Old daemon and wallet version 0.17.0.1
>> 10 new open source projects and developments, worth knowing about
**Jitsi : Video conferences **
Don’t know why I missed this before, came up in reddit discussion of the complex dependencies of Google-Talkplugin.
What is Jitsi Meet?
You can also try it out yourself at meet.jit.si.
I noticed something interesting with the Google Talk plugin .deb
Could this possibly become a plugin for the Qt?
I noticed something interesting with the Google Talk plugin .deb
what do you expect from a company that makes money from selling personal info?
What is described in the reddit link fit’s exactly to the behavior google has with end user data security. Tehy are the largest data miners in the world and instal lheir backdoors everywhere
kris_davison last edited by | Tip kris_davison
Hi all not sure if you have already heard about this but I thought it may be useful in the future.
Docker.com its containerisation software a little like a very lightweight VM that can contain whatever software you like and can run anywhere. (Any modern Linux anyway as Windows/Mac are not well supported)
We are starting to use them at work and I though they may be a great way to install a Feathercoin deamon (or full node?) as all software would essentially be preinstalled and could just be run by the user.
It’s worth a look its pretty new (only 15months) but already has huge support.
Maybe this could be good for preconfigured miners for different card types etc. Just a thought.
Hey… I am trying to Meet up project. How it’s help us ?
This public private key is hardly easy or mainstream, so was interested to read about clean room :
A linux livecd + application combo that provides a secure, usable environment for managing GPG keys.
Using an offline master key with active subkeys is considered to be the most secure way to use GPG, however the workflow for setting up and maintaining such a gpg key is incredibly laborious. You need look no further for proof of this than the gigantic 18-step procedure provided by the FSFE.
The vast majority of the steps are simply navigating the complicated GnuPG command line interface with very little actual input or decision making necessary on the user’s part.
The Clean Room project aims to provide a bootable environment that provides a clean and simple interface for GPG tasks. Balancing user friendliness and security in an attempt to drastically simplify the GPG management process is it’s core goal.
Getting software package updates while offline
What is this Offline Master Key Thing?
In a standard GPG arrangement, the user has ostensibly one key (in reality they have one master signing/certifying key and one encryption subkey). The private key material for the keys are stored in $HOME/.gnupg/ on the user’s main workstation. When an action that requires access to the private key (e.g., decrypt or sign) is performed, the private key is read straight from disk.
While conceptually simple (as simple as anything surrounding PGP is) there is the unfortunate side-effect that the identity chain is highly-coupled to the keys used for encryption and signing.
User’s expend significant effort (remember your last key-signing “party”?) in creating and expanding their identity certifications (aka the Web of Trust). Their PGP key becomes a proof of identity within the relevant social circle.
Yet, the PGP key is actually fulfilling three distinct purposes:
Confidentiality (encryption, decryption)
Ensuring integrity (message signing)
Of these, identification is the most important, hence the reason user’s go to great lengths to certify identity. Without identity verification, the usefulness of confidentiality and integrity become questionable.
There is always the concern that key material stored on a production machine can be compromised. When private key material is compromised in the traditional GPG setup, the affected keys must be revoked obliterating the painstakingly built identity chain.
Wouldn’t it be great if we could retain easy encryption and signing ability while protecting one’s identity and associated trust links even in the event of a compromise?
KRITA - art program**
Krita has just had a major update so may be worth checking out, especially any artists.
Krita is a FREE digital painting and illustration application.
Krita offers CMYK support, HDR painting, perspective grids, dockers, filters, painting assistants, and many other features you would expect. Check out the gallery to see what other artists have done with Krita
**A.I. Techniques and Frameworks
H2O makes Hadoop do math! H2O scales statistics, machine learning and math over BigData. H2O is extensible and users can build blocks using simple math legos in the core. H2O keeps familiar interfaces like R, Excel & JSON so that BigData enthusiasts & experts can explore, munge, model and score datasets using a range of simple to advanced algorithms. Data collection is easy. Decision making is hard. H2O makes it fast and easy to derive insights from your data through faster and better predictive modeling. H2O has a vision of online scoring and modeling in a single platform.
PredictionIO is an open source machine learning framework for developers and data scientists. It supports event collection, deployment of algorithms, evaluation, querying predictive results via REST APIs.
