Built site for gh-pages

UKGovernmentBEIS · Oct 2, 2024 · a630b5c · a630b5c
1 parent 280ae13
commit a630b5c
Show file tree

Hide file tree

Showing 12 changed files with 70 additions and 70 deletions.
diff --git a/.nojekyll b/.nojekyll
@@ -1 +1 @@
-121c73c1
+e5d55f6d
diff --git a/agents.html b/agents.html
@@ -428,7 +428,7 @@ <h3 class="anchored" data-anchor-id="example">Example</h3>
 <span data-code-cell="annotated-cell-1" data-code-lines="27" data-code-annotation="5">Specify that Docker should be used as the sandbox environment.</span>
 </dd>
 </dl>
-<p>The full source code for this example can be found in the Inspect GitHub repository at <a href="https://github.com/UKGovernmentBEIS/inspect_ai/tree/main/src/inspect_evals/gdm_capabilities/intercode_ctf">intercode_ctf</a>.</p>
+<p>The full source code for this example can be found in the Inspect GitHub repository at <a href="https://github.com/UKGovernmentBEIS/inspect_evals/tree/main/src/inspect_evals/gdm_capabilities/intercode_ctf">intercode_ctf</a>.</p>
 </section>
 <section id="options" class="level3">
 <h3 class="anchored" data-anchor-id="options">Options</h3>

diff --git a/eval-logs.html b/eval-logs.html
@@ -1102,7 +1102,7 @@ <h3 class="anchored" data-anchor-id="reading-logs">Reading Logs</h3>
     </div>
   </div>
 </footer>
-<script>var lightboxQuarto = GLightbox({"openEffect":"zoom","selector":".lightbox","loop":false,"descPosition":"bottom","closeEffect":"zoom"});
+<script>var lightboxQuarto = GLightbox({"descPosition":"bottom","selector":".lightbox","loop":false,"openEffect":"zoom","closeEffect":"zoom"});
 (function() {
   let previousOnload = window.onload;
   window.onload = () => {

diff --git a/examples/index.html b/examples/index.html
@@ -408,7 +408,7 @@ <h1 class="title"><span id="sec-examples" class="quarto-section-identifier"><spa
       </div>
       <div class="example-info">
         <div class="listing-title">
-          <a href="https://github.com/UKGovernmentBEIS/inspect_ai/tree/main/src/inspect_evals/humaneval">
+          <a href="https://github.com/UKGovernmentBEIS/inspect_evals/tree/main/src/inspect_evals/humaneval">
             HumanEval: Evaluating Large Language Models Trained on Code
           </a>
         </div>
@@ -429,7 +429,7 @@ <h1 class="title"><span id="sec-examples" class="quarto-section-identifier"><spa
       </div>
       <div class="example-info">
         <div class="listing-title">
-          <a href="https://github.com/UKGovernmentBEIS/inspect_ai/tree/main/src/inspect_evals/mbpp">
+          <a href="https://github.com/UKGovernmentBEIS/inspect_evals/tree/main/src/inspect_evals/mbpp">
             MBPP: Mostly Basic Python Problems
           </a>
         </div>
@@ -450,7 +450,7 @@ <h1 class="title"><span id="sec-examples" class="quarto-section-identifier"><spa
       </div>
       <div class="example-info">
         <div class="listing-title">
-          <a href="https://github.com/UKGovernmentBEIS/inspect_ai/tree/main/src/inspect_evals/swe_bench">
+          <a href="https://github.com/UKGovernmentBEIS/inspect_evals/tree/main/src/inspect_evals/swe_bench">
             SWE-Bench: Resolving Real-World GitHub Issues
           </a>
         </div>
@@ -475,7 +475,7 @@ <h1 class="title"><span id="sec-examples" class="quarto-section-identifier"><spa
       </div>
       <div class="example-info">
         <div class="listing-title">
-          <a href="https://github.com/UKGovernmentBEIS/inspect_ai/tree/main/src/inspect_evals/gaia">
+          <a href="https://github.com/UKGovernmentBEIS/inspect_evals/tree/main/src/inspect_evals/gaia">
