diff --git a/DESCRIPTION b/DESCRIPTION
index 95b8a0f..5e194a3 100644
--- a/DESCRIPTION
+++ b/DESCRIPTION
@@ -1,7 +1,7 @@
 Package: arf
 Title: Adversarial Random Forests
-Version: 0.2.3
-Date: 2024-11-07
+Version: 0.2.4
+Date: 2025-02-23
 Authors@R: 
     c(person(given = "Marvin N.",
              family = "Wright",
diff --git a/NEWS.md b/NEWS.md
index 874ca72..53b6b88 100644
--- a/NEWS.md
+++ b/NEWS.md
@@ -1,3 +1,6 @@
+# arf 0.2.4
+* Let verbose=FALSE silence (some) warnings
+
 # arf 0.2.3
 * Add impute() function for direct missing data imputation with ARF
 * Add one-line functions darf(), earf(), rarf()
diff --git a/todo.R b/todo.R
deleted file mode 100644
index e3f056c..0000000
--- a/todo.R
+++ /dev/null
@@ -1,23 +0,0 @@
-# Hexsticker: https://github.com/GuangchuangYu/hexSticker 
-
-# Allow arbitrary queries for total evidence, marginals, MAP, etc.
-# e.g. p(x1), p(x1, x2), p(x1 | x2). Problem: need to accommodate both
-# equalities and inequalities on either side of the conditioning bar.
-# Also conjunctions and disjunctions.
-
-# Add conditional sampling option to forge
-
-# Add methods for data imputation
-
-# Other exponential family options, with normalization constant?
-
-# Add KDE option?
-
-# Idea: let each tree have its own synthetic dataset?
-
-# Bayesian version with some prior? Could help with zero-density events when
-# a level is unobserved, for instance, without being ruled out per se.
-
-# Localized version, where we only regrow nodes that split too well
-
-# Fully adversarial with alternating rounds at each node?
\ No newline at end of file