diff --git a/GPy/core/gp.py b/GPy/core/gp.py
index cd2f9a97..fc76ad68 100644
--- a/GPy/core/gp.py
+++ b/GPy/core/gp.py
@@ -114,7 +114,7 @@ class GP(Model):
         self._predictive_variable = self.X
 
 
-    def set_XY(self, X=None, Y=None, trigger_update=True):
+    def set_XY(self, X=None, Y=None):
         """
         Set the input / output data of the model
         This is useful if we wish to change our existing data but maintain the same model
@@ -124,7 +124,7 @@ class GP(Model):
         :param Y: output observations
         :type Y: np.ndarray
         """
-        if trigger_update: self.update_model(False)
+        self.update_model(False)
         if Y is not None:
             if self.normalizer is not None:
                 self.normalizer.scale_by(Y)
@@ -140,34 +140,33 @@ class GP(Model):
                     assert isinstance(X, type(self.X)), "The given X must have the same type as the X in the model!"
                     self.unlink_parameter(self.X)
                     self.X = X
-                    self.link_parameters(self.X)
+                    self.link_parameter(self.X)
                 else:
                     self.unlink_parameter(self.X)
                     from ..core import Param
                     self.X = Param('latent mean',X)
-                    self.link_parameters(self.X)
+                    self.link_parameter(self.X)
             else:
                 self.X = ObsAr(X)
-        if trigger_update: self.update_model(True)
-        if trigger_update: self._trigger_params_changed()
+        self.update_model(True)
 
-    def set_X(self,X, trigger_update=True):
+    def set_X(self,X):
         """
         Set the input data of the model
 
         :param X: input observations
         :type X: np.ndarray
         """
-        self.set_XY(X=X, trigger_update=trigger_update)
+        self.set_XY(X=X)
 
-    def set_Y(self,Y, trigger_update=True):
+    def set_Y(self,Y):
         """
         Set the output data of the model
 
         :param X: output observations
         :type X: np.ndarray
         """
-        self.set_XY(Y=Y, trigger_update=trigger_update)
+        self.set_XY(Y=Y)
 
     def parameters_changed(self):
         """
diff --git a/GPy/core/parameterization/param.py b/GPy/core/parameterization/param.py
index 91ce9e24..8fdd744e 100644
--- a/GPy/core/parameterization/param.py
+++ b/GPy/core/parameterization/param.py
@@ -42,7 +42,7 @@ class Param(Parameterizable, ObsAr):
     Multilevel indexing (e.g. self[:2][1:]) is not supported and might lead to unexpected behaviour.
     Try to index in one go, using boolean indexing or the numpy builtin
     np.index function.
-    
+
     See :py:class:`GPy.core.parameterized.Parameterized` for more details on constraining etc.
 
     """
@@ -180,6 +180,7 @@ class Param(Parameterizable, ObsAr):
         import copy
         Pickleable.__setstate__(s, copy.deepcopy(self.__getstate__(), memo))
         return s
+
     def _setup_observers(self):
         """
         Setup the default observers
diff --git a/GPy/models/bayesian_gplvm_minibatch.py b/GPy/models/bayesian_gplvm_minibatch.py
index fcbc166d..0394ff7e 100644
--- a/GPy/models/bayesian_gplvm_minibatch.py
+++ b/GPy/models/bayesian_gplvm_minibatch.py
@@ -107,8 +107,7 @@ class BayesianGPLVMMiniBatch(SparseGPMiniBatch):
             self.X.gradient += self.kern.gradients_X_diag(full_values['dL_dKdiag'], self.X)
 
     def _outer_init_full_values(self):
-        full_values = super(BayesianGPLVMMiniBatch, self)._outer_init_full_values()
-        return full_values
+        return super(BayesianGPLVMMiniBatch, self)._outer_init_full_values()
 
     def parameters_changed(self):
         super(BayesianGPLVMMiniBatch,self).parameters_changed()
@@ -134,6 +133,8 @@ class BayesianGPLVMMiniBatch(SparseGPMiniBatch):
                 d = self.output_dim
                 self._log_marginal_likelihood -= kl_fctr*self.variational_prior.KL_divergence(self.X)*self.stochastics.batchsize/d
 
