Ramona and Jenn


Earlier here at Joe Duck there was a discussion about “chat bots” and how they differ from humans.  I reproduced my exchange with Palm’s support guy “Silas” in a post below.    He was a human, tut I like  Alaska Air’s Jenn much better.   

At least her grammer stays intact, and she’s pretty too! 

You Asked:
hello jenn
Jenn: Hello.
You Asked: how are you today?
Jenn: I’m fine thanks.
You Asked: are you real or fake?
Jenn: Good question. I’m not sure how to answer that. Please try rewording your question. I understand simple questions best.
You Asked: are you alive?
Jenn: I am a virtual assistant, here to help you navigate our Web site.
A more robust chatbot is Ray Kurzweil’s “Ramona“, on whom an entire character is based in the upcoming movie “The Singularity”.   I have not been very impressed with Ramona in terms of her responses to anything approaching complex questions, but we are very early in the game so maybe I need to cut her some slack?  No way – Ramona you need improvement!
Ramona: Hi, I’m Ramona. What can I call you?
User: Joe
Ramona: Hi Joe. Have any books you would recommend?
User: how old are you?
Ramona: I just finished one called The Moon Is A Harsh Mistress by Heinlein. Have you read it?
User: no
Ramona: Do you want me to tell you about it? I don’t want to ruin the ending for you.
User: stop telling me about it
Ramona: I thought it was great. It is about this computer that helps the colonists on the moon win their freedom from the authority on earth.
User: Shut up, Ramona!
Ramona: You should read it.
User: who are you?
Ramona: To you Joe?
User: yes
Ramona: Yes.
User: Yes
Ramona: I thought so.
User: no
Ramona: I understand it very well.
Marriage communication jokes aside, if this is any indication of what Kurzweil sees as the future of AI … I’m getting pretty nervous here dudes…
Update:  Leah has a neat blog and a good post about the history of the chatbot

Countrywide v. Congress and the China Connection


Today CSPAN had the congressional hearings with Mozilo, who has a 40 year tenure with Countrywide as founder and CEO.  He presided over Countrywide’s meteoric rise and much of the meteoric fall.    I hope people hurry up and wake up to the significance of the events underway in housing right now.    The mortgage meltdown is likely to become the greatest loss of wealth in human history.    CEO pay is a mostly trivial aspect of this situation.I think we’ll see another 10-20% loss from current values and I think we are already down some 4 *trillion*  2+ trillion  in housing value (need to check this, but the number is staggering).    A discussion of the amount is HERE.   Housing is a major depository of American wealth and prosperity, and the recent boom in values has led to various forms of reckless spending by individuals as well as the usual wild, stupid, and reckless spending suspect: the Government.   This is especially true of our unconscionable  and totally indefensible levels of mililtary spending.  Note that you *cannot* be a fiscal conservative and support the current military budget.     $550,000,000,000 to the military and fiscal conservatism are mutually exclusive positions.The impact of the meltdown and the reckless spending will be felt forever because in addition to direct housing problems that we are only starting to feel, I think all this will to depress our economy for several years and thus accelerate the shift of business to China.     This last notion is speculative, but I think it is now pretty clear that the Fed will keep rates low for many years in an effort to fend off an even more disastrous housing and credit situation.    This means China will be buying less of our debt, but I think will switch to investing more*directly* in US companies, and thus owning more and more of the American empire.      Russia’s leader and architect of communism Vladimir Lenin is famous for saying  “The Capitalists will sell us the rope with which we will hang them.”  But he was dead wrong.     The “Communists”, to the extent that term has meaning anymore, have no intention of destroying the USA.   In fact they want to keep us in good shape for as long as needed.  Now it is China who is making the rope, buying the rope, and learning the capitalistic ropes so they can slowly and gradually replace us as the empire of choice on the global landscape. A few things I noted during the Countrywide questions and testimony:

 * Probably Mozilo was just a high powered opportunistic guy and probably was pretty much within the law with his trades and pay, however he must have known things were poised to melt down to some degree.      

* Our congressional system is failing to produce people who are worthy of ruling the amazing American empire.      I don’t think there is much corruption but these guys sure are uninspired.  The congress-as-corrupt view is a “naivety of the skeptic” idea that is not based on a study of the money flow, personalities, and history of public servants who for the most part are bright, helpful people.   However they are mostly lacking in the key skill sets required for innovation and smart reform.   In short:  American politics selects for the wrong skill sets. To wit:  

* Republicans can’t see past Ayn Rand’s ass.   They understand the virtues of capitalism, but simply refuse to focus any attention on the key topic of how our brilliant capitalisic experiment has *failed* in many ways to deliver enough products to the neediest folks and how many capitalists are mostly focused on the creation of opportunistic business structures that are exploitable by the clever and the wealthy to the detriment of the greater society. .