Numenta Platform for Intelligent Computing (NuPIC)
Watch this video : http://numenta.org/nupic.html
NuPIC is a Python / C++ open source project that implements HTM as described in the HTM White Paper.
NuPIC uses human style learning to, win games, or do other processes, learned from scratch or by example.
numenta/nupic Â* GitHub
I will be moving my BotLibre research and chat logs to my own Hubot instance soon. Rapid development on Github at the chat end of Bots.
A customizable life embetterment robot.
Hubot is a chat bot, modelled after GitHub’s Campfire bot, hubot. He’s pretty cool. He’s extendable with old community scripts, or new community org and your own custom scripts, and can work on many different chat services.
Some other intereting stuff in development
Also with a lot of development on Github currently.
Cjdns implements an encrypted IPv6 network using public-key cryptography for address allocation and a distributed hash table for routing. This provides near-zero-configuration networking, and prevents many of the security and scalability issues that plague existing networks.
Detekt is a Python tool that relies on Yara, Volatility and Winpmem to scan the memory of a running Windows system (currently supporting Windows XP to Windows 8 both 32 and 64 bit and Windows 8.1 32bit).
Detekt tries to detect the presence of pre-defined patterns that have been identified through the course of our research to be unique identifiers that indicate the presence of a given malware running on the computer. Currently it is provided with patterns for:
pypy can run some python applications faster by precompiling the scripts.
Juno & Julia
Walks like Python. Runs like C.
Juno builds on Julia’s unique combination of ease-of-use and performance. Beginners and experts can build more powerful programs more quickly, and get to a result faster.
Great for power users, too.
Juno is built on Light Table, which means it’s a decent editor as well as a pretty face. It’s customisable to your heart’s content (though the defaults are pretty good too) and has power features like multiple cursors, fuzzy file finding and Vim keybindings.
Julia is a high-level, high-performance dynamic programming language for technical computing, with syntax that is familiar to users of other technical computing environments. It provides a sophisticated compiler, distributed parallel execution, numerical accuracy, and an extensive mathematical function library. The library, largely written in Julia itself, also integrates mature, best-of-breed C and Fortran libraries for linear algebra, random number generation, signal processing, and string processing. In addition, the Julia developer community is contributing a number of external packages through Juliaâ€s built-in package manager at a rapid pace. IJulia, a collaboration between the IPython and Julia communities, provides a powerful browser-based graphical notebook interface to Julia.
Re: AI techniques developments : Just read this : http://phys.org/news/2015-03-evolving-robot-brains.html
and the software to do that on Github :
This thread will become a sandbox for innovation one day.
It should stay pinned. Epic.
Critterding - Framework to evolve artificial intelligent lifeforms
I’ve taken over the Github for Critterding and am hosting version 14 with the approval of the Devs. My version has a few more fixes than the other versions (some haven’t got to source forge)+ some changes bobke has passed to me, which I’m going to check and push soon. The Beta 14 version is virtually a complete version, there is a rare segmentation fault, in my case that is because of setting a parameter to mutate and it’s gone out of control. Critterding autosaves so you just restart it.
I’ve started noting some enhancements that can be made, especially towards a sandbox for evolving artificial intelligent brains or applications to use in the real world…
My long term goal is to, learn a bit more programming and monitor any pushes and gradually doing some updates myself.
My initial enhancement idea to persue is to add “pre designed” body shapes, then train the neural net to control those bodies and get food from a green ball. It would be good if the system did everything by evolving, so, the idea would be to add a facility to evolve body shapes, by how well they match to a “sketched” shape.
I can then transfer that brain to a computer and camera in one of my toy robot dogs.
Even if it is only an example of framework (it isn’t), there is a lot to learn in how a ongoing neural net controlled system can be trained from scratch, or use tools to add instinctive behaviour, body shapes or other “restrictions” that mean the resultant brains could be used more generally.
CoinBot has moved to a bigger brain : It doesn’t matter that he is stupid, he wants to learn off you and will soon (hopefully) stupidly listening to spam bots try to log in to FTC, so get friendly.
had a nice chat with the web chat bot:
You: do you know feathercoin?
coin bot: I know about Litecoin
You: what is litecoin?
coin bot: famous people
You: it it a coin?
coin bot: The value of Feathercoins can vary
You: what is the value of feathercoin?
coin bot: The code for Feathercoin is FTC
The Coin Bot has been trained up from scratch, all responses are learnt from Chats or Chat logs.