+        self._Xgrad = self.X.gradient.copy()
+
     def plot_latent(self, labels=None, which_indices=None,
                 resolution=50, ax=None, marker='o', s=40,
                 fignum=None, plot_inducing=True, legend=True,
diff --git a/GPy/models/mrd.py b/GPy/models/mrd.py
index ebb5a960..cb98e1a8 100644
--- a/GPy/models/mrd.py
+++ b/GPy/models/mrd.py
@@ -174,16 +174,15 @@ class MRD(BayesianGPLVMMiniBatch):
             #grad_dict = b.full_values
 
             if self.has_uncertain_inputs():
-                self.X.mean.gradient += b.X.mean.gradient
-                self.X.variance.gradient += b.X.variance.gradient
+                self.X.gradient += b._Xgrad
             else:
-                self.X.gradient += b.X.gradient
+                self.X.gradient += b._Xgrad
 
-        if self.has_uncertain_inputs():
-            # update for the KL divergence
-            self.variational_prior.update_gradients_KL(self.X)
-            self._log_marginal_likelihood -= self.variational_prior.KL_divergence(self.X)
-            pass
+        #if self.has_uncertain_inputs():
+        #    # update for the KL divergence
+        #    self.variational_prior.update_gradients_KL(self.X)
+        #    self._log_marginal_likelihood -= self.variational_prior.KL_divergence(self.X)
+        #    pass
 
     def log_likelihood(self):
         return self._log_marginal_likelihood
diff --git a/GPy/testing/pickle_tests.py b/GPy/testing/pickle_tests.py
index fd1bf93c..64357b39 100644
--- a/GPy/testing/pickle_tests.py
+++ b/GPy/testing/pickle_tests.py
@@ -20,6 +20,8 @@ from GPy.examples.dimensionality_reduction import mrd_simulation
 from GPy.core.parameterization.variational import NormalPosterior
 from GPy.models.gp_regression import GPRegression
 from functools import reduce
+from GPy.util.caching import Cacher
+from pickle import PicklingError
 
 def toy_model():
     X = np.linspace(0,1,50)[:, None]
@@ -205,23 +207,6 @@ class Test(ListDictTestCase):
     def _callback(self, what, which):
         what.count += 1
 
-    @unittest.skip
-    def test_add_observer(self):
-        par = toy_model()
-        par.name = "original"
-        par.count = 0
-        par.add_observer(self, self._callback, 1)
-        pcopy = GPRegression(par.X.copy(), par.Y.copy(), kernel=par.kern.copy())
-        self.assertNotIn(par.observers[0], pcopy.observers)
-        pcopy = par.copy()
-        pcopy.name = "copy"
-        self.assertTrue(par.checkgrad())
-        self.assertTrue(pcopy.checkgrad())
-        self.assertTrue(pcopy.kern.checkgrad())
-        import ipdb;ipdb.set_trace()
-        self.assertIn(par.observers[0], pcopy.observers)
-        self.assertEqual(par.count, 3)
-        self.assertEqual(pcopy.count, 6) # 3 of each call to checkgrad
 
 if __name__ == "__main__":
     #import sys;sys.argv = ['', 'Test.test_parameter_index_operations']
diff --git a/GPy/util/caching.py b/GPy/util/caching.py
index 65f608bf..cbc1f3f1 100644
--- a/GPy/util/caching.py
+++ b/GPy/util/caching.py
@@ -3,6 +3,7 @@
 from ..core.parameterization.observable import Observable
 import collections, weakref
 from functools import reduce
+from pickle import PickleError
 
 class Cacher(object):
     def __init__(self, operation, limit=5, ignore_args=(), force_kwargs=()):
@@ -149,10 +150,10 @@ class Cacher(object):
         return Cacher(self.operation, self.limit, self.ignore_args, self.force_kwargs)
 
     def __getstate__(self, memo=None):
-        raise NotImplementedError("Trying to pickle Cacher object with function {}, pickling functions not possible.".format(str(self.operation)))
+        raise PickleError("Trying to pickle Cacher object with function {}, pickling functions not possible.".format(str(self.operation)))
 
     def __setstate__(self, memo=None):
-        raise NotImplementedError("Trying to pickle Cacher object with function {}, pickling functions not possible.".format(str(self.operation)))
+        raise PickleError("Trying to pickle Cacher object with function {}, pickling functions not possible.".format(str(self.operation)))
 
     @property
     def __name__(self):