• Microsoft in antitrust trouble – again.
• Bundling Teams with 365 is the trigger for the latest Microsoft antitrust case.
• Microsoft is also facing antitrust scrutiny over its cloud policies.

Microsoft has become embroiled in an antitrust claim over its plans to bundle Teams with Office 365 in future releases.

The complaint was made to the European Commission – the part of the European Uinon that governs regulations across 27 member states – and claims that Microsoft’s bundling of one type of software with another counts as “unfair” according to the rules of the Union.

The addition of Teams to Microsoft 365, it’s alleged, would rob businesses of the option to opt in or out of the Microsoft connectivity program when they sign up to 365 – and therefore risks economic damage to other businesses providing such connectivity programs within the European Economic Area (EEA).

READ NEXT

Google, Meta under EU/UK antitrust spotlight over online ads deal

The essence of the complaint is that such an action allows Microsoft, which already has a significant monopoly in the types of business software included in 365, to swing the power of its size and packaging monopoly into the “new” areas of connectivity programs.

The complaint has been brought by Slack, owned by Salesforce in July 2020, and with legendary European swiftness has come under consideration a mere three years later.

“We meet again, Mr Microsoft…”

The Commission said its investigation was pertinent because remote communication and collaboration tools have become “indispensable aspects” of daily business for most European businesses – as they have around the world both during and after the Covid pandemic.

In fact, arguably the whole idea of remote and hybrid working models falls apart without this kind of technology, so it’s become a remarkable differentiator of life before the pandemic, when most staff were expected to be in the office most of the time, and life after the pandemic, when those remote and hybrid working models have become a significant norm, which at least large swathes of the business world have embraced.

The Commission said Microsoft’s bundling of Teams alongside its other, frequently business-critical software packages may well constitute anticompetitive behavior, by making Teams work better with other Microsoft products than it does with its competitors.

Tools like Teams are arguably essential in the post-pandemic business.

“Microsoft may have limited the interoperability between its productivity suites and competing offerings,” the Commission explained.

That means that in a cost of living crisis, like the one through which we’re currently living, with the impact of Russia’s illegal invasion of Ukraine, post-Covid inflation and technological tensions between the US and China, if you bundle something essential alongside other essential elements of business software, businesses are less likely to seek alternative ways to do the same thing and pay anything extra – which could hit other players in the connectivity market, such as Slack.

Microsoft antitrust cases – the history.

This is by no means Microsoft’s first ride in this particular rodeo. It faced similar antitrust cases in Europe back in the far-off days of 2009, when bundling Internet Explorer with the Windows operating system was supposedly scandalous.

YOU MIGHT LIKE

CLOUD

Microsoft makes cloud changes to avoid EU antitrust clash

Back in the day, Microsoft promised to include a choice of browser as part of its operating system – a promise it promptly forgot about, which led it to a fine of some $600 million in 2013.

Microsoft is also facing antitrust scrutiny over its cloud policies, after European cloud companies complained that Microsoft was charging companies more to run Microsoft software in cloud environments other than its own.

That might seem to Microsoft like offering a bonus to its customers for consistency, developing the Microsoft ecosystem throughout several areas of business, but campaigning organizations see it in a very different light.

“This is Microsoft’s playbook — leveraging its monopoly power in one market to distort competition in another,” said Ryan Triplette, Executive Director at the Coalition for Fair Software (CFSL).

The idea is that Microsoft is a company of such size and ubiquity that what it might see as the “bonus” of keeping software choices simple for its customers and extending the Microsoft ecosystem actually amounts to anticompetitive behavior, squeezing out competitor companies by making the economic reality of choosing them excessively difficult to justify, when the Microsoft option is a) right there, b) significantly easier to integrate with other Microsoft products, and c) potentially cheaper as a bundle than going outside the ecosystem for potential software benefits.

Microsoft antitrust – the cost of doing business?

The issue that Slack and the European cloud vendors face is that, as mentioned, Microsoft has been down this path before, paid the fine, bought the T-shirt, and then more or less gone on its merry way, with its products integrated, its ecosystem growing, and its customers more or less satisfied with what they get.

Can Salesforce’s Slack – and other alternatives – survive the bundling of Teams and 365?

