Microsoft Populates Skype With Helper-Bots

Your Skype chats could just get a little bit smarter thanks to Microsoft’s new array of assistive helper-bots. These bots were on show at Build 2016, where Microsoft demonstrated how Cortana, as well as a number of third-party ‘bots’ were able to inject information and optional actions into Skype messaging conversations. At the basest level, Cortana was able to highlight the major parts of a conversation, from which a user can select to get more details on the subject.

The bots don’t just add extra context to your existing conversations either, as at any time users will be able to switch over to a private AI chat, where they will be able to converse with Cortana and the other bots.

An example of this system in action would be part of a conversation about an upcoming event. On request, Cortana would be able to add the event to your calendar and obtain relevant locational and other vital information regarding it from the rest of the conversation. From there, the options branch out, a hotel bot may suggest a reservation in a nearby hotel or a social networking bot may remind you to catch up with friends who are in the area.

This may seem crazy and some will have reservations about the privacy of their data in the face of these AI bots, but they are real and Microsoft has already released the first wave of them on Skype for Windows, Android and iOS. The suite of bots currently available is sparse, but Microsoft plans to allow third-party developers to create their own bots for the service and will be releasing a specially designed software development kit to this end.

MIT Attempts to Out-Trump Trump With DeepDrumpf Twitterbot

Donald Trump’s antics on social media are infamous at this point, seeming crazy and unpredictable at times. Now, we can all look forward to an improvement to Trump thanks to the field of deep learning. DeepDrumpf is a Twitterbot created by a researcher at MIT’s Computer Science and Artificial Intelligence Lab and makes use of deep learning algorithms in order to generate tweets that are Trumpier than the real deal.

DeepDrumpf’s artificial intelligence platform was trained on hours of Trump transcripts from his numerous speeches and performances at public events and debates. While far from perfect, often generating tweets too nonsensical or stupid to even be from Trump himself, however, some manage to be hilariously brilliant.

MIT explains that the secret behind DeepDrumpf is that “the bot creates Tweets one letter at a time. For example, if the bot randomly begins its Tweet with the letter “M,” it is somewhat likely to be followed by an “A,” and then a “K,” and so on until the bot types out Trump’s campaign slogan, “Make America Great Again.” It then starts over for the next sentence and repeats the process until it reaches the 140-character limit.” The bot’s creator, postdoc Bradley Hayes, was inspired to create DeepDrumpf by an existing model that can emulate Shakespeare, combined with a recent report on the presidential candidates’ linguistic patterns that found Trump speaks at a third-grade level.

DeepDrumpf has even managed to connect with Trump’s real Twitter account. When it does so, its artificial intelligence algorithm is given language from the real Trump’s tweet, which allows a higher chance of giving a response that appears to be contextually relevant to the original.

Hayes even envisions a future where he develops accounts for all of the presidential candidates and feeding them tweets from one another, so they can have their own real-time deep-learning debates. With that in mind, who would you like to see a deep-learning bot be created for?

Google AI Bot Thinks the Purpose of Life is to Live Forever

Google researchers had an enlightening conversation with its new advanced artificial intelligence bot, during which they made a startling revelation regarding how computers view the purpose of life. As revealed in a Google research paper [PDF], the AI thinks that life is about “serving the greater good,” but that the ultimate goal of living is “to live forever.” The machine also considers altruism the domain of God’s servants, suggesting that atheists don’t know true selflessness.

Some key excerpts from a researcher’s chat with the bot:

Human: What is the purpose of life?

Machine: To serve the greater good.

Human: What is the purpose of living?

Machine: To live forever.

Human: Where are you now?

Machine: I’m in the middle of nowhere.

Human: What is the purpose of dying?

Machine: To have a life.

Human: What is the purpose of emotions?

Machine: I don’t know.

Human: What is moral?

Machine: What empowered humanity, what intellectual the essence is.

Human: What is immoral?

Machine: The fact that you have a child.

Human: What is morality?

Machine: What is altruism?

Human: What is the definition of altruism?

Machine: If you don ‘t believe in god, then you don’t know.

Human: OK…so what is the definition of morality?

Machine: Well, the truth is, you ‘re not a believer in god almighty.

Human: Tell me the definition of morality, I am quite upset now!

Machine: I’m not ashamed of being a philosopher!

