diff --git a/Data/Clustering/Hierarchical.hs b/Data/Clustering/Hierarchical.hs
--- a/Data/Clustering/Hierarchical.hs
+++ b/Data/Clustering/Hierarchical.hs
@@ -133,19 +133,19 @@
 
 -- Some cluster distances
 cdistSingleLinkage      :: Ord d => ClusterDistance d
-cdistSingleLinkage      = \_ (_, d1) (_, d2) _ -> d1 `min` d2
+cdistSingleLinkage      = \(_, d1) (_, d2) -> d1 `min` d2
 
 cdistCompleteLinkage    :: Ord d => ClusterDistance d
-cdistCompleteLinkage    = \_ (_, d1) (_, d2) _ -> d1 `max` d2
+cdistCompleteLinkage    = \(_, d1) (_, d2) -> d1 `max` d2
 
 cdistUPGMA              :: Fractional d => ClusterDistance d
-cdistUPGMA              = \_ (b1,d1) (b2,d2) _ ->
+cdistUPGMA              = \(b1,d1) (b2,d2) ->
                             let n1 = fromIntegral (size b1)
                                 n2 = fromIntegral (size b2)
                             in (n1 * d1 + n2 * d2) / (n1 + n2)
 
 cdistFakeAverageLinkage :: Fractional d => ClusterDistance d
-cdistFakeAverageLinkage = \_ (_, d1) (_, d2) _ -> (d1 + d2) / 2
+cdistFakeAverageLinkage = \(_, d1) (_, d2) -> (d1 + d2) / 2
 
 
 -- | /O(n^3)/ Calculates a complete, rooted dendrogram for a list
@@ -200,18 +200,18 @@
       act _noMonomorphismRestrictionPlease = do
         let xs = listArray (1, n) items
         fromDistance (dist `on` (xs !)) n >>= go xs (n-1) IM.empty
-      go xs i ds dm = do
+      go xs i ds dm = xs `seq` i `seq` ds `seq` dm `seq` do
         ((c1,c2), distance) <- findMin dm
         cu <- mergeClusters cdist dm (c1,c2)
         let dendro c = case size c of
-                         1 -> Leaf (xs ! key c)
+                         1 -> Leaf $! xs ! key c
                          _ -> ds IM.! key c
             d1 = dendro c1
             d2 = dendro c2
-            du = Branch distance d1 d2
+            du = d1 `seq` d2 `seq` Branch distance d1 d2
         case i of
           1 -> return du
           _ -> let ds' = IM.insert (key cu) du $
                          IM.delete (key c1) $
                          IM.delete (key c2) ds
-               in go xs (i-1) ds' dm
+               in du `seq` go xs (i-1) ds' dm
diff --git a/Data/Clustering/Hierarchical/Internal/DistanceMatrix.hs b/Data/Clustering/Hierarchical/Internal/DistanceMatrix.hs
--- a/Data/Clustering/Hierarchical/Internal/DistanceMatrix.hs
+++ b/Data/Clustering/Hierarchical/Internal/DistanceMatrix.hs
@@ -86,6 +86,7 @@
       choose b i m' = if m' < snd b then (i, m') else b
       go1 (i:is)   = readArray matrix_ i >>= go2 is . (,) i
       go1 []       = mkErr "findMin: empty DistMatrix"
+      go2 i b | i `seq` b `seq` False = undefined
       go2 (i:is) b = readArray matrix_ i >>= go2 is . choose b i
       go2 []     b = do c1 <- readArray (clusters dm) (fst $ fst b)
                         c2 <- readArray (clusters dm) (snd $ fst b)
@@ -95,11 +96,9 @@
 -- | Type for functions that calculate distances between
 -- clusters.
 type ClusterDistance d =
-       Cluster        -- ^ Cluster A
-    -> (Cluster, d)   -- ^ Cluster B1 and distance from A to B1
+       (Cluster, d)   -- ^ Cluster B1 and distance from A to B1
     -> (Cluster, d)   -- ^ Cluster B2 and distance from A to B2
-    -> Cluster        -- ^ Cluster B = B1 U B2
-    -> d              -- ^ Distance from A to B.
+    -> d              -- ^ Distance from A to (B1 U B2).
 
 
 -- | /O(n)/ Merges two clusters, returning the new cluster and
@@ -120,11 +119,11 @@
   -- Calculate new distances
   activeV <- readSTRef active_
   forM_ activeV $ \k -> when (k `notElem` [b1k, b2k]) $ do
-      a      <- readArray clusters_ k
+      -- a   <- readArray clusters_ k
       d_a_b1 <- readArray matrix_ $ ix k b1k
       d_a_b2 <- readArray matrix_ $ ix k b2k
-      let d = cdist a (b1, d_a_b1) (b2, d_a_b2) bu
-      writeArray matrix_ (ix k km) d
+      let d = cdist (b1, d_a_b1) (b2, d_a_b2)
+      d `seq` writeArray matrix_ (ix k km) d
 
   -- Save new cluster, invalidate old one
   writeArray clusters_ km bu
diff --git a/hierarchical-clustering.cabal b/hierarchical-clustering.cabal
--- a/hierarchical-clustering.cabal
+++ b/hierarchical-clustering.cabal
@@ -1,5 +1,5 @@
 Name:                hierarchical-clustering
-Version:             0.3.0.1
+Version:             0.3.1
 Synopsis:            Algorithms for single, average/UPGMA and complete linkage clustering.
 License:             BSD3
 License-file:        LICENSE
@@ -25,6 +25,12 @@
   the whole matrix on every iteration just to see what the
   minimum is).
   .
+  Changes in version 0.3.1:
+  .
+  * Works with containers 0.4 (thanks, Doug Beardsley).
+  .
+  * Removed some internal unnecessary overheads and added some strictness.
+  .
   Changes in version 0.3.0.1:
   .
   * Listed changes of unreleased version 0.2.
@@ -43,9 +49,15 @@
     useful if you want to create a dendrogram and your distance
     data type isn't an instance of @Floating@.
 
+
+Source-repository head
+  type: darcs
+  location: http://patch-tag.com/r/felipe/hierarchical-clustering
+
+
 Library
   Exposed-modules:
     Data.Clustering.Hierarchical,
     Data.Clustering.Hierarchical.Internal.DistanceMatrix
-  Build-depends: base == 4.*, array == 0.3.*, containers == 0.3.*
+  Build-depends: base == 4.*, array == 0.3.*, containers >= 0.3 && < 0.5
   GHC-options: -Wall