diff --git a/.meta/.readme.rst b/.meta/.readme.rst
index 05509a00..3dfb34f5 100644
--- a/.meta/.readme.rst
+++ b/.meta/.readme.rst
@@ -476,7 +476,7 @@ Nested progress bars
 On Windows `colorama <https://github.com/tartley/colorama>`__ will be used if
 available to keep nested bars on their respective lines.
 
-For manual control over positioning (e.g. for multi-threaded use),
+For manual control over positioning (e.g. for multi-processing use),
 you may specify ``position=n`` where ``n=0`` for the outermost bar,
 ``n=1`` for the next, and so on:
 
@@ -484,7 +484,7 @@ you may specify ``position=n`` where ``n=0`` for the outermost bar,
 
     from time import sleep
     from tqdm import trange, tqdm
-    from multiprocessing import Pool, freeze_support, RLock
+    from multiprocessing import Pool, freeze_support
 
     L = list(range(9))
 
@@ -492,14 +492,39 @@ you may specify ``position=n`` where ``n=0`` for the outermost bar,
         interval = 0.001 / (n + 2)
         total = 5000
         text = "#{}, est. {:<04.2}s".format(n, interval * total)
-        for i in trange(total, desc=text, position=n):
+        for _ in trange(total, desc=text, position=n):
             sleep(interval)
 
     if __name__ == '__main__':
         freeze_support()  # for Windows support
-        p = Pool(len(L), initializer=tqdm.set_lock, initargs=(RLock(),))
+        p = Pool(len(L), initializer=tqdm.set_lock, initargs=(tqdm.get_lock(),))
         p.map(progresser, L)
 
+Note that in python 3, threads do not require manual positioning,
+and ``tqdm.write`` is safe to use:
+
+.. code:: python
+
+    from time import sleep
+    from tqdm import tqdm, trange
+    from concurrent.futures import ThreadPoolExecutor
+
+    L = list(range(9))
+
+    def progresser(n):
+        interval = 0.001 / (n + 2)
+        total = 5000
+        text = "#{}, est. {:<04.2}s".format(n, interval * total)
+        for _ in trange(total, desc=text):
+            sleep(interval)
+        if n == 6:
+            tqdm.write("n == 6 completed.")
+            tqdm.write("`tqdm.write()` is thread-safe in py3!")
+
+    if __name__ == '__main__':
+        with ThreadPoolExecutor() as p:
+            p.map(progresser, L)
+
 Hooks and callbacks
 ~~~~~~~~~~~~~~~~~~~
 
diff --git a/README.rst b/README.rst
index 0c136e7d..9b87cdcb 100644
--- a/README.rst
+++ b/README.rst
@@ -640,7 +640,7 @@ Nested progress bars
 On Windows `colorama <https://github.com/tartley/colorama>`__ will be used if
 available to keep nested bars on their respective lines.
 
-For manual control over positioning (e.g. for multi-threaded use),
+For manual control over positioning (e.g. for multi-processing use),
 you may specify ``position=n`` where ``n=0`` for the outermost bar,
 ``n=1`` for the next, and so on:
 
@@ -648,7 +648,7 @@ you may specify ``position=n`` where ``n=0`` for the outermost bar,
 
     from time import sleep
     from tqdm import trange, tqdm
-    from multiprocessing import Pool, freeze_support, RLock
+    from multiprocessing import Pool, freeze_support
 
     L = list(range(9))
 
@@ -656,14 +656,39 @@ you may specify ``position=n`` where ``n=0`` for the outermost bar,
         interval = 0.001 / (n + 2)
         total = 5000
         text = "#{}, est. {:<04.2}s".format(n, interval * total)
-        for i in trange(total, desc=text, position=n):
+        for _ in trange(total, desc=text, position=n):
             sleep(interval)
 
     if __name__ == '__main__':
         freeze_support()  # for Windows support
-        p = Pool(len(L), initializer=tqdm.set_lock, initargs=(RLock(),))
+        p = Pool(len(L), initializer=tqdm.set_lock, initargs=(tqdm.get_lock(),))
         p.map(progresser, L)
 
+Note that in python 3, threads do not require manual positioning,
+and ``tqdm.write`` is safe to use:
+
+.. code:: python
+
+    from time import sleep
+    from tqdm import tqdm, trange
+    from concurrent.futures import ThreadPoolExecutor
+
+    L = list(range(9))
+
+    def progresser(n):
+        interval = 0.001 / (n + 2)
+        total = 5000
+        text = "#{}, est. {:<04.2}s".format(n, interval * total)
+        for _ in trange(total, desc=text):
+            sleep(interval)
+        if n == 6:
+            tqdm.write("n == 6 completed.")
+            tqdm.write("`tqdm.write()` is thread-safe in py3!")
+
+    if __name__ == '__main__':
+        with ThreadPoolExecutor() as p:
+            p.map(progresser, L)
+
 Hooks and callbacks
 ~~~~~~~~~~~~~~~~~~~
 