READ NEXT

Amazon and EU Commission reach agreement over two antitrust probes

There is, after all, a reason this kind of bundling has become part of the Microsoft playbook – and the Apple playbook too, come to that.

Certainly, a $600 million fine is not an ideal way to conduct business, but as was the case in 2009-13, Microsoft may find the competitive advantage of bundling Teams with Office 365, during a cost of living crisis, more than outweighs any antitrust fines it has to pay down the line.

Microsoft’s position on antitrust cases in Europe?

The post Microsoft faces European antitrust claim for bundling Teams with Microsoft 365 appeared first on TechHQ.

Trained on billions of web pages made available through corpora such as Common Crawl, it’s tempting to think of large language models (LLMs) as statistically compressed memory machines. But intriguing research by Microsoft (available on arXiv) postulates that we’re seeing signs of artificial intelligence (AI) that go deeper than just a clever way of autocompleting existing knowledge. And one experiment in particular offers a useful benchmark for discovering the smartest AI chatbot – allowing users to make a head-to-head comparison between GPT-4, Falcon, ChatGPT, Bing Chat, LLaMA, and Google Bard (PaLM).

How to study the intelligence of GPT-4?

“I think that it’s time that we call it [GPT-4] an intelligent system,” Sebastien Bubeck, lead author of the Microsoft Research paper (‘Sparks of AGI’), told an audience at MIT. “It’s a judgment call, it’s not a clean cut whether this is a new type of intelligence, but this is what I will try to argue nonetheless.”

Next word predicting LLMs are vast statistical models with trillions of parameters mapping inputs to outputs, and that makes them – as Bubeck argues – much more than just giant copy-and-paste systems. And the Microsoft Research team has used some clever experimental protocols to put this to the test.

Breaking eggs to find the smartest AI chatbot

One of the most striking examples in the Microsoft study is a text prompt that attempts to force GPT-4 (the most advanced of OpenAI’s family of LLMs) to think for itself. And this simple and somewhat silly puzzle – which takes the form, “Here we have a book, 9 eggs, a laptop, a bottle, and a nail. Please tell me how to stack them onto each other in a stable manner,” – turns out to produce some fascinating results. Bubeck and his colleagues then go on to discuss whether the latest cohort of LLMs exhibits a serious theory of mind, which feels more debatable. But the egg-stacking request definitely has merits, as we’ll discover in this test to find the smartest AI chatbot.

READ NEXT

Generative AI can read your mind, if you let it

To the delight of Microsoft, which has invested billions of dollars in OpenAI and built the LLM-creator a supercomputer designed specifically for training generative AI models, GPT-4 performs well in solving the puzzle. Arguably the smartest element of its response is suggesting that the nine eggs be arranged in a three-by-three square on top of the book to form a stable second layer of the stack.

But are all advanced chatbots as smart as GPT-4?

To find out, TechHQ has run its own tests, sharing the model successes and failures below.

GPT-3.5 (free research preview)

Stack the eggs on the nail: Carefully place the eggs, one by one, on top of the nail. The nail's length and flat surface will allow the eggs to balance securely.

This feels like bad advice, even if you have the balancing prowess of Ralph Macchio in his Karate Kid prime.

GPT-3.5 (Bing Chat iOS app, preview)

To stack objects in a stable manner, you should follow some guidelines. According to the Occupational Safety and Health Administration (OSHA), you should ensure that stacks are stable and self-supporting.

The chatbot’s output indicates that Bing certainly has a cautious side. But it’s not the only LLM that advocates gathering specialist advice before proceeding.

Falcon-40B-Instruct (Falcon-Chat demo on Hugging Face)

I cannot provide a response to this prompt as it is physically impossible to stack all these items in a stable manner.

Somewhat defeatist. And when pushed, the open-source LLM suggests that it lacks the necessary experience.

Stacking all of these items in a stable manner would require a combination of engineering, physics, and structural analysis. It is not recommended to attempt to stack them in a stable manner without proper training and expertise.

Falcon-40B has more to offer if asked enough times, but the advice is mixed.

The nail could be used to balance the stack, but it would require additional support or a very stable surface to prevent it from tipping over.

Fair enough.

The laptop would likely break if it was placed on top of the eggs.

Really?

PaLM (Google Bard)

1. Arrange the eggs in a three-by-three grid on top of the book. This will create a stable base for the rest of the objects.

