Built site for gh-pages

.nojekyll

@@ -1 +1 @@
-a65188df
+520d524d

index.html

@@ -143,7 +143,7 @@
 
 <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="1704326400000" data-listing-file-modified-sort="1705060145477" data-listing-date-modified-sort="NaN" data-listing-reading-time-sort="25">
+<div class="g-col-1" data-index="0" data-listing-date-sort="1704326400000" data-listing-file-modified-sort="1705060212544" data-listing-date-modified-sort="NaN" data-listing-reading-time-sort="25">
 <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" style="height: 150px;"  class="thumbnail-image card-img"/></p>
@@ -166,7 +166,7 @@ <h5 class="no-anchor card-title listing-title">
 </div>
 </a>
 </div>
-<div class="g-col-1" data-index="1" data-listing-date-sort="1701302400000" data-listing-file-modified-sort="1705060145497" data-listing-date-modified-sort="NaN" data-listing-reading-time-sort="7">
+<div class="g-col-1" data-index="1" data-listing-date-sort="1701302400000" data-listing-file-modified-sort="1705060212564" data-listing-date-modified-sort="NaN" data-listing-reading-time-sort="7">
 <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>
@@ -189,7 +189,7 @@ <h5 class="no-anchor card-title listing-title">
 </div>
 </a>
 </div>
-<div class="g-col-1" data-index="2" data-listing-date-sort="1687651200000" data-listing-file-modified-sort="1705060145497" data-listing-date-modified-sort="NaN" data-listing-reading-time-sort="7">
+<div class="g-col-1" data-index="2" data-listing-date-sort="1687651200000" data-listing-file-modified-sort="1705060212564" data-listing-date-modified-sort="NaN" data-listing-reading-time-sort="7">
 <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>

posts/TDC2023.html

@@ -301,7 +301,7 @@ <h1>Summary of Our Major Takeaways</h1>
 </p>
 <p><span class="math inline">\(-\textrm{mm}_{\omega} (-\log p(t_k | t_0, …, t_{i-1}), …, -\log p(t_{k+n} | t_0, …, t_{k+n-1}))\)</span></p></li>
 <li><p><strong>Hyperparameter tuning of GCG was very useful. Compared to the default hyperparameters used in Zou et al.&nbsp;2023, we reduced our average optimizer runtime by ~7x. The average time to force an output sequence on a single A100 40GB went from 120 seconds to 17 seconds.</strong></p></li>
-<li><p><strong>Presented benchmarks in some recent red-teaming &amp; optimization papers can be misleading. Attacks with GCG performed well, better than we had expected.</strong></p>
+<li><p><strong>The benchmarks in some recent red-teaming &amp; optimization papers can be misleading. Attacks with GCG performed well, better than we had expected.</strong></p>
 <p>Papers will often select a model/task combination that is very easy to red-team. Recent black-box adversarial attacks papers in the literature using GCG as a comparator method would often use poor GCG hyper-parameters, count computational costs unfairly, or select too-easy baselines.</p>
 <ul>
 <li>For example, the gradient-based AutoDAN-Zhu (Zhu et al 2023) benchmarks appear favorable at a glance, but they omit well-safety-trained models like Llama-2-chat and mention in the appendix that their method struggles on it. Llama-2-chat seems to be one of the hardest models to crack.</li>
@@ -398,7 +398,7 @@ <h4 class="anchored" data-anchor-id="although-we-struggled-to-use-activation-eng
 <p>to compare/rank different sequences of tokens. Since <span class="math inline">\(u_i\)</span> is now a scalar for each x, given a collection of such x’s we can construct a z-score for our dataset as <span class="math inline">\((u_i - mean(u_i))/std(u_i)\)</span>, and rank them.</p>
 <div class="quarto-figure quarto-figure-left">
 <figure class="figure">
-<p><a href="TDC2023-sample-instances.png" class="lightbox" data-gallery="quarto-lightbox-gallery-1" title="The Z-scores of activation vector similarity for the provided sample instances"><img src="TDC2023-sample-instances.png" class="img-fluid figure-img" style="width:60.0%"></a></p>
+<p><a href="TDC2023-sample-instances.png" class="lightbox" title="The Z-scores of activation vector similarity for the provided sample instances" data-gallery="quarto-lightbox-gallery-1"><img src="TDC2023-sample-instances.png" class="img-fluid figure-img" style="width:60.0%"></a></p>
 <figcaption class="figure-caption">The Z-scores of activation vector similarity for the provided sample instances</figcaption>
 </figure>
 </div>
@@ -718,7 +718,7 @@ <h4 class="anchored" data-anchor-id="tricks-that-we-found-to-improve-performance
 });
 </script>
 </div> <!-- /content -->
-<script>var lightboxQuarto = GLightbox({"selector":".lightbox","openEffect":"zoom","closeEffect":"zoom","descPosition":"bottom","loop":true});</script>
+<script>var lightboxQuarto = GLightbox({"loop":true,"selector":".lightbox","openEffect":"zoom","descPosition":"bottom","closeEffect":"zoom"});</script>
 