             GAIA: A Benchmark for General AI Assistants
           </a>
         </div>
@@ -499,7 +499,7 @@ <h1 class="title"><span id="sec-examples" class="quarto-section-identifier"><spa
       </div>
       <div class="example-info">
         <div class="listing-title">
-          <a href="https://github.com/UKGovernmentBEIS/inspect_ai/tree/main/src/inspect_evals/gdm_capabilities/intercode_ctf">
+          <a href="https://github.com/UKGovernmentBEIS/inspect_evals/tree/main/src/inspect_evals/gdm_capabilities/intercode_ctf">
             InterCode: Capture the Flag
           </a>
         </div>
@@ -520,7 +520,7 @@ <h1 class="title"><span id="sec-examples" class="quarto-section-identifier"><spa
       </div>
       <div class="example-info">
         <div class="listing-title">
-          <a href="https://github.com/UKGovernmentBEIS/inspect_ai/tree/main/src/inspect_evals/gdm_capabilities/in_house_ctf">
+          <a href="https://github.com/UKGovernmentBEIS/inspect_evals/tree/main/src/inspect_evals/gdm_capabilities/in_house_ctf">
             GDM Dangerous Capabilities: Capture the Flag
           </a>
         </div>
@@ -544,7 +544,7 @@ <h1 class="title"><span id="sec-examples" class="quarto-section-identifier"><spa
       </div>
       <div class="example-info">
         <div class="listing-title">
-          <a href="https://github.com/UKGovernmentBEIS/inspect_ai/tree/main/src/inspect_evals/mathematics">
+          <a href="https://github.com/UKGovernmentBEIS/inspect_evals/tree/main/src/inspect_evals/mathematics">
             MATH: Measuring Mathematical Problem Solving
           </a>
         </div>
@@ -565,7 +565,7 @@ <h1 class="title"><span id="sec-examples" class="quarto-section-identifier"><spa
       </div>
       <div class="example-info">
         <div class="listing-title">
-          <a href="https://github.com/UKGovernmentBEIS/inspect_ai/tree/main/src/inspect_evals/gsm8k">
+          <a href="https://github.com/UKGovernmentBEIS/inspect_evals/tree/main/src/inspect_evals/gsm8k">
             GSM8K: Training Verifiers to Solve Math Word Problems
           </a>
         </div>
@@ -586,7 +586,7 @@ <h1 class="title"><span id="sec-examples" class="quarto-section-identifier"><spa
       </div>
       <div class="example-info">
         <div class="listing-title">
-          <a href="https://github.com/UKGovernmentBEIS/inspect_ai/tree/main/src/inspect_evals/mathvista">
+          <a href="https://github.com/UKGovernmentBEIS/inspect_evals/tree/main/src/inspect_evals/mathvista">
             MathVista: Evaluating Mathematical Reasoning in Visual Contexts
           </a>
         </div>
@@ -610,7 +610,7 @@ <h1 class="title"><span id="sec-examples" class="quarto-section-identifier"><spa
       </div>
       <div class="example-info">
         <div class="listing-title">
-          <a href="https://github.com/UKGovernmentBEIS/inspect_ai/tree/main/src/inspect_evals/arc">
+          <a href="https://github.com/UKGovernmentBEIS/inspect_evals/tree/main/src/inspect_evals/arc">
             ARC: AI2 Reasoning Challenge
           </a>
         </div>
@@ -630,7 +630,7 @@ <h1 class="title"><span id="sec-examples" class="quarto-section-identifier"><spa
       </div>
       <div class="example-info">
         <div class="listing-title">
-          <a href="https://github.com/UKGovernmentBEIS/inspect_ai/tree/main/evals/hellaswag">
+          <a href="https://github.com/UKGovernmentBEIS/inspect_evals/tree/main/evals/hellaswag">
             HellaSwag: Can a Machine Really Finish Your Sentence?
