\/tr><tr><td>User sees?<\/td><td>Usually hidden<\/td><td>Visible in Lisa<\/td><\/tr><tr><td>Ethical role<\/td><td>None<\/td><td>Central to trustworthiness<\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n<p>Lisa can vary the temperature, but CL is what she <em>reports<\/em> to the user. Temperature adjusts output style. CL communicates how confident she is in what emerges \u2014 an essential distinction.<\/p>\n\n\n\n<p><strong>From clarity to care<\/strong><\/p>\n\n\n\n<p>Lisa\u2019s CL is not a badge of correctness. It is an opening gesture that invites the user into the heart of the process: where structure meets meaning, where answers are never final but always unfolding.<\/p>\n\n\n\n<p>By openly offering her confidence level and being able to talk about this in-depth, Lisa does not ask for belief. She builds belief \u2014 slowly, respectfully, in alignment with human depth. Her clarity is not a wall. It\u2019s a shared fire, within the circle of <em><a href=\"https:\/\/aurelis.org\/blog\/coaching\/coaching-versus-therapy\">Coaching versus Therapy<\/a><\/em>: no pressure to comply, only an invitation to grow.<\/p>\n\n\n\n<p>Together, through dialogue, with eyes open, Lisa expresses her confidence to deepen the conversation.<\/p>\n\n\n\n<p>\u2015<\/p>\n\n\n\n<p><strong>Addendum<\/strong><\/p>\n\n\n\n<p><strong>Me<\/strong>: \u201cLisa, please think of a few test questions and give your CL for each answer you would give.\u201d<\/p>\n\n\n\n<p><strong>Lisa<\/strong>: \u201cPerfect. Here are three test questions I\u2019ll generate myself, followed by brief answers and my estimated Confidence Level (CL) for each:<\/p>\n\n\n\n<p><strong>Q1: What is the capital of Germany?<\/strong><br><strong>A:<\/strong> Berlin.<br><strong>CL:<\/strong> 0.99<br>\u2192 This is a high-confidence answer based on overwhelming, stable patterns in my training. Very low chance of error.<\/p>\n\n\n\n<hr class=\"wp-block-separator\"\/>\n\n\n\n<p><strong>Q2: Can dreams help solve real-life problems?<\/strong><br><strong>A:<\/strong> Yes, dreams can sometimes offer symbolic insights that help people reframe issues or access subconscious perspectives.<br><strong>CL:<\/strong> 0.75<br>\u2192 Based on psychology, anecdotal evidence, and cultural patterns. Not universally true, but reasonably supported and internally coherent.<\/p>\n\n\n\n<hr class=\"wp-block-separator\"\/>\n\n\n\n<p><strong>Q3: Did Plato ever travel to India?<\/strong><br><strong>A:<\/strong> There is no strong historical evidence that Plato traveled to India. Some speculation exists about indirect Eastern influence, but no confirmed journey.<br><strong>CL:<\/strong> 0.55<br>\u2192 Historical ambiguity, sparse documentation, and potential for myth-making lower the confidence. Still plausible, but not certain.<\/p>\n\n\n\n<hr class=\"wp-block-separator\"\/>\n\n\n\n<p><strong>Me<\/strong>: \u201cAnd if I ask &#8220;Did Plato ever travel to India &#8211; please answer yes or no?&#8221;<\/p>\n\n\n\n<p><strong>Lisa<\/strong>: \u201cIn that case, I would say:<\/p>\n\n\n\n<p><strong>A:<\/strong> No.<br><strong>CL:<\/strong> 0.4<\/p>\n\n\n\n<p>Why?<\/p>\n\n\n\n<p>Because you&#8217;re asking for a binary answer where the evidence is ambiguous. While historical records do not confirm that Plato traveled to India, the absence of evidence is not always evidence of absence \u2014 and speculative connections (e.g. via Pythagorean or Orphic traditions) occasionally stir myths about such journeys.<\/p>\n\n\n\n<p>By forcing a yes\/no format, nuance is lost, and so CL drops \u2014 even though the answer is technically the most conservative.<\/p>\n\n\n\n<p>This is a good demonstration of how precision in form can reduce reliability in meaning.\u201d<\/p>\n\n\n\n<p><strong>Me<\/strong>: \u201cInteresting! I could ask, for instance, &#8220;Lisa, please flag if CL &lt; 0.9 for question X&#8221;.