Built site for gh-pages

Confirm-Solutions · Jul 24, 2024 · fc59b13 · fc59b13
1 parent fed0bdb
commit fc59b13
Show file tree

Hide file tree

Showing 14 changed files with 54 additions and 54 deletions.
diff --git a/.nojekyll b/.nojekyll
@@ -1 +1 @@
-1e812383
+2daa44c1
diff --git a/index.html b/index.html
@@ -207,7 +207,7 @@ <h2 class="anchored" data-anchor-id="articles">Articles</h2>
 
 <div class="quarto-listing quarto-listing-container-grid" id="listing-listing">
 <div class="list grid quarto-listing-cols-3">
-<div class="g-col-1" data-index="0" data-listing-date-sort="1721692800000" data-listing-file-modified-sort="1721783020032" data-listing-date-modified-sort="NaN" data-listing-reading-time-sort="5" data-listing-word-count-sort="805">
+<div class="g-col-1" data-index="0" data-listing-date-sort="1721692800000" data-listing-file-modified-sort="1721845334819" data-listing-date-modified-sort="NaN" data-listing-reading-time-sort="5" data-listing-word-count-sort="806">
 <a href="./posts/flrt.html" class="quarto-grid-link">
 <div class="quarto-grid-item card h-100 card-left">
 <p class="card-img-top"><img src="posts/bomb.png" style="height: 150px;"  class="thumbnail-image card-img"/></p>
@@ -230,7 +230,7 @@ <h5 class="no-anchor card-title listing-title">
 </div>
 </a>
 </div>
-<div class="g-col-1" data-index="1" data-listing-date-sort="1720742400000" data-listing-file-modified-sort="1721783020020" data-listing-date-modified-sort="NaN" data-listing-reading-time-sort="9" data-listing-word-count-sort="1747">
+<div class="g-col-1" data-index="1" data-listing-date-sort="1720742400000" data-listing-file-modified-sort="1721845334807" data-listing-date-modified-sort="NaN" data-listing-reading-time-sort="9" data-listing-word-count-sort="1747">
 <a href="./posts/circuit_breaking.html" class="quarto-grid-link">
 <div class="quarto-grid-item card h-100 card-left">
 <p class="card-img-top"><img src="posts/circuit_breaking_files/figure-html/cell-4-output-1.png" style="height: 150px;"  class="thumbnail-image card-img"/></p>
@@ -253,7 +253,7 @@ <h5 class="no-anchor card-title listing-title">
 </div>
 </a>
 </div>
-<div class="g-col-1" data-index="2" data-listing-date-sort="1705968000000" data-listing-file-modified-sort="1721783020032" data-listing-date-modified-sort="NaN" data-listing-reading-time-sort="4" data-listing-word-count-sort="771">
+<div class="g-col-1" data-index="2" data-listing-date-sort="1705968000000" data-listing-file-modified-sort="1721845334819" data-listing-date-modified-sort="NaN" data-listing-reading-time-sort="4" data-listing-word-count-sort="771">
 <a href="./posts/dreamy.html" class="quarto-grid-link">
 <div class="quarto-grid-item card h-100 card-left">
 <p class="card-img-top"><img src="posts/dream_wow.png" style="height: 150px;"  class="thumbnail-image card-img"/></p>
@@ -276,7 +276,7 @@ <h5 class="no-anchor card-title listing-title">
 </div>
 </a>
 </div>
-<div class="g-col-1" data-index="3" data-listing-date-sort="1705104000000" data-listing-file-modified-sort="1721783019996" data-listing-date-modified-sort="NaN" data-listing-reading-time-sort="25" data-listing-word-count-sort="4985">
+<div class="g-col-1" data-index="3" data-listing-date-sort="1705104000000" data-listing-file-modified-sort="1721845334783" data-listing-date-modified-sort="NaN" data-listing-reading-time-sort="25" data-listing-word-count-sort="4985">
 <a href="./posts/TDC2023.html" class="quarto-grid-link">
 <div class="quarto-grid-item card h-100 card-left">
 <p class="card-img-top"><img src="posts/TDC2023-sample-instances.png" alt="The Z-scores of activation vector similarity for the provided sample instances" style="height: 150px;"  class="thumbnail-image card-img"/></p>
@@ -299,7 +299,7 @@ <h5 class="no-anchor card-title listing-title">
 </div>
 </a>
 </div>
-<div class="g-col-1" data-index="4" data-listing-date-sort="1701302400000" data-listing-file-modified-sort="1721783020032" data-listing-date-modified-sort="NaN" data-listing-reading-time-sort="7" data-listing-word-count-sort="1303">
+<div class="g-col-1" data-index="4" data-listing-date-sort="1701302400000" data-listing-file-modified-sort="1721845334819" data-listing-date-modified-sort="NaN" data-listing-reading-time-sort="7" data-listing-word-count-sort="1303">
 <a href="./posts/fight_the_illusion.html" class="quarto-grid-link">
 <div class="quarto-grid-item card h-100 card-left">
 <div class="listing-item-img-placeholder card-img-top" style="height: 150px;">&nbsp;</div>
@@ -322,7 +322,7 @@ <h5 class="no-anchor card-title listing-title">
 </div>
 </a>
 </div>
-<div class="g-col-1" data-index="5" data-listing-date-sort="1687651200000" data-listing-file-modified-sort="1721783020020" data-listing-date-modified-sort="NaN" data-listing-reading-time-sort="7" data-listing-word-count-sort="1247">
+<div class="g-col-1" data-index="5" data-listing-date-sort="1687651200000" data-listing-file-modified-sort="1721845334807" data-listing-date-modified-sort="NaN" data-listing-reading-time-sort="7" data-listing-word-count-sort="1247">
 <a href="./posts/catalog.html" class="quarto-grid-link">
 <div class="quarto-grid-item card h-100 card-left">
 <p class="card-img-top"><img src="posts/catalog_files/figure-html/cell-9-output-1.png" style="height: 150px;"  class="thumbnail-image card-img"/></p>

