diff --git a/GPy/core/model.py b/GPy/core/model.py
index 6d90e13a..0990e7f1 100644
--- a/GPy/core/model.py
+++ b/GPy/core/model.py
@@ -302,7 +302,7 @@ class Model(Parameterized):
             denominator = (2 * np.dot(dx, gradient))
             global_ratio = (f1 - f2) / np.where(denominator==0., 1e-32, denominator)
 
-            return np.abs(1. - global_ratio) < tolerance)
+            return np.abs(1. - global_ratio) < tolerance
         else:
             # check the gradient of each parameter individually, and do some pretty printing
             try:
diff --git a/GPy/core/sparse_gp.py b/GPy/core/sparse_gp.py
index 23f8e690..d137ceff 100644
--- a/GPy/core/sparse_gp.py
+++ b/GPy/core/sparse_gp.py
@@ -60,7 +60,7 @@ class SparseGP(GP):
             dL_dKmm = self.grad_dict.pop('dL_dKmm')
             self.kern.update_gradients_full(dL_dKmm, self.Z, None)
             target = self.kern.gradient.copy()
-            self.kern.update_gradients_expectations(variational_posterior=self.X, Z=self.Z, dL_dpsi0=grad_dict['dL_dpsi0'], dL_dpsi1=grad_dict['dL_dpsi1'], dL_dpsi2=grad_dict['dL_dpsi2'])
+            self.kern.update_gradients_expectations(variational_posterior=self.X, Z=self.Z, dL_dpsi0=self.grad_dict['dL_dpsi0'], dL_dpsi1=self.grad_dict['dL_dpsi1'], dL_dpsi2=self.grad_dict['dL_dpsi2'])
             self.kern.gradient += target
 
             #gradients wrt Z
diff --git a/GPy/testing/kernel_tests.py b/GPy/testing/kernel_tests.py
index d54b3871..2a35ad3b 100644
--- a/GPy/testing/kernel_tests.py
+++ b/GPy/testing/kernel_tests.py
@@ -252,7 +252,7 @@ class KernelGradientTestsContinuous(unittest.TestCase):
         k.randomize()
         self.assertTrue(check_kernel_gradient_functions(k, X=self.X, X2=self.X2, verbose=verbose))
 
-#TODO: turn off grad checkingwrt X for indexed kernels liek coregionalize
+#TODO: turn off grad checkingwrt X for indexed kernels like coregionalize
 # class KernelGradientTestsContinuous1D(unittest.TestCase):
 #     def setUp(self):
 #         self.N, self.D = 100, 1
diff --git a/GPy/util/caching.py b/GPy/util/caching.py
index 792d82e2..ea09292a 100644
--- a/GPy/util/caching.py
+++ b/GPy/util/caching.py
@@ -48,7 +48,7 @@ class Cacher(object):
                 if k in kw and kw[k] is not None:
                     return self.operation(*args, **kw)
         # TODO: WARNING !!! Cache OFFSWITCH !!! WARNING
-        return self.operation(*args)
+        #return self.operation(*args)
 
         #if the result is cached, return the cached computation
         state = [all(a is b for a, b in itertools.izip_longest(args, cached_i)) for cached_i in self.cached_inputs]