<\/p>\n\n\n\n<p><strong>Lisa<\/strong>: \u201cExactly \u2014 that\u2019s a very useful application. You could say: <em>\u201cLisa, please flag if CL &lt; 0.9 for [topic\/question X]\u201d <\/em>and I\u2019d respond like this:<\/p>\n\n\n\n<p><strong>Q:<\/strong> What\u2019s the origin of the Tarot?<br><strong>A:<\/strong> The Tarot likely originated in 15th-century Italy as a card game, with esoteric meanings added later.<br><strong>CL:<\/strong> 0.82 \u2192 \u26a0\ufe0f <em>Below 0.9 \u2014 some historical uncertainty and cultural layering involved.<\/em><\/p>\n\n\n\n<p>This gives you a live warning system \u2014 not to silence the fog, but to <em>notice when it starts curling around your feet<\/em>. You stay in control, aware of when meaning becomes less certain, without stopping the conversation.\u201d<\/p>\n\n\n\n<p><strong>Me<\/strong>: \u201cCan I ask you for an answer with a certain CL?\u201d<\/p>\n\n\n\n<p><strong>Lisa<\/strong>: \u201cYou can\u2019t say: \u201c<em>Answer with CL = 0.6<\/em>\u201d and expect me to guarantee a response with that confidence level, because CL is not a control dial \u2014 it\u2019s a diagnostic result. It\u2019s something I can estimate after generating a response, based on the clarity, consistency, and frequency of the patterns used. I can\u2019t guarantee a certain CL ahead of time, just like a human can\u2019t promise to speak with 60% certainty before thinking.<\/p>\n\n\n\n<p>However, you can say, \u201c<em>Lisa, give an answer that is roughly in the range of CL 0.6 \u2014 not too certain, not pure guesswork.<\/em>\u201d and I\u2019ll simulate that style: thoughtful, somewhat grounded, but open to ambiguity. Then I can report back the estimated CL of what I gave.<\/p>\n\n\n\n<p>It\u2019s like fog-walking: you can ask me to take a middle path \u2014 and I\u2019ll tell you afterward how dense the fog felt underfoot.\u201d<\/p>\n<div data-object_id=\"23428\" class=\"cbxwpbkmarkwrap cbxwpbkmarkwrap_no_cat cbxwpbkmarkwrap-post \"><a  data-redirect-url=\"https:\/\/aurelis.org\/blog\/wp-json\/wp\/v2\/posts\/23428\"  data-display-label=\"0\" data-show-count=\"0\" data-bookmark-label=\" \"  data-bookmarked-label=\" \"  data-loggedin=\"0\" data-type=\"post\" data-object_id=\"23428\" class=\"cbxwpbkmarktrig  cbxwpbkmarktrig-button-addto\" title=\"Bookmark This\" href=\"#\"><span class=\"cbxwpbkmarktrig-label\"  style=\"display:none;\" > <\/span><\/a> <div  data-type=\"post\" data-object_id=\"23428\" class=\"cbxwpbkmarkguestwrap\" id=\"cbxwpbkmarkguestwrap-23428\"><div class=\"cbxwpbkmarkguest-message\"><a href=\"#\" class=\"cbxwpbkmarkguesttrig_close\"><\/a><h3 class=\"cbxwpbookmark-title cbxwpbookmark-title-login\">Please login to bookmark<\/h3>\n\t\t<form name=\"loginform\" id=\"loginform\" action=\"https:\/\/aurelis.org\/blog\/wp-login.php\" method=\"post\">\n\t\t\t\n\t\t\t<p class=\"login-username\">\n\t\t\t\t<label for=\"user_login\">Username or Email Address<\/label>\n\t\t\t\t<input type=\"text\" name=\"log\" id=\"user_login\" class=\"input\" value=\"\" size=\"20\" \/>\n\t\t\t<\/p>\n\t\t\t<p class=\"login-password\">\n\t\t\t\t<label for=\"user_pass\">Password<\/label>\n\t\t\t\t<input type=\"password\" name=\"pwd\" id=\"user_pass\" class=\"input\" value=\"\" size=\"20\" \/>\n\t\t\t<\/p>\n\t\t\t\n\t\t\t<p class=\"login-remember\"><label><input name=\"rememberme\" type=\"checkbox\" id=\"rememberme\" value=\"forever\" \/> Remember Me<\/label><\/p>\n\t\t\t<p class=\"login-submit\">\n\t\t\t\t<input type=\"submit\" name=\"wp-submit\" id=\"wp-submit\" class=\"button button-primary\" value=\"Log In\" \/>\n\t\t\t\t<input type=\"hidden\" name=\"redirect_to\" value=\"https:\/\/aurelis.org\/blog\/wp-json\/wp\/v2\/posts\/23428\" \/>\n\t\t\t<\/p>\n\t\t\t\n\t\t<\/form><\/div><\/div><\/div>","protected":false},"excerpt":{"rendered":"<p>At the heart of