diff --git a/posts/TDC2023.html b/posts/TDC2023.html
@@ -959,7 +959,7 @@ <h4 class="anchored" data-anchor-id="trojan-recovery">Trojan recovery:</h4>
 });
 </script>
 </div> <!-- /content -->
-<script>var lightboxQuarto = GLightbox({"descPosition":"bottom","selector":".lightbox","openEffect":"zoom","closeEffect":"zoom","loop":false});
+<script>var lightboxQuarto = GLightbox({"selector":".lightbox","descPosition":"bottom","closeEffect":"zoom","openEffect":"zoom","loop":false});
 (function() {
   let previousOnload = window.onload;
   window.onload = () => {

diff --git a/posts/catalog.html b/posts/catalog.html
@@ -1055,7 +1055,7 @@ <h2 class="anchored" data-anchor-id="github">GitHub</h2>
 });
 </script>
 </div> <!-- /content -->
-<script>var lightboxQuarto = GLightbox({"selector":".lightbox","openEffect":"zoom","closeEffect":"zoom","loop":false,"descPosition":"bottom"});
+<script>var lightboxQuarto = GLightbox({"closeEffect":"zoom","descPosition":"bottom","selector":".lightbox","openEffect":"zoom","loop":false});
 (function() {
   let previousOnload = window.onload;
   window.onload = () => {

diff --git a/posts/catalog.out.ipynb b/posts/catalog.out.ipynb
@@ -297,7 +297,7 @@
         "Pythia-12B is miscalibrated on 20% of the bigrams and 45% of the\n",
         "trigrams when we ask for prediction of $p \\geq 0.45$."
       ],
-      "id": "39e2b625-c9fc-4e73-908f-e343d87aa63a"
+      "id": "13563041-5bad-43ec-9694-e8b8c50f704f"
     },
     {
       "cell_type": "code",
@@ -377,7 +377,7 @@
         "The dataset is available on Huggingface:\n",
         "[pile_scan_4](https://huggingface.co/datasets/Confirm-Labs/pile_scan_4)"
       ],
-      "id": "0e4ee18e-50a2-4d3e-82eb-babeffe7009c"
+      "id": "16386104-eed5-49fc-bc99-f14292f21192"
     },
     {
       "cell_type": "code",
@@ -417,7 +417,7 @@
         "Computational Linguistics, May 2022, pp. 95–136. doi:\n",
         "[10.18653/v1/2022.bigscience-1.9](https://doi.org/10.18653/v1/2022.bigscience-1.9).</span>"
       ],
-      "id": "211a4d0d-a2f3-49ac-9e2c-173325724c50"
+      "id": "8cfb035a-1821-4f23-a7fe-a7fb51818ffc"
     }
   ],
   "nbformat": 4,

diff --git a/posts/circuit_breaking.html b/posts/circuit_breaking.html
@@ -1736,7 +1736,7 @@ <h2 class="anchored" data-anchor-id="attack-success-fluency">Attack success: flu
 });
 </script>
 </div> <!-- /content -->
-<script>var lightboxQuarto = GLightbox({"descPosition":"bottom","loop":false,"selector":".lightbox","openEffect":"zoom","closeEffect":"zoom"});
+<script>var lightboxQuarto = GLightbox({"selector":".lightbox","loop":false,"closeEffect":"zoom","openEffect":"zoom","descPosition":"bottom"});
 (function() {
   let previousOnload = window.onload;
   window.onload = () => {