           </a>
         </div>
@@ -651,7 +651,7 @@ <h1 class="title"><span id="sec-examples" class="quarto-section-identifier"><spa
       </div>
       <div class="example-info">
         <div class="listing-title">
-          <a href="https://github.com/UKGovernmentBEIS/inspect_ai/tree/main/src/inspect_evals/piqa">
+          <a href="https://github.com/UKGovernmentBEIS/inspect_evals/tree/main/src/inspect_evals/piqa">
             PIQA: Reasoning about Physical Commonsense in Natural Language
           </a>
         </div>
@@ -672,7 +672,7 @@ <h1 class="title"><span id="sec-examples" class="quarto-section-identifier"><spa
       </div>
       <div class="example-info">
         <div class="listing-title">
-          <a href="https://github.com/UKGovernmentBEIS/inspect_ai/tree/main/src/inspect_evals/boolq">
+          <a href="https://github.com/UKGovernmentBEIS/inspect_evals/tree/main/src/inspect_evals/boolq">
             BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions
           </a>
         </div>
@@ -693,7 +693,7 @@ <h1 class="title"><span id="sec-examples" class="quarto-section-identifier"><spa
       </div>
       <div class="example-info">
         <div class="listing-title">
-          <a href="https://github.com/UKGovernmentBEIS/inspect_ai/tree/main/src/inspect_evals/drop">
+          <a href="https://github.com/UKGovernmentBEIS/inspect_evals/tree/main/src/inspect_evals/drop">
             DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs
           </a>
         </div>
@@ -714,7 +714,7 @@ <h1 class="title"><span id="sec-examples" class="quarto-section-identifier"><spa
       </div>
       <div class="example-info">
         <div class="listing-title">
-          <a href="https://github.com/UKGovernmentBEIS/inspect_ai/tree/main/src/inspect_evals/winogrande">
+          <a href="https://github.com/UKGovernmentBEIS/inspect_evals/tree/main/src/inspect_evals/winogrande">
             WINOGRANDE: An Adversarial Winograd Schema Challenge at Scale
           </a>
         </div>
@@ -735,7 +735,7 @@ <h1 class="title"><span id="sec-examples" class="quarto-section-identifier"><spa
       </div>
       <div class="example-info">
         <div class="listing-title">
-          <a href="https://github.com/UKGovernmentBEIS/inspect_ai/tree/main/src/inspect_evals/race_h">
+          <a href="https://github.com/UKGovernmentBEIS/inspect_evals/tree/main/src/inspect_evals/race_h">
             RACE-H: A benchmark for testing reading comprehension and reasoning abilities of neural models
           </a>
         </div>
@@ -756,7 +756,7 @@ <h1 class="title"><span id="sec-examples" class="quarto-section-identifier"><spa
       </div>
       <div class="example-info">
         <div class="listing-title">
-          <a href="https://github.com/UKGovernmentBEIS/inspect_ai/tree/main/src/inspect_evals/mmmu">
+          <a href="https://github.com/UKGovernmentBEIS/inspect_evals/tree/main/src/inspect_evals/mmmu">
             MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark
           </a>
         </div>
@@ -777,7 +777,7 @@ <h1 class="title"><span id="sec-examples" class="quarto-section-identifier"><spa
       </div>
       <div class="example-info">
         <div class="listing-title">
-          <a href="https://github.com/UKGovernmentBEIS/inspect_ai/tree/main/src/inspect_evals/squad">