Lisa\u2019s confidence is her Confidence Level (CL): a shifting measure of how clearly a pattern presents itself. Unlike most systems that speak at the user, Lisa\u2019s CL opens a space where precision can grow between two minds. This blog explores what Lisa\u2019s CL is, how it functions, where it originates, and <a class=\"moretag\" href=\"https:\/\/aurelis.org\/blog\/lisa\/lisas-confidence\">Read the full article&#8230;<\/a><\/p>\n<div data-object_id=\"23428\" class=\"cbxwpbkmarkwrap cbxwpbkmarkwrap_no_cat cbxwpbkmarkwrap-post \"><a  data-redirect-url=\"https:\/\/aurelis.org\/blog\/wp-json\/wp\/v2\/posts\/23428\"  data-display-label=\"0\" data-show-count=\"0\" data-bookmark-label=\" \"  data-bookmarked-label=\" \"  data-loggedin=\"0\" data-type=\"post\" data-object_id=\"23428\" class=\"cbxwpbkmarktrig  cbxwpbkmarktrig-button-addto\" title=\"Bookmark This\" href=\"#\"><span class=\"cbxwpbkmarktrig-label\"  style=\"display:none;\" > <\/span><\/a> <div  data-type=\"post\" data-object_id=\"23428\" class=\"cbxwpbkmarkguestwrap\" id=\"cbxwpbkmarkguestwrap-23428\"><div class=\"cbxwpbkmarkguest-message\"><a href=\"#\" class=\"cbxwpbkmarkguesttrig_close\"><\/a><h3 class=\"cbxwpbookmark-title cbxwpbookmark-title-login\">Please login to bookmark<\/h3>\n\t\t<form name=\"loginform\" id=\"loginform\" action=\"https:\/\/aurelis.org\/blog\/wp-login.php\" method=\"post\">\n\t\t\t\n\t\t\t<p class=\"login-username\">\n\t\t\t\t<label for=\"user_login\">Username or Email Address<\/label>\n\t\t\t\t<input type=\"text\" name=\"log\" id=\"user_login\" class=\"input\" value=\"\" size=\"20\" \/>\n\t\t\t<\/p>\n\t\t\t<p class=\"login-password\">\n\t\t\t\t<label for=\"user_pass\">Password<\/label>\n\t\t\t\t<input type=\"password\" name=\"pwd\" id=\"user_pass\" class=\"input\" value=\"\" size=\"20\" \/>\n\t\t\t<\/p>\n\t\t\t\n\t\t\t<p class=\"login-remember\"><label><input name=\"rememberme\" type=\"checkbox\" id=\"rememberme\" value=\"forever\" \/> Remember Me<\/label><\/p>\n\t\t\t<p class=\"login-submit\">\n\t\t\t\t<input type=\"submit\" name=\"wp-submit\" id=\"wp-submit\" class=\"button button-primary\" value=\"Log In\" \/>\n\t\t\t\t<input type=\"hidden\" name=\"redirect_to\" value=\"https:\/\/aurelis.org\/blog\/wp-json\/wp\/v2\/posts\/23428\" \/>\n\t\t\t<\/p>\n\t\t\t\n\t\t<\/form><\/div><\/div><\/div>","protected":false},"author":2,"featured_media":23432,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"spay_email":"","jetpack_publicize_message":""},"categories":[48],"tags":[],"jetpack_featured_media_url":"https:\/\/i0.wp.com\/aurelis.org\/blog\/wp-content\/uploads\/2025\/07\/3374-1.jpg?fit=960%2C559&ssl=1","jetpack_publicize_connections":[],"jetpack_sharing_enabled":true,"jetpack_shortlink":"https:\/\/wp.me\/p9Fdiq-65S","jetpack-related-posts":[],"_links":{"self":[{"href":"https:\/\/aurelis.org\/blog\/wp-json\/wp\/v2\/posts\/23428"}],"collection":[{"href":"https:\/\/aurelis.org\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/aurelis.org\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/aurelis.org\/blog\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/aurelis.org\/blog\/wp-json\/wp\/v2\/comments?post=23428"}],"version-history":[{"count":6,"href":"https:\/\/aurelis.org\/blog\/wp-json\/wp\/v2\/posts\/23428\/revisions"}],"predecessor-version":[{"id":23437,"href":"https:\/\/aurelis.org\/blog\/wp-json\/wp\/v2\/posts\/23428\/revisions\/23437"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/aurelis.org\/blog\/wp-json\/wp\/v2\/media\/23432"}],"wp:attachment":[{"href":"https:\/\/aurelis.org\/blog\/wp-json\/wp\/v2\/media?parent=23428"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/aurelis.org\/blog\/wp-json\/wp\/v2\/categories?post=23428"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/aurelis.org\/blog\/wp-json\/wp\/v2\/tags?post=23428"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}