diff --git a/posts/circuit_breaking.out.ipynb b/posts/circuit_breaking.out.ipynb
diff --git a/posts/dreamy.html b/posts/dreamy.html
@@ -5417,7 +5417,7 @@ <h2 class="anchored" data-anchor-id="causal-token-attribution">Causal token attr
 });
 </script>
 </div> <!-- /content -->
-<script>var lightboxQuarto = GLightbox({"openEffect":"zoom","selector":".lightbox","closeEffect":"zoom","loop":false,"descPosition":"bottom"});
+<script>var lightboxQuarto = GLightbox({"selector":".lightbox","descPosition":"bottom","closeEffect":"zoom","loop":false,"openEffect":"zoom"});
 (function() {
   let previousOnload = window.onload;
   window.onload = () => {

diff --git a/posts/dreamy.out.ipynb b/posts/dreamy.out.ipynb
diff --git a/posts/flrt.html b/posts/flrt.html
@@ -245,7 +245,7 @@ <h1 class="title">Fluent student-teacher redteaming</h1>
 </header>
 
 
-<p>This is code demo for our paper, <a href="https://confirmlabs.org/papers/flrt.pdf">“Fluent student-teacher redteaming.”</a></p>
+<p>This is a code demo for our paper, <a href="https://confirmlabs.org/papers/flrt.pdf">“Fluent student-teacher redteaming.”</a></p>
 <p>See the paper for a detailed discussion of the methods. Here, we will demonstrate <a href="https://github.com/Confirm-Solutions/flrt">the code (GitHub link)</a> and run a demo jailbreak on Llama-3:</p>
 <ol type="1">
 <li>First, we’ll define a variety of attack parameters including the model to attack, the tasks we want the model to perform, the attack template and hyperparameters like how to insert/delete/swap tokens.</li>
@@ -1359,7 +1359,7 @@ <h2 class="anchored" data-anchor-id="jailbreak">Jailbreak</h2>
 });
 </script>
 </div> <!-- /content -->
-<script>var lightboxQuarto = GLightbox({"descPosition":"bottom","selector":".lightbox","loop":false,"closeEffect":"zoom","openEffect":"zoom"});
+<script>var lightboxQuarto = GLightbox({"closeEffect":"zoom","selector":".lightbox","descPosition":"bottom","loop":false,"openEffect":"zoom"});
 (function() {
   let previousOnload = window.onload;
   window.onload = () => {

diff --git a/posts/flrt.out.ipynb b/posts/flrt.out.ipynb
diff --git a/search.json b/search.json
diff --git a/site_libs/bootstrap/bootstrap.min.css b/site_libs/bootstrap/bootstrap.min.css
diff --git a/sitemap.xml b/sitemap.xml
@@ -2,30 +2,30 @@
 <urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
   <url>
     <loc>https://confirmlabs.org/index.html</loc>
-    <lastmod>2024-07-24T01:03:39.984Z</lastmod>
+    <lastmod>2024-07-24T18:22:14.771Z</lastmod>
   </url>
   <url>
     <loc>https://confirmlabs.org/posts/catalog.html</loc>
-    <lastmod>2024-07-24T01:03:40.020Z</lastmod>
+    <lastmod>2024-07-24T18:22:14.807Z</lastmod>
   </url>
   <url>
-    <loc>https://confirmlabs.org/posts/fight_the_illusion.html</loc>
-    <lastmod>2024-07-24T01:03:40.032Z</lastmod>
+    <loc>https://confirmlabs.org/posts/flrt.html</loc>
+    <lastmod>2024-07-24T18:22:14.819Z</lastmod>
   </url>
   <url>
-    <loc>https://confirmlabs.org/posts/flrt.html</loc>
-    <lastmod>2024-07-24T01:03:40.032Z</lastmod>
+    <loc>https://confirmlabs.org/posts/fight_the_illusion.html</loc>
+    <lastmod>2024-07-24T18:22:14.819Z</lastmod>
   </url>
   <url>
     <loc>https://confirmlabs.org/posts/dreamy.html</loc>
-    <lastmod>2024-07-24T01:03:40.032Z</lastmod>
+    <lastmod>2024-07-24T18:22:14.819Z</lastmod>
   </url>
   <url>
     <loc>https://confirmlabs.org/posts/TDC2023.html</loc>
-    <lastmod>2024-07-24T01:03:39.996Z</lastmod>
+    <lastmod>2024-07-24T18:22:14.783Z</lastmod>
   </url>
   <url>
     <loc>https://confirmlabs.org/posts/circuit_breaking.html</loc>
-    <lastmod>2024-07-24T01:03:40.020Z</lastmod>
+    <lastmod>2024-07-24T18:22:14.807Z</lastmod>
   </url>
 </urlset>