The Atomic Playboy and the Radiation Romeo

The button below will open a new browser window displaying the Flash interface for Atomic and Romeo (Version 16 with Preloader). You will find a page of introductory text, some instructions and then the interface where you can suggest a topic for conversation.

This version 16 uses the landscape layout, updates the heckler and end-of-conversation functions with an audio sign-off. All the features from previous versions remain - scroll bar control,custId variable allows me to better log and track conversations.

The chat-bots are hosted on the Pandorabots server under the Shared Service subscription. Please note, the terms of the Updated Policy Guidelines for Free Community Server state that the “Use of automated scripts to make your pandorabot talk to itself or another bot or script” is proscribed (Pandorabots 2011). This project is being developed with the agreement of the Pandorabots Inc management and we would like to acknowledge their support. ( Pandorabots )

Please leave a comment...

After you have had a play with Atomic and Romeo please use this link to leave a comment.
Maybe you could suggest a topic of conversation or a layout suggestion.
All suggestions gratefully received.

Friday, July 27, 2012

All comments welcome.

I've added a new permanent section above inviting comments on Atomic and Romeo. All feedback will be gratefully received.
Want to suggest a topic of conversation? This is the place to do it.
Comment on their performance? Likewise, this is the place to do it.
What about the interface or layout? Again, this is the place to do it.


Tom Clark said...

Cheers Michael. I am having another look at the bots now. Most inputs draw Atomic's first response, 'I have no answer for that,' but then the interest starts with the variety of paths down which an unanswered may veer. Tom C

SusanK said...

Hmmmm.. used the chat bots, firstly I miss typed the first word got the 'a' instead of 'o' in 'how' - sadly the chat bots are not dyslexic. Then I used olympics and pie-drive and got the same initial reply... hmmm... I wanted more humour... I'll try again

SusanK said...

Well I even tried a topic that they may know - given that I know the creator - I went with Dogs as in 'Dogs are fun' and I got the same response 'I have no answer for that'. If it really is Dr Atomic, then I think he may have forged his PhD? I liked the Will Robison reference and C3PO too...

Also the interface and it's functions all work beautifully, but then I would expect that of Will Robinson!

David C. said...

I tried them on a couple of topics and they sound almost believable (i.e. like humans). Although they get off topic pretty quickly and do repeat themselves. But a great program - a new twist on the Turing test - I love it!


John Hannon said...

Hi Michael, I just had a go at the latest interface of the bots, and it seems to work really well technically and as a user experience.
Since you are inviting the world to try and comment, perhaps an invitational sentence at the top of the blogspot page can help to orientate the user to the project - eg. invite them to do what with the bots, to start with. This may be useful in giving the user a stake and inviting comments.

Paul O'Keeffe said...

Hi Michael. As a complete novice to this kind of entertainment parts were interesting and others a little left wondering. As others have stated your bot's response to my question "I have no answer for that" if he is a PhD shouldn't he be able come up with at least one or two different responses IE you want to know about "question" you have got to be frig-gin joking and then of they go in there spiel. On the whole it was entertaining. I would liked to have had some of the come backs in high school.
Keep going Paul

Chris Lawrence said...

It's coming along, Michael. :)

As a first impression, however, there were a couple of unmet expectations and couple of UI misunderstandings that I encountered.

After the intro and build-up, I expected it to be a little more responsive and interactive (and ultimately, fun!). The dialogue that I got didn't seem related to the topic I provided at all. After a couple of goes, I basically concluded that I could probably just mash the keyboard with my forehead and get a similar result. I think I also felt a little disappointed that there wasn't any sound or imagery.

It took me a while to work out how to use the heckle feature. I initially just typed out the heckle I wanted and then pressed the button, which simply cleared the heckle field and stopped the dialogue. I thought an error had occurred and so closed the window and opened it again. It wasn't until I read the fine-print that I used it properly. Even with it working, I didn't feel I really had any chance of upsetting or insulting either of them (game over).

There's definitely a lot of potential there though, and I didn't experience any notable lag or anything.

Best of luck with the Beta version. :)

Jamie Lewis said...

I do enjoy their "rant" - I feel like I'm reading a marx bros screenplay. I'll be back for more.

Josh said...

This is a really interesting project and I enjoyed playing with your chatbots.