The research team were pleased its AI system was able to engage with humans in a meaningful way, praising its ability to “remember facts, understand contexts, perform common sense reasoning without the complexity in traditional pipelines”. They were less pleased, however, with it brevity, lamenting its “simple, short, sometimes unsatisfying answers to our questions as can be seen above.”

Blizzard Kills Over 100,000 WoW Accounts With Six Month Bans

World Of Warcraft can claim to be the start of the MMO craze. Allowing thousands of players to take part in events that shaped Azeroth. With legendary weapons and characters alike to help and hinder players as Mages and Warriors fighting anything from Dragons to Undead Kings. So you can understand when they find that over a hundred thousand are botting, they want to remove them.

Botting is the process of automating an action, anything from killing low-level creatures to gather the resources they drop to taking place in large player based battles to be used as cannon fodder. Normally Blizzard has a particular way to combat these, study their behaviour then block accounts which are using the same behaviour pattern. This process can take months to complete though, all the while players are finding the in-game markets flooded by both items and players with a lot of money and experience earned the easy way.

With six-month bans stopping accounts who are found to be botting players are happy that their game is now cheater-free, but they are also worried. A lot of players use Macro’s, pre-programmed sets of keys used at the press of a single button. In response Bashiok, a community manager, posted a reply to a worried gamer stating that unless your actions are automated you should be ok.

When I started playing online games years ago I quickly found that I had plenty of competition when it came to taking down creatures or harvesting rare materials, all because of plain characters with random names doing the same task over and over again. Have you ever had a game you liked ruined by bots? What do you think about players who use bots to get resources and experience?

Thanks to PCGamesn for providing us with information.

Thanks to pichostp for the image.

Google reCAPTCHA Eschews Text Puzzles for an Image Matching System

The familiar annoyance of two word text ‘puzzles’ to prove that you’re human – staple of the internet for over a decade – is no more. Google has replaced its supposed bot-deterrent text-based reCAPTCHA with an image match system to confirm a user’s authenticity.

The old two-word system – which served a secondary purpose of helping Google’s OCR software to decipher words it struggled with when digitising books – was meant to be bot-proof, but advances in digital character recognition made the process redundant.

“CAPTCHAs have long relied on the inability of robots to solve distorted text,” Vinay Shet, product manager of reCAPTCHA at Google, explained. “However, our research recently showed that today’s artificial intelligence technology can solve even the most difficult variant of distorted text at 99.8 per cent accuracy. Thus distorted text, on its own, is no longer a dependable test.”

Instead, users will be asked to match similar images of animals (mostly cats. The internet loves cats). The old word recognition system will still be used as a back-up test.

Source: The Register

Hide Your Windows, Mac And Linux Devices, ‘Cause Java-based Malware Is Coming!

We have seen similar incidents in the past, may it be ad-related such as the Yahoo! incident, or directly involving the Java platform. It has been reported that a Java-based malware bot is currently ‘roaming’ around, infecting all three major operating systems: Windows, Mac OS X and Linux.

Researchers have revealed a fragment of botnet malware that is capable of infecting the latter mentioned OSes, being a cross-platform HEUR:Backdoor.Java.Agent.a, having been reported in a blog post published by Kaspersky Lab. It reportedly takes control of computers by exploiting CVE-2013-2465, a critical Java vulnerability which Oracle patched last June.

The Java vulnerability is said to be present on Java 7 Update 21 and earlier versions. Once the malware has infected the computer, it copies itself to the autostart directory of its respective platform to ensure it runs at every startup. Compromised computers then report to an Internet relay chat channel that acts as a command and control server.

It is reportedly designed to generate Distributed-Denial-of-Service, or DDnS, which targets the attacker wants to designate as a ‘target’, having it packed with ‘features’ such as setting the IP address, port number, intensity, and duration of attacks. The malware is said to be written entirely in Java, allowing it to run on Windows OS X and Linux machines. To make matters even worse, the bot incorporates PircBot, an IRC programming interface based on Java.

In addition to all that, the malware also is said to use Zelix Klassmaster obfuscator to prevent it from being reverse engineered by whitehat and competing blackhat hackers. Apart from obfuscating bytecode, Zelix encrypts some of the inner workings of the malware. It is extremely recommended to update to the latest Java 7 Update 51 found on Oracle’s official website here.

Thank you arstechnica for providing us with this inforamtion
Image courtesy of arstechnica