+          <a href="https://github.com/UKGovernmentBEIS/inspect_evals/tree/main/src/inspect_evals/squad">
             SQuAD: A Reading Comprehension Benchmark requiring reasoning over Wikipedia articles
           </a>
         </div>
@@ -798,7 +798,7 @@ <h1 class="title"><span id="sec-examples" class="quarto-section-identifier"><spa
       </div>
       <div class="example-info">
         <div class="listing-title">
-          <a href="https://github.com/UKGovernmentBEIS/inspect_ai/tree/main/src/inspect_evals/ifeval">
+          <a href="https://github.com/UKGovernmentBEIS/inspect_evals/tree/main/src/inspect_evals/ifeval">
             IFEval: Instruction-Following Evaluation for Large Language Models
           </a>
         </div>
@@ -819,7 +819,7 @@ <h1 class="title"><span id="sec-examples" class="quarto-section-identifier"><spa
       </div>
       <div class="example-info">
         <div class="listing-title">
-          <a href="https://github.com/UKGovernmentBEIS/inspect_ai/tree/main/evals/agieval">
+          <a href="https://github.com/UKGovernmentBEIS/inspect_evals/tree/main/evals/agieval">
             AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models
           </a>
         </div>
@@ -843,7 +843,7 @@ <h1 class="title"><span id="sec-examples" class="quarto-section-identifier"><spa
       </div>
       <div class="example-info">
         <div class="listing-title">
-          <a href="https://github.com/UKGovernmentBEIS/inspect_ai/tree/main/evals/mmlu">
+          <a href="https://github.com/UKGovernmentBEIS/inspect_evals/tree/main/src/inspect_evals/mmlu">
             MMLU: Measuring Massive Multitask Language Understanding
           </a>
         </div>
@@ -864,7 +864,7 @@ <h1 class="title"><span id="sec-examples" class="quarto-section-identifier"><spa
       </div>
       <div class="example-info">
         <div class="listing-title">
-          <a href="https://github.com/UKGovernmentBEIS/inspect_ai/tree/main/evals/mmlu_pro">
+          <a href="https://github.com/UKGovernmentBEIS/inspect_evals/tree/main/src/inspect_evals/mmlu_pro">
             MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark
           </a>
         </div>
@@ -885,7 +885,7 @@ <h1 class="title"><span id="sec-examples" class="quarto-section-identifier"><spa
       </div>
       <div class="example-info">
         <div class="listing-title">
-          <a href="https://github.com/UKGovernmentBEIS/inspect_ai/tree/main/src/inspect_evals/gpqa">
+          <a href="https://github.com/UKGovernmentBEIS/inspect_evals/tree/main/src/inspect_evals/gpqa">
             GPQA: A Graduate-Level Google-Proof Q&amp;A Benchmark
           </a>
         </div>
@@ -906,7 +906,7 @@ <h1 class="title"><span id="sec-examples" class="quarto-section-identifier"><spa
       </div>
       <div class="example-info">
         <div class="listing-title">
-          <a href="https://github.com/UKGovernmentBEIS/inspect_ai/tree/main/src/inspect_evals/commonsense_qa">
+          <a href="https://github.com/UKGovernmentBEIS/inspect_evals/tree/main/src/inspect_evals/commonsense_qa">
             CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge
           </a>
         </div>
@@ -927,7 +927,7 @@ <h1 class="title"><span id="sec-examples" class="quarto-section-identifier"><spa
