I'm moving this from a post I made that was tied up with suggestions about changing the prompt away from >> to make it more obviously taken as an asymmetric delimiter. This is an interesting feature which can be discussed in its own right...
Let's imagine someone tells you they've set x: 1, and then have the following code:
>> x + 2
== 3
>> print "hi"
hi
Try pasting that today, say, in Red and you will get:
>> >> x + 2
*** Script Error: >> operator is missing an argument
*** Where: catch
*** Stack:
>> == 3
*** Script Error: == operator is missing an argument
*** Where: catch
*** Stack:
>>
>> >> print "hi"
*** Script Error: >> operator is missing an argument
*** Where: catch
*** Stack:
>> hi
*** Script Error: hi has no value
*** Where: catch
*** Stack:
But What If...
...imagine you could go on a website, drag across someone's transcript, and paste it right into your console unedited and have it run.
What I'm talking about is knowing that you are receiving a paste (either by virtue of an API that tells you, or just noticing that the rate at which lines are coming in is faster than a human types...a heuristic I have been meaning to implement so that lines are batched instead of intermixing with the output). And really being able to just paste a console transcript whole cloth, but have it respond by outputting its own complementary transcript.
So now let's say your transcript looked like:
>> x + 2
== 3
>> print "hi"
hi
So if you pasted it into an environment where you'd said x: 10 it would take the data one line at a time, and >> would kick it over into a replay mode
>> x: 10
== 10
>> ; here you do the paste, it sees the >> and kicks over
[[ TRANSCRIPT PASTE DETECTED ]]
( to disable, see http://rebol.info/disable-transcript-paste-detection )
; >> x + 2
; == 3
;
; >> print "hi"
; == hi
[[ REPLAYING TRANSCRIPT ]]
>> x + 2
== 12
>> print "hi"
hi
...Heuristics, hmmm... 
If we keep the current indicators for prompts, e.g. >> and == with ** for errors, then we'd be making heuristic decisions here...since these are all things you can legally use elsewhere.
== is in common use today as an operator, though it rarely appears at the beginning of a line. I intend it to not be an operator, but a divider of some kind. So it actually be contentious, because although == doesn't appear at the start of a line today, it would as a divider. So maybe plain equals, just off by one space?
>> x + 2
= 12
Parity just looks confusing, don't think anyone would get used to it:
>> x + 2
<< 12
Anyway, now that I've outlined this feature, I want it yesterday. The value of such a feature may exceed the value of dedicating <<x>> as some new lexical type for MAP! or similar.