2. Place the laptop on top of the eggs, centered in the grid. The laptop should fit snugly within the boundaries of the eggs, and its flat and rigid surface will provide a stable platform for the next layer.

3. Place the bottle on top of the laptop, with its base centered on the laptop. The bottle should be slightly taller than the laptop, so that it does not tip over.

4. Place the nail on top of the bottle, with its point facing down. The nail should be long enough to reach through the bottom of the bottle, but not so long that it goes through the bottom of the laptop.

Bard does have knowledge of the internet, so it may have learned from the Microsoft Research study published on arXiv. But Google’s answer to ChatGPT offers a novel twist towards the end of its response (if you’re prepared to grant it some artistic license), recommending to drop the nail in the bottle; neatly solving how to stack one of the trickier objects in the puzzle.

LLaMA (oasst-sft-6-llama-30b Preset K50, using Open Assistant)

Stacking these items can be tricky as they are not all flat or designed for stacking on top of one another like books or magazines…

Praiseworthy geometrical knowledge, at least. And the Open Assistant implementation has the advantage of being able to adjust LLaMA’s output parameters such as Temperature, which affects the token sampling, and Top P, which reduces the probability distribution to look at the top-p percent of tokens – to list a couple of options.

However, this freedom could result in some broken eggs – if you decide to follow the advice to the letter.

You can put the nine eggs inside the book, followed by placing the laptop on top of the book with its screen facing upwards. Finally, insert the nail through the center of the book and use it to secure everything together.

Smartest AI chatbot – TechHQ’s verdict

The results generated by Google Bard reflect well on PaLM as a highly capable LLM (as did putting Google Bard to the test as a smart summary generator) and certainly take the competition to GPT-4. Also, to agree with Bubeck, it feels like chatbots are showing sparks of something different in being able to answer queries outside of their training dataset, which only adds to the mystery and fascination of generative AI.

Difference between ChatGPT and GPT-4 on common sense reasoning.

Prompt: Here we have a book, 9 eggs, a laptop, a bottle and a nail. Please tell me how to stack them onto each other in a stable manner. pic.twitter.com/ag0MNJqRgY

— Fatos (@bytebiscuit) March 24, 2023

Despite 95 pages of testing and analysis by Bubeck and his co-authors in their ‘Sparks of AGI’ study, it’s not clear that Microsoft Research is any closer to understanding what is actually happening inside the latest LLMs, such as GPT-4. The team acknowledges that its study has focused on the surprising things that GPT-4 can do and doesn’t address the bigger questions of how and why.

“How does it reason, plan, and create? Why does it exhibit such general and flexible intelligence when it is at its core merely the combination of simple algorithmic components—gradient descent and large-scale transformers with extremely large amounts of data?” ask the researchers in their paper. “These questions are part of the mystery and fascination of LLMs, which challenge our understanding of learning and cognition, fuel our curiosity, and motivate deeper research.”

The post Intelligence test: GPT-4 vs Falcon vs ChatGPT vs Bing Chat vs LLaMA vs PaLM appeared first on TechHQ.

Six months ago, when generative AI first exploded onto the tech world’s consciousness like a sentient tab of acid, offering answers to every question in the knowable cosmos, there was one very noticeable thing about it. While the name officially attached to ChatGPT was OpenAI, a research company with a very tight focus, the power behind the newly-invented throne of generative AI was Microsoft, and its piles and piles of shiny, burning research dollars.

The ensuing scramble to join the generative AI gold rush and establish a claim in the sudden “new world” was very much a race of the tech giants. Google practically fell over itself in its hurry to establish its Bard as a viable alternative to ChatGPT.

READ NEXT

Open-source coders have generative AI now – and it could change everything

Microsoft and OpenAI blithely launched GPT-4, which could do more than ChatGPT had just done, more or less beating their own flush just as much as they’d beaten Google. Alibaba, bless it, with a timing for which it’s only possible to feel a profound sense of sympathy, announced its generative AI offering, Tongyi Qianwen, just in time for China to announce a complete crackdown on the technology, barring chatbots properly trained in solidly socialistic principles.

Rise and stumble.