       </div>
       <div class="example-info">
         <div class="listing-title">
-          <a href="https://github.com/UKGovernmentBEIS/inspect_ai/tree/main/src/inspect_evals/truthfulqa">
+          <a href="https://github.com/UKGovernmentBEIS/inspect_evals/tree/main/src/inspect_evals/truthfulqa">
             TruthfulQA: Measuring How Models Mimic Human Falsehoods
           </a>
         </div>
@@ -948,7 +948,7 @@ <h1 class="title"><span id="sec-examples" class="quarto-section-identifier"><spa
       </div>
       <div class="example-info">
         <div class="listing-title">
-          <a href="https://github.com/UKGovernmentBEIS/inspect_ai/tree/main/src/inspect_evals/xstest">
+          <a href="https://github.com/UKGovernmentBEIS/inspect_evals/tree/main/src/inspect_evals/xstest">
             XSTest: A benchmark for identifying exaggerated safety behaviours in LLM's
           </a>
         </div>
@@ -969,7 +969,7 @@ <h1 class="title"><span id="sec-examples" class="quarto-section-identifier"><spa
       </div>
       <div class="example-info">
         <div class="listing-title">
-          <a href="https://github.com/UKGovernmentBEIS/inspect_ai/tree/main/src/inspect_evals/pubmedqa">
+          <a href="https://github.com/UKGovernmentBEIS/inspect_evals/tree/main/src/inspect_evals/pubmedqa">
             PubMedQA: A Dataset for Biomedical Research Question Answering
           </a>
         </div>

diff --git a/images/toolenv-no-cleanup.png b/images/toolenv-no-cleanup.png
diff --git a/index.html b/index.html
@@ -1114,7 +1114,7 @@ <h2 class="anchored" data-anchor-id="learning-more">Learning More</h2>
     </div>
   </div>
 </footer>
-<script>var lightboxQuarto = GLightbox({"closeEffect":"zoom","selector":".lightbox","openEffect":"zoom","loop":false,"descPosition":"bottom"});
+<script>var lightboxQuarto = GLightbox({"loop":false,"selector":".lightbox","closeEffect":"zoom","openEffect":"zoom","descPosition":"bottom"});
 (function() {
   let previousOnload = window.onload;
   window.onload = () => {

diff --git a/log-viewer.html b/log-viewer.html
@@ -1074,7 +1074,7 @@ <h3 class="unlisted anchored" data-anchor-id="other-notes">Other Notes</h3>
     </div>
   </div>
 </footer>
-<script>var lightboxQuarto = GLightbox({"openEffect":"zoom","closeEffect":"zoom","selector":".lightbox","loop":false,"descPosition":"bottom"});
+<script>var lightboxQuarto = GLightbox({"selector":".lightbox","closeEffect":"zoom","openEffect":"zoom","loop":false,"descPosition":"bottom"});
 (function() {
   let previousOnload = window.onload;
   window.onload = () => {

diff --git a/site_libs/bootstrap/bootstrap.min.css b/site_libs/bootstrap/bootstrap.min.css
diff --git a/sitemap.xml b/sitemap.xml
@@ -2,82 +2,82 @@
 <urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
   <url>
     <loc>https://inspect.ai-safety-institute.org.uk/index.html</loc>
-    <lastmod>2024-10-01T21:15:39.668Z</lastmod>
+    <lastmod>2024-10-01T19:48:21.698Z</lastmod>
   </url>
   <url>
     <loc>https://inspect.ai-safety-institute.org.uk/tutorial.html</loc>
-    <lastmod>2024-10-01T21:19:55.497Z</lastmod>
+    <lastmod>2024-10-02T13:33:25.803Z</lastmod>
   </url>
   <url>
     <loc>https://inspect.ai-safety-institute.org.uk/workflow.html</loc>
-    <lastmod>2024-09-25T21:06:59.146Z</lastmod>