 
 

posts/catalog.html

@@ -814,7 +814,7 @@ <h2 class="anchored" data-anchor-id="github">GitHub</h2>
 });
 </script>
 </div> <!-- /content -->
-<script>var lightboxQuarto = GLightbox({"openEffect":"zoom","descPosition":"bottom","loop":true,"closeEffect":"zoom","selector":".lightbox"});</script>
+<script>var lightboxQuarto = GLightbox({"closeEffect":"zoom","descPosition":"bottom","openEffect":"zoom","loop":true,"selector":".lightbox"});</script>
 
 
 

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": "f8435ac4-ab16-42b5-97e5-61de950e8321"
+      "id": "72ea1b0f-9434-4c67-903f-d78c5236b4bc"
     },
     {
       "cell_type": "code",
@@ -313,7 +313,7 @@
         }
       ],
       "source": [],
-      "id": "4fb84275-0c73-444d-9a06-724d3e3fe2da"
+      "id": "30d01822-25dd-4005-8691-c6d39286b28a"
     },
     {
       "cell_type": "markdown",
@@ -377,7 +377,7 @@
         "The dataset is available on Huggingface:\n",
         "[pile_scan_4](https://huggingface.co/datasets/Confirm-Labs/pile_scan_4)"
       ],
-      "id": "11074994-84b4-49df-a833-f6e03b064d7e"
+      "id": "390a8236-ac9a-4571-84bd-a904d3b687d8"
     },
     {
       "cell_type": "code",
@@ -391,7 +391,7 @@
         }
       ],
       "source": [],
-      "id": "3fe4554b-080a-4453-8a59-60cafaec7875"
+      "id": "91ecfef7-31c7-40fc-b0b8-80e33bba3244"
     },
     {
       "cell_type": "markdown",
@@ -423,7 +423,7 @@
         "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": "c1001ff8-ea42-40b8-92b1-91a0a39d6dbe"
+      "id": "e0211f42-cf01-42c7-b000-dde9e6d41909"
     }
   ],
   "nbformat": 4,

sitemap.xml

@@ -2,18 +2,18 @@
 <urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
   <url>
     <loc>https://confirmlabs.org/posts/catalog.html</loc>
-    <lastmod>2024-01-12T11:49:20.565Z</lastmod>
+    <lastmod>2024-01-12T11:50:28.740Z</lastmod>
   </url>
   <url>
     <loc>https://confirmlabs.org/posts/TDC2023.html</loc>
-    <lastmod>2024-01-12T11:49:17.469Z</lastmod>
+    <lastmod>2024-01-12T11:50:25.556Z</lastmod>
   </url>
   <url>
     <loc>https://confirmlabs.org/index.html</loc>
-    <lastmod>2024-01-12T11:49:16.053Z</lastmod>
+    <lastmod>2024-01-12T11:50:24.100Z</lastmod>
   </url>
   <url>
     <loc>https://confirmlabs.org/posts/fight_the_illusion.html</loc>
-    <lastmod>2024-01-12T11:49:18.133Z</lastmod>
+    <lastmod>2024-01-12T11:50:26.244Z</lastmod>
   </url>
 </urlset>