As you mention in your blog entries, there will always be far greater areas about which Atomic knows nothing; perhaps a suggested conversation starter pack a little along the lines of the skit at the end of Monty Python's 'The Meaning of Liff' could help - although I guess you've done that to an extent by mentioning Atomic's expertise regarding Joyce.

Again regarding Atomic's ignorance: I'd like to see an increased repertoire of responses, especially for the early conversational banter. My experience was that there was a pretty rapid incidence towards repetition for the first few lines. Perhaps those opening gambit trees could be increased from 5 to more?

Also, until I perused your blog entries I didn't realise the conversation would stop - I kept thinking my repeated attempts to heckle (which is a fun feature) were breaking the coding somehow.

All in all, double-plus good!

Unknown said...

Hey Josh,

Thanks for the comments - I truly do appreciate them.
You're absolutely correct about needing to write more opening gambits. Also, I'll have to find a better way of letting people know about the effect of the 'heckle'.

Thanks again.

Sam Joseph said...

Hi guys, Any chance we can get you to enter in the funniest computer ever contest:

Janet Fulton said...

Hi Michael

Wasn't quite sure what to expect and after I typed my question in (very boring one) I didn't quite understand the responses.

Maybe I'm getting old but I found the conversation went too fast for me so I had to go back and reread the first postings.

And then I laughed.

PS I may have broken it or made Atomic cranky. I heckled twice and after the second one he went away :)

Melanie said...

Hi Michael, this was interesting. My first effort was a typo and the two characters went on anyway, not referring to the topic typed in error. I stopped and started a new topic and pretty much got the same convo and they didn't mention my topic. My first heckle didn't come up on screen and my second shut down the exchange. Great to have a go of. Thanks for the opp.

PunkRockDrifter said...

I wanted to try this, but being in flash it limits devices, iOS devices don't like, android phone could handle it but the formatting was askew. Will have to wait till I can get home on a pc...

Anonymous said...

Hi, This is recently retired Prof Ken, on the Humor Research Listserv. Over the years I learned a lot of Flash from they have programs that teach ActinScript to optimize Flash Programs for mobile devices. I suggest this rather as background info for the dissertation than something for you to personally learn.


Really cool Mike. The script (or, performance?) that results flows really well and has many genuinely funny (laugh out loud) moments, for me. It really does give the impression of a straight man/funny man comedy duo, engaging in banter.

Also, having had a little bit of a play with Pandora chatbots and AIML myself, I can appreciate the amount of work it probably took to get it all looking and working this well. Very impressed, well done.

The heckling feature was pretty remarkable too, offering the chance for interactivity. They (Atomic & Romeo) seemed to deal well with the heckling, and then segued nicely back into the routine. All felt realistic and very effective.

My only tech issue was that the window when it first opened (on my laptop pc, using IE) wasn't wide enough to allow me to hit NEXT but I finally rightclicked and it `show full' and it fixed the issue.

Anyway well done.

And if you get a chance, enjoy the trailer for HAIRY BALLS:
(I work for this company sometimes)
ie Q: How many people work at your company?
A: Oh, about half of them.

Unknown said...

Hey mate, back again. :)

Couple of comments:
• If I make a mistake in the topic field and click into the field again to correct it, the whole field clears and I have to type it all out again.
• When starting a new topic, the main dialogue frame constantly jumps between the latest line added and the line at the start of the new topic - makes it hard to read/follow.
• Typing in the word "PhD" was the only time I managed to influence the subject matter.
• As soon as I see a repeated conversation, I feel a loss of interest in the whole activity and am very conscious of how scripted it is.
• I felt it was a bit odd that the conversation halted every time I began to type in a heckle rather than ignoring me until I committed to one.

I think it was Shawn Leslie that once said Good design means never having to say “Click Here.” I think this might apply to the 6 steps you list before interacting with the chat-bots. You could probably get rid of the instructions, as most of them are (or could be) implied visually in the way that the interface is presented and operates.

If the entire thing really felt like a chat room (just one input field for me to type into), I think I'd probably have a lot more fun trying to heckle or influence the topic of conversation.

Keep up the great work, mate - it's getting there! :)

susan kerrigan said...

Some of these lines are so corny.. however, I felt that their vocabulary has increased, after 3 goes I still saw new line coming up. Liked the 'I made you say 'underwear'. Can't say why. Also Atomci has a foul mouth, he swore at me.

All good fun

Anonymous said...

Your chatbot is bad and you should feel bad.