The Bot construction may be thought of more like a novel, Coin Bot is currently a brief synopsis (1 years work).
The responses can be trained and complex behaviour “Trained in” in the Bot framework I am using.
The idea to prevent spam would be to have a Chat Bot on the FTC “User Registration Page”, It would be programmed with one greeting. I have paid for that for a year and there is a code to easily put in the html.
“Please type your user name in the chat box for us, thank you, Coin Bot”
We could the then set a 30 sec time out (say) for a new member to type a response to Coin Bot, and an email message to admin if the time or name is not correct. i.e. its a bot. The extra work will distract the spammer (if he has to do it by hand) also extra details of the login process will then be known, to further enhance the anti spam measure. We don’t have to pay external spam control, first site to start to use AI security measures.
Initially it could just be an extra step, unless speak is pressed no registration.
The main advantage I see is, I can use my Bot, the Bot company are interested in the idea and may integrate the idea to give the bots email / skill based on a trainable trigger.
I have also discuses with them my idea to work in a meta level above the characters in human language. For instance a system could allocate a number to a word, say based on the position of letters. This would automatically correct one of the problems with the bot, words beginning with capitals or ending in s are different words, whereas in the number meta level, even slightly miss spelt words would be close on the position of letters meta level.
All images and characters have to be normalised to numerical data to be processed, in the case of using ASCI numbers to replace letters, these are not optimised to the usage case as an evolved / flexible system could be using machine learning and optimisation techniques.
Also, a system could evolve such that it can test various options for converting words to numbers, such that it searches an finds word the quickest. It could do this by allocating numbers for each letter such that there is the optimal numerical distance between close words, and that alternate (spellings) are at particular “angles” on that imaginary plane. This would also mean the system self optimised to spell, search any new language.
The word system could then be applied to a meta layer of the sentence, thus allowing the bot to learn language “skills” from scratch.
At the moment using standard filter techniques there is no way to identify a Spam account, although many are “plain to a human”. Take the case where you identify a Bot naming algorithm - one name + “d” + a second name + 3 figure number. Or where the Bot is named – Random 5 characters + name + 2 figure number.
A suitably designed and trained Bot would find those naming formulas easily if search on the number meta level, or even a learned skills from a text interface. Also again, the bot is not meant to be intelligent, it reports to a human like a filter or simple chron system. I would recoment “Human out of 10” send me an email if its < 3.
The Bots, in my opinion, are not there to imitate humans, they are there to do the donkey work intellectual analysis to give humans the knowledge to make sensible decisions. They are also capable of taking over the “look up table” of many intellectual pursuits, e.g programming languages or coding principles, and allow the common person to do software development.
For instance we will soon have AI bots learning to program by searching for bugs on Github? If googles AIs were redirected from spying they could easily be doing that now. Who wants to go through every line of code on Github to see if anyone made a similar mistake to this issue that has been corrected?
or who wants to go through every user on this forum and guess / estimate if they are a spam bot?
My (proposed) bots would do that all day long, no complaints…
Also we need to rush before the spam bots get AI.
coin bot: I am the Coin Bot
You: Wellenreiter said he talked to you
coin bot: I know about Litecoin
You: That’s what he said you said
coin bot: There ain’t no such thing as a free lunch.
You: what about free software?
coin bot: Feathercoin bypasses the old banking system by using peer-to-peer technology.
You: what did he say?
coin bot: He said “frostfire: Sideways-Sanae was here yesterday”
You: Wellenreiter was here yesterday
coin bot: did you talk to him about Sideways-Sanae?
You: You talked to him about FTC
coin bot: I know about Litecoin
You: what do you know?
coin bot: We economists don’t know much, but we do know how to create a shortage.
Just a note on the current state of machine learning i.e. great if you are Google. Researchers have trained a Artificial Intelligence to patch security issues by cutting and pasting code from binaries. The binaries don’t have to be programmed in the same language, the machine learning extracts and uses the binary patches by learning from their actions.
1. Being able to replace binery code on the fly negates all source code and current software security measures, i.e. if security measures can be added (real time) they can be taken out.