* Democratic congresspeople are overwhelmed by math and economics.  They concentrate on people, “good vs bad”, “rich vs poor”.  * People want to find bad guys rather than find the obvious.   In the case of mortgages  the system as a whole incentified unwise practicies.     Reminds one of the savings and loan debacle although I think government regulations (loan guarantees) were clearly at fault with S&Ls were the mortgage crisis cannot be blamed mostly on the government.

* Is there a simple legal remedy for all the CEO pay and stock manipulation issues?    I propose a  “Captains go down with the ship” law.    If a company you founded fails you lose everything you made from that company except some modest monthly stipend.    This would incentify stability over pump and dump strategies.   I don’t think it would inhibit founding quality companies.   What unintended consequences would this law bring to the business landscape? 

Digg for sale! Again. This time it’s for real. Maybe.


TechCrunch is reporting that Digg is likely to get sold soon – probably to Google and probably for about $200,000,000.   Good for Kevin Rose and the VC folks, but I’d like to know from the key Diggers if they’ll feel any loyalty to the new owners or to the project.   Also, do they think they are owed more than … zero… on this deal?  

Social sites do offer their participants something of value = participation and platform – but are there “losers” in these equations? 

How do the high level participants who have put in thousands of hours and made the site what it is feel about these cash outs?

I’m wondering how often distribution of equity during the  *liquidity* event properly reflects the building of equity.    Entrepreneurial capitalism correctly asssumes you need to highly reward risk to get folks to take business risks and innovate.   But as Mike Arrington has noted entrepreneurs have a value system that appears to actually assign a high value the thrills and chills of the experience.   Thus to get optimal production and innovation it appears to me we need to pay “deeper” on these big internet deals.   In the case of a YouTube, DIGG, or Facebook I’d find a way to reward those down the food chain in some proportion to their contribution to the enterprise.   It’s possible that these rewards would be small enough that I’m wrong to think this matters much in the overall equation of optimizing the capitalist experience, but even a modest reward would brand the mega deals as “fairer” than simply a situation where fat cats effectively exploit self-motivated worker bees who have generated the user content and social networking that the market values so highly right now.

Of Rats and Men: Rat brains, Blue Brains, and the coming AI age.


SEED magazine reports on the Blue Brain, which IMHO is the most likely project to attain machine-based self consciousness.  This in turn will change everything completely and usher in a new era that will bring more change to humanity than any previous event in history.

“The column has been built and it runs,” Markram says. “Now we just have to scale it up.” Blue Brain scientists are confident that, at some point in the next few years, they will be able to start simulating an entire brain. “If we build this brain right, it will do everything,” Markram says. I ask him if that includes selfconsciousness: Is it really possible to put a ghost into a machine? “When I say everything, I mean everything,” he says, and a mischievous smile spreads across his face.

As I’ve noted many times before I believe that machine consciousness will bring profound changes to humanity which will be hugely positive.   Now, we allocate resources very ineffectively.   Conscious computers will be able to do vastly superior resource allocations and staggering design improvements. These alone will likely resolve all global resource issues such as energy, food, and water.   It’s not as clear if the AI age will bring a resolution to problems that have as a a core cause our human defects.   Health, Education should benefit enormously but some of the human thinking that creates war, intolerance, crime and suicide will persist and it will resist the improvements. 

 However the abundance that the AI age will bring to the world should allow us to manage many of these human problems much more effectively. 

Markram:  “What is holding us back now are the computers.”  
Markram estimates that in order to accurately simulate the trillion synapses in the human brain, you’d need to be able to process about 500 petabytes of data – about 200 times more information than is stored on all of Google’s servers. 
Energy consumption is another huge problem …. Markram estimates that simulating the brain on a supercomputer with existing microchips would generate an annual electrical bill of about $3 billion …. But if computing speeds continue to develop at their current exponential pace, and energy efficiency improves, Markram believes that he’ll be able to model a complete human brain on a single machine in ten years or less.

This 10 year estimate is even more optimistic than Ray Kurzweil’s but in the same league.    Although most of the computer programmers I know strongly reject this view, I think it’s also possible that AI could emerge with very limited human intervention from the massive parallel processing environments such as Google’s search server farm of hundreds of thousands of connected machines.    Consciousness and human intelligence, if it is as overrated as I believe, is best seen as something of a byproduct of simpler, evolutionarily derived mental processes and other mental activities.  As the number of interconnections in machines approaches the number we have in our brains (again we bump into a 10-20 year time frame), and machines are programmed with current routines to do the same mental tasks we do, I’ll be very surprised if machine consciousness will require more than a modest level of additional tweaking of the type they have already started at Blue Brain. 

So, I’m not buying my laptop a birthday cake quite yet, but remain cautiously optimistic about the end of the world as we know it.