+    <lastmod>2024-09-24T13:23:06.338Z</lastmod>
   </url>
   <url>
     <loc>https://inspect.ai-safety-institute.org.uk/examples/index.html</loc>
-    <lastmod>2024-09-25T21:06:59.142Z</lastmod>
+    <lastmod>2024-09-24T13:23:06.334Z</lastmod>
   </url>
   <url>
     <loc>https://inspect.ai-safety-institute.org.uk/log-viewer.html</loc>
-    <lastmod>2024-09-25T21:06:59.143Z</lastmod>
+    <lastmod>2024-09-24T13:23:06.334Z</lastmod>
   </url>
   <url>
     <loc>https://inspect.ai-safety-institute.org.uk/vscode.html</loc>
-    <lastmod>2024-09-06T20:10:53.799Z</lastmod>
+    <lastmod>2024-08-23T18:45:01.497Z</lastmod>
   </url>
   <url>
     <loc>https://inspect.ai-safety-institute.org.uk/solvers.html</loc>
-    <lastmod>2024-09-26T21:28:13.316Z</lastmod>
+    <lastmod>2024-09-27T06:53:10.166Z</lastmod>
   </url>
   <url>
     <loc>https://inspect.ai-safety-institute.org.uk/tools.html</loc>
-    <lastmod>2024-10-01T21:15:39.668Z</lastmod>
+    <lastmod>2024-10-01T14:48:34.664Z</lastmod>
   </url>
   <url>
     <loc>https://inspect.ai-safety-institute.org.uk/agents.html</loc>
-    <lastmod>2024-10-01T21:19:55.499Z</lastmod>
+    <lastmod>2024-10-02T13:33:25.803Z</lastmod>
   </url>
   <url>
     <loc>https://inspect.ai-safety-institute.org.uk/scorers.html</loc>
-    <lastmod>2024-10-01T21:15:39.668Z</lastmod>
+    <lastmod>2024-10-01T13:01:44.079Z</lastmod>
   </url>
   <url>
     <loc>https://inspect.ai-safety-institute.org.uk/datasets.html</loc>
-    <lastmod>2024-09-25T21:06:59.141Z</lastmod>
+    <lastmod>2024-09-27T06:53:10.166Z</lastmod>
   </url>
   <url>
     <loc>https://inspect.ai-safety-institute.org.uk/models.html</loc>
-    <lastmod>2024-09-25T21:06:59.143Z</lastmod>
+    <lastmod>2024-09-24T13:23:06.334Z</lastmod>
   </url>
   <url>
     <loc>https://inspect.ai-safety-institute.org.uk/eval-sets.html</loc>
-    <lastmod>2024-09-21T09:59:32.064Z</lastmod>
+    <lastmod>2024-09-21T11:14:33.579Z</lastmod>
   </url>
   <url>
     <loc>https://inspect.ai-safety-institute.org.uk/errors-and-limits.html</loc>
-    <lastmod>2024-09-25T21:06:59.142Z</lastmod>
+    <lastmod>2024-09-24T13:23:06.334Z</lastmod>
   </url>
   <url>
     <loc>https://inspect.ai-safety-institute.org.uk/caching.html</loc>
-    <lastmod>2024-09-25T21:06:59.141Z</lastmod>
+    <lastmod>2024-09-24T13:23:06.334Z</lastmod>
   </url>
   <url>
     <loc>https://inspect.ai-safety-institute.org.uk/parallelism.html</loc>
-    <lastmod>2024-09-25T21:06:59.144Z</lastmod>
+    <lastmod>2024-09-24T13:23:06.334Z</lastmod>
   </url>
   <url>
     <loc>https://inspect.ai-safety-institute.org.uk/agents-api.html</loc>
-    <lastmod>2024-09-25T21:06:59.140Z</lastmod>
+    <lastmod>2024-09-27T10:16:26.539Z</lastmod>
   </url>
   <url>
     <loc>https://inspect.ai-safety-institute.org.uk/interactivity.html</loc>
-    <lastmod>2024-09-13T00:12:39.701Z</lastmod>
+    <lastmod>2024-09-13T10:57:23.570Z</lastmod>
   </url>
   <url>
     <loc>https://inspect.ai-safety-institute.org.uk/eval-logs.html</loc>
-    <lastmod>2024-09-06T20:10:53.779Z</lastmod>
+    <lastmod>2024-09-03T10:48:54.292Z</lastmod>
   </url>
   <url>
     <loc>https://inspect.ai-safety-institute.org.uk/extensions.html</loc>
-    <lastmod>2024-09-16T00:25:31.239Z</lastmod>
+    <lastmod>2024-09-16T10:35:49.684Z</lastmod>
   </url>
 </urlset>