2. Machine learning will very soon be able to (i.e. already can) decompile all binaries software, to any language = end of proprietary software?
Adobe Machine Learning program - Computer program fixes old code faster than expert engineers
I see that the next step an Machine Learning taking over “management” level jobs has already happened at Pay Pal, with seller / buyer dispute resolution.
Companies like Moka are also resolving legal disputes “online”. The main rouble is this software is not open source and currently our lives are being run by Artificial Intelligence but we have no ability to monitor or decide how far that goes ie when a human should step in and over ride the decision.
A classic example is my local Tesco, a “monopoly” supermarket in my middle class area is for ever trying to reduce the amount of value items. I often have to complain ( disabled = poor), the Tesco “Algorithms” attempt to maximise profit, even when that means selling unhealthy food or removing value products or absolute basics, such as cottage cheese, from the shelf.
Just looking at http://gazebosim.org/ , slight drawback in that it is not available for Ubuntu 15.04 yet, however, just loading Virtualbox to see if it will run in that.
Using Virtualbox is not as useful as having a proper robot / machine learning macro assistant as part of the desktop, so still waiting for Robotubuntu …
Robot simulation is an essential tool in every roboticist’s toolbox. A well-designed simulator makes it possible to rapidly test algorithms, design robots, and perform regression testing using realistic scenarios. Gazebo offers the ability to accurately and efficiently simulate populations of robots in complex indoor and outdoor environments. At your fingertips is a robust physics engine, high-quality graphics, and convenient programmatic and graphical interfaces. Best of all, Gazebo is free with a vibrant community.
Get the benefit of ZFS style copy on write and File system snapshots, retro fitable to you Linux FS with Dattobd.
The Datto Block Driver (Dattobd) solves the above problems. Dattobd is an open source Linux kernel module for point-in-time live snapshotting.
Dattobd can be loaded onto a running Linux machine (without a reboot) and used to create an image file representing any block device at the instant the snapshot is taken.
After the first snapshot, Dattobd tracks incremental changes to the block device and can therefore efficiently update existing backups by copying only the blocks that have changed.
Two amazing programs are now available on Git hub, which are significant developments in the availability of open source machine learning to the “normal person”,
This code implements multi-layer Recurrent Neural Network (RNN, LSTM, and GRU) for training/sampling from character-level language models. The model learns to predict the probability of the next character in a sequence. In other words, the input is a single text file and the model learns to generate text like it.
The context of this code base is described in detail in my blog post. The project page that has a few pointers to some datasets.
If you are new to Torch/Lua/Neural Nets, it might be helpful to know that this code is really just a slightly more fancy version of this 100-line gist that I wrote in Python/numpy. The code in this repo additionally allows for multiple layers, uses an LSTM instead of an RNN, has more supporting code for model checkpointing, and is of course much more efficient.
This code was originally based on Oxford University Machine Learning class practical 6, which is in turn based on learning to execute code from Wojciech Zaremba. Chunks of it were also developed in collaboration with my labmate Justin Johnson.
ConceptNet aims to give computers access to common-sense knowledge, the kind of information that ordinary people know but usually leave unstated.
This Python package contains a toolset for loading new datasets into ConceptNet 5, and it serves the HTML and JSON Web APIs for it. You don’t need it to simply access ConceptNet 5; see http://conceptnet5.media.mit.edu for more information.
If you’re interested in using ConceptNet, please join the conceptnet-users Google group: http://groups.google.com/group/conceptnet-users?hl=en
Further documentation is available on the Wiki: https://github.com/commonsense/conceptnet5/wiki
ConceptNet is a multilingual knowledge base, representing words and phrases that people use and the common-sense relationships between them. The knowledge in ConceptNet is collected from a variety of resources, including crowd-sourced resources (such as Wiktionary and Open Mind Common Sense), games with a purpose (such as Verbosity and nadya.jp), and expert-created resources (such as WordNet and JMDict).
Interesting to see these projects have developed recently :
Interesting developments in combined Man Machine Intelligence?
First signs of “open forum” style public action tools becoming available?
This looks interesting : Although I initially thought it was for sniping eBay!
Snipe-IT Installation Guide
Snipe-IT is a Free Open Source (FOSS) project for IT asset management, to enable IT departments to track who has which laptop, when it was purchased, which software licenses and accessories are available, and so on.