diff --git a/GPy/core/model.py b/GPy/core/model.py
index 65a85589..08a4ea25 100644
--- a/GPy/core/model.py
+++ b/GPy/core/model.py
@@ -213,7 +213,7 @@ class Model(Parameterized):
             self.obj_grads = np.clip(self._transform_gradients(self.objective_function_gradients()), -1e10, 1e10)
         return obj_f, self.obj_grads
 
-    def optimize(self, optimizer=None, start=None, messages=False, max_iters=1000, ipython_notebook=False, **kwargs):
+    def optimize(self, optimizer=None, start=None, messages=False, max_iters=1000, ipython_notebook=True, **kwargs):
         """
         Optimize the model using self.log_likelihood and self.log_likelihood_gradient, as well as self.priors.
 
@@ -255,7 +255,7 @@ class Model(Parameterized):
         else:
             optimizer = optimization.get_optimizer(optimizer)
             opt = optimizer(start, model=self, max_iters=max_iters, **kwargs)
-
+                        
         with VerboseOptimization(self, opt, maxiters=max_iters, verbose=messages, ipython_notebook=ipython_notebook) as vo:
             opt.run(f_fp=self._objective_grads, f=self._objective, fp=self._grads)
             vo.finish(opt)
@@ -402,7 +402,7 @@ class Model(Parameterized):
         model_details = [['<b>Model</b>', self.name + '<br>'],
                          ['<b>Log-likelihood</b>', '{}<br>'.format(float(self.log_likelihood()))],
                          ["<b>Number of Parameters</b>", '{}<br>'.format(self.size)],
-                         ["<b>Updates</b>", '{}<br>'.format(self._updates)],
+                         ["<b>Updates</b>", '{}<br>'.format(self._update_on)],
                          ]
         from operator import itemgetter
         to_print = ["""<style type="text/css">
@@ -419,7 +419,7 @@ class Model(Parameterized):
         model_details = [['Name', self.name],
                          ['Log-likelihood', '{}'.format(float(self.log_likelihood()))],
                          ["Number of Parameters", '{}'.format(self.size)],
-                         ["Updates", '{}'.format(self._updates)],
+                         ["Updates", '{}'.format(self._update_on)],
                          ]
         from operator import itemgetter
         max_len = reduce(lambda a, b: max(len(b[0]), a), model_details, 0)
diff --git a/GPy/core/parameterization/updateable.py b/GPy/core/parameterization/updateable.py
index 6abf0280..07083ce0 100644
--- a/GPy/core/parameterization/updateable.py
+++ b/GPy/core/parameterization/updateable.py
@@ -11,7 +11,6 @@ class Updateable(Observable):
     A model can be updated or not.
     Make sure updates can be switched on and off.
     """
-    _updates = True
     def __init__(self, *args, **kwargs):
         super(Updateable, self).__init__(*args, **kwargs)
 
diff --git a/GPy/core/sparse_gp.py b/GPy/core/sparse_gp.py
index ebaf721f..709f800a 100644
--- a/GPy/core/sparse_gp.py
+++ b/GPy/core/sparse_gp.py
@@ -149,7 +149,7 @@ class SparseGP(GP):
 
                 var_ = mdot(la.T, tmp, la)
                 p0 = psi0_star[i]
-                t = self.posterior.woodbury_inv
+                t = np.atleast_3d(self.posterior.woodbury_inv)
                 t2 = np.trace(t.T.dot(psi2_star), axis1=1, axis2=2)
                 
                 if full_cov:
diff --git a/GPy/core/verbose_optimization.py b/GPy/core/verbose_optimization.py
index affa7d43..af64d3a8 100644
--- a/GPy/core/verbose_optimization.py
+++ b/GPy/core/verbose_optimization.py
@@ -11,9 +11,8 @@ def exponents(fnow, current_grad):
     return np.sign(exps) * np.log10(exps).astype(int)
 
 class VerboseOptimization(object):
-    def __init__(self, model, opt, maxiters, verbose=True, current_iteration=0, ipython_notebook=False):
+    def __init__(self, model, opt, maxiters, verbose=False, current_iteration=0, ipython_notebook=True):
         self.verbose = verbose
-        self.ipython_notebook = ipython_notebook
         if self.verbose:
             self.model = model
             self.iteration = current_iteration
@@ -26,13 +25,18 @@ class VerboseOptimization(object):
 
             self.update()
 
-            if self.ipython_notebook:
+            try:
                 from IPython.display import display
                 from IPython.html.widgets import FloatProgressWidget, HTMLWidget, ContainerWidget
                 self.text = HTMLWidget()
                 self.progress = FloatProgressWidget()
                 self.model_show = HTMLWidget()
+                self.ipython_notebook = ipython_notebook
+            except:
+                # Not in Ipython notebook
+                self.ipython_notebook = False
 
+            if self.ipython_notebook:
                 self.text.set_css('width', '100%')
                 #self.progress.set_css('width', '100%')
 
@@ -142,4 +146,5 @@ class VerboseOptimization(object):
             if not self.ipython_notebook:
                 print()
                 print('Optimization finished in {0:.5g} Seconds'.format(self.stop-self.start))
-                print()
+		print('Optimization status: {0:.5g}'.format(self.status))             
+		print()
diff --git a/GPy/inference/latent_function_inference/var_dtc.py b/GPy/inference/latent_function_inference/var_dtc.py
index 1be2557b..a878ed18 100644
--- a/GPy/inference/latent_function_inference/var_dtc.py
+++ b/GPy/inference/latent_function_inference/var_dtc.py
@@ -21,7 +21,7 @@ class VarDTC(LatentFunctionInference):
     For efficiency, we sometimes work with the cholesky of Y*Y.T. To save repeatedly recomputing this, we cache it.
 
     """
-    const_jitter = 1e-6
+    const_jitter = 1e-8
     def __init__(self, limit=1):
         #self._YYTfactor_cache = caching.cache()
         from ...util.caching import Cacher
diff --git a/GPy/inference/latent_function_inference/var_dtc_parallel.py b/GPy/inference/latent_function_inference/var_dtc_parallel.py
index 2816d578..cac69872 100644
--- a/GPy/inference/latent_function_inference/var_dtc_parallel.py
+++ b/GPy/inference/latent_function_inference/var_dtc_parallel.py
@@ -24,7 +24,7 @@ class VarDTC_minibatch(LatentFunctionInference):
     For efficiency, we sometimes work with the cholesky of Y*Y.T. To save repeatedly recomputing this, we cache it.
 
     """
-    const_jitter = 1e-6
+    const_jitter = 1e-8
     def __init__(self, batchsize=None, limit=1, mpi_comm=None):
 
         self.batchsize = batchsize
diff --git a/GPy/testing/pickle_tests.py b/GPy/testing/pickle_tests.py
index d6d6f923..c79e9914 100644
--- a/GPy/testing/pickle_tests.py
+++ b/GPy/testing/pickle_tests.py
@@ -138,8 +138,6 @@ class Test(ListDictTestCase):
         self.assertIsNot(par.gradient_full, pcopy.gradient_full)
         self.assertTrue(pcopy.checkgrad())
         self.assert_(np.any(pcopy.gradient!=0.0))
-        pcopy.optimize('bfgs')
-        par.optimize('bfgs')
         np.testing.assert_allclose(pcopy.param_array, par.param_array, atol=1e-6)
         par.randomize()
         with tempfile.TemporaryFile('w+b') as f: