Front page.

index.qmd

@@ -17,11 +17,10 @@ We have two ongoing projects:
 adversarial techniques can help with (a) evaluating model capabilities via red-teaming (b) model interpretability (c) providing data and feedback for safety-training pipelines.
 
     Recently, we have built methods for powerful and
-    fluent adversarial attacks. This work is currently being compiled into a paper
-    to be released in Summer 2024. Earlier this year, we published ["Fluent Dreaming for
-    Language Models"](https://arxiv.org/pdf/2402.01702) which combines whitebox
-    optimization with interpretability. We also won a division of the [NeurIPS 2023
-    Trojan Detection Competition](https://confirmlabs.org/posts/TDC2023).
+    fluent adversarial attacks described in ["Fluent Student-teacher Redteaming"](https://confirmlabs.org/papers/flrt.pdf). 
+    Earlier this year, we published ["Fluent Dreaming for Language Models"](https://arxiv.org/pdf/2402.01702)
+    which combines whitebox optimization with interpretability. We also won a
+    division of the [NeurIPS 2023 Trojan Detection Competition](https://confirmlabs.org/posts/TDC2023).
 
 (2) **Pretraining AI editor architectures:** We believe AI inspection of AI
 internals could become a useful component of AI interpretability and oversight.

posts/circuit_breaking.ipynb

@@ -5,7 +5,7 @@
    "metadata": {},
    "source": [
     "---\n",
-    "title: 'Breaking Circuit Breakers'\n",
+    "title: 'Breaking circuit breakers'\n",
     "date: 07/12/2024\n",
     "author:\n",
     "  - name: \n",