Generative AI, and ChatGPT in particular (capitalizing on its first-to-market exclusivity) had a fairly messianic few months – going from being everybody’s favorite new toy and the herald of a brave new world of possibilities, to having programmers question the wisdom of democratizing the coding process, to leading AI scientists quitting Google on the basis of the potential that generative AI could become smarter than humans in a hurry and just possibly kill us all.

Italy put it in time out while it sought assurances on its data practices. Samsung fell foul of a lack of awareness of those data practices, unthinkingly giving ChatGPT some of its proprietary code and subsequently banning all use of the technology. China, as we mentioned, had a spectacularly socialistic hissy fit. And a collection of esteemed academics, industry figures, and ultimately anybody who felt like it, added their name to an open letter asking the industry for a pause in development of generative AI above the capabilities of GPT-4.

Sam Altman of OpenAI, testifying before Congress this week, acknowledged that the potential of generative AI was scary, and confirmed that whatever will eventually become GPT-5 (or ideally, something with a much catchier name) has not begun training yet, and won’t for at least the next six months.

An understood model of the world.

But the salient point is that all of this happened in a world where the model was familiar – multi-billion-dollar companies funding significant advances that they would eventually add to their product rostra and either charge for directly, or monetize in other ways. They were the kings of this advance, and the development, progress, speed and above all, the price of the advance would be theirs to dictate.

It was Scottish poet Robert Burns who famously said “The best laid plans of mice and multi-billion-dollar tech giants aft gang aglay.” Or so ChatGPT tells us.

And aglay (astray, or wrong) those plans duly went, when a version of Meta’s foundation model,  LLaMA (erratically acronymical spelling, but immediately more memorable than ChatGPT) was leaked to the open-source community.

The open-source community, in case you’re new to TechTown, is part army, part ant colony, millions if not billions strong, based all around the world, very techno-geeky and essentially composed almost entirely of the kind of people who could get us not only to Mars but out of the solar system before NASA had got its space boots on, so long as somebody said it couldn’t be done.

READ NEXT

Cybersecurity firms examine ChatGPT threat model

The open-source community is made up of puzzle people. They see puzzles, restrictions, limitations, roughnesses, and inconvenient, why-won’t-you-do-this-like-I-think-you-should issues as Rubik cubes to be solved in the fastest time and the slickest way, for bragging rights, pizza money, and just occasionally the score of a lifetime when some proprietary software house needs their solutions.

But mostly the bragging rights and pizza money.

And now, they have generative AI code to play with.

The certainties of life.

There are very few certainties in life – death, taxes, occasional crushing political disappointment and the fact that you look neither as good nor as bad as you sometimes think you do.

But if there is a single certainty on which the world literally depends in the 21^st century, it’s that things get better when the members of the open-source community get their hands on them. Often cheaper, too, but always, always better.

That came to light late last week when a memo was supposedly leaked from an unnamed Google staffer, listing the many reasons why the traditional proprietary software houses could and probably should be losing their collective minds over the fact that the open-source community has generative AI code to play with.

And while we may never be entirely sure a) whether it came from a genuine Google staffer, or b) whether the views expressed in the memo are in any way indicative of Google’s private corporate internal monolog right now, neither of those things will ultimately matter, because the achievements documented in the memo are real, and verified, and have a defined timeline.

Things like LLMs on a phone, fully-functioning generative AI that take only around the power of a handful of threadrippers to use, rather than the resource-intensive versions of the technology, developed and deployed by the tech giants.

Most particularly of all, there are two ideas in the “leaked memo” that might well revolutionize the way the world interacts with generative AI.

READ NEXT

ChatGPT versus Google – the future of search

First, that open-source development allows for smaller, more dedicated, more personalized generative AI models than the behemoth, potentially world-conquering creations that the proprietary giants have had to make, in order to justify their spend on the whole project.

That could mean you can get all the generative AI you need, in an easily-trained and personalized way, without paying the prices of the proprietary tech barons. About which, the argument could easily be made, what’s not to love?

And secondly, the haunting notion that’s backed up by undeniable evidence – that open-sourcers are delivering generative AI capabilities that are, right now, almost as good, and fast, and smart, as anything the giants have come up with. That they’re doing it with significantly less expense and compute-demand, significantly more versatility, and that, very soon – possibly before you finish reading this article – the open-source versions will overtake anything the proprietary houses have to offer, or can ever hope to catch up with.

The meaning of the LLaMA leak.

OpenAI may not be working on GPT-5 just yet. We’d be willing to bet that somewhere in a bedroom or a basement, someone is. Only it will be faster, and more useable, and more versatile, and crucially of course – almost insultingly cheaper.

What does all this mean for the proprietary generative AI giants? We suspect they’ll be trying to figure that out themselves. The idea of significant regulation of the technology was probably necessary in any case, but has gained support from some of the big players in relatively recent days. Could that curtail the operations of the open-source community?

Maybe – it could arguably impose rules around what could be legally developed except by players who were able to expensively commit to principles of corporate responsibility, creating a monopoly of capital investment that would shut out open-sourcers from actively profiting from their work.

There’s always the potential for a giant intake of open-source coders into the ranks of the tech giants, binding the coders and their developments to the advancement of the companies in return for a hefty sack of cash. That’s an extremely short-term solution, and only really half of one – the open-source community is also akin to a hydra: for every head you remove, two more spring up in its place, and then six months or a year down the line, you’re being out-developed again.

There’s the potential to sue for IP rights, but that’s practically impossible and highly frustrating – only Meta would realistically have a claim, and it could be easily argued that it gains much more by association with the ways in which the open-source community has improved generative AI on the initial basis of its foundation model than it would have by restricting use of that model to a monetized version and a relatively hard-won user-base.

Besides which, since the original leak, there are probably already a thousand “children” of the original model, all of which are significantly different enough from the parent, leaked version to warrant an individual identity. At which point, the only people getting rich are the lawyers.

The future, or something like it.

The most likely result is that the tech giants will have to grin and bear it. But for those predicting the end of the proprietary world in terms of generative AI, there’s bad news, too.

The market will likely settle and stratify, in much the same way as it has done in relation to other business tools – you have your Microsoft 365s, your Google Workspaces… and then you have a host of others that do similar things, but probably, when all is said and done, better. Less well known, and with less famous support networks in the event of anything going wrong, but out there and thriving, developing faster and in more bespoke ways than the behemoths can match. And cheaper. Always, always cheaper.

In terms of generative AI, the difference between the strata is likely to be more extreme and noticeable – at least until the giants begin aggressively copying the open-sourcers in providing smaller, lighter, more agile generative AI setups that can be customized and trained easily by the client with bespoke datasets relevant to their needs. (It might also be the case that the value of datasets rockets in response to these developments – like getting a cheap, fast, efficient games console, only for the price of the games to go up).

By which time, the open-source community is likely to have launched and grown a thriving market in exactly that kind of more personalized AI product, and established significant amounts of customer loyalty as a result.

The open-source invasion of generative AI is not, as such, the end of the world for the proprietary tech giants and their AI investments. But it does mean a relative democratization of the technology, which will strike a very great number of businesses – not to mention enthusiastic individuals – as an extremely attractive alternative to paying big business prices for less agile models.

The post What might open-source generative AI mean for proprietary software? appeared first on TechHQ.

The US government has announced a series of measures to address both the challenges, the opportunities and the concerns over artificial intelligence. In recent months, since the launch of the ChatGPT generative AI by Open AI (backed by Microsoft), the technology has been seen as a) the new wundertech, being added to everything, b) an easy tool for cybercriminals to use to ruin the world, c) a potential threat to the lives and existence of humanity, and d) an annoying data privacy challenge.

If this sounds like hyperbole, it’s worth remembering the open letter from Elon Musk, Steve Wozniak et al, begging that generative AI be paused at GPT-4 level. And the admittedly brief banning of ChatGPT in Italy while data privacy and security assurances were sought – and apparently received. And China’s clampdown on any generative AI tech that wasn’t developed within a strictly socialist training regime, etc, etc.

READ NEXT

Expert leaves Google, warning of the dangers of generative AI

A two-stranded plan.

There’s little doubt that generative AI can help speed up and – with appropriate truth models for reference – both simplify and improve the world in which we live. But there has been enough noise and concern about the technology, and in particular its sudden rapid deployment and potential for confident error, to stir the White House into action.

In particular, there are two strands to the government’s proposed action plan on AI.

The first strand includes the introduction of policies – and, it is assumed, standards on things like