diff --git a/examples/parallel_bars.py b/examples/parallel_bars.py
index 65a2073b..b62020a1 100644
--- a/examples/parallel_bars.py
+++ b/examples/parallel_bars.py
@@ -1,38 +1,50 @@
 from __future__ import print_function
 from time import sleep
 from tqdm import tqdm, trange
-from multiprocessing import Pool, freeze_support, RLock
+from multiprocessing import Pool, freeze_support
+from concurrent.futures import ThreadPoolExecutor
+from functools import partial
+import sys
 
 
-L = list(range(9))
+L = list(range(9))[::-1]
 
 
-def progresser(n):
+def progresser(n, auto_position=False):
     interval = 0.001 / (len(L) - n + 2)
     total = 5000
     text = "#{}, est. {:<04.2}s".format(n, interval * total)
-    # NB: ensure position>0 to prevent printing '\n' on completion.
-    # `tqdm` can't automate this since this thread
-    # may not know about other bars in other threads #477.
-    for _ in tqdm(range(total), desc=text, position=n + 1):
+    for _ in tqdm(range(total), desc=text, position=None if auto_position else n):
         sleep(interval)
+    # NB: may not clear instances with higher `position` upon completion
+    # since this worker may not know about other bars #796
+    if auto_position:
+        # we think we know about other bars (currently only py3 threading)
+        if n == 6:
+            tqdm.write("n == 6 completed")
+
+if sys.version_info[:1] > (2,):
+    progresser_thread = partial(progresser, auto_position=True)
+else:
+    progresser_thread = progresser
 
 
 if __name__ == '__main__':
     freeze_support()  # for Windows support
-    p = Pool(len(L),
-             initializer=tqdm.set_lock,
-             initargs=(RLock(),))
+    print("Multi-processing")
+    p = Pool(len(L), initializer=tqdm.set_lock, initargs=(tqdm.get_lock(),))
     p.map(progresser, L)
-    print('\n' * len(L))
 
-    # alternatively, on UNIX, just use the default internal lock
-    p = Pool(len(L))
-    p.map(progresser, L)
-    print('\n' * len(L))
+    # unfortunately need ncols
+    # to print spaces over leftover multi-processing bars (#796)
+    with tqdm(leave=False) as t:
+        ncols = t.ncols or 80
+    print(("{msg:<{ncols}}").format(msg="Multi-threading", ncols=ncols))
 
-    # a manual test demonstrating automatic fix for #477 on one thread
-    for _ in trange(10, desc="1", position=1):
-        for _ in trange(10, desc="2", position=0):
+    with ThreadPoolExecutor(4) as p:
+        p.map(progresser_thread, L)
+
+    print("Manual nesting")
+    for i in trange(16, desc="1"):
+        for _ in trange(16, desc="2 @ %d" % i, leave=i % 2):
             sleep(0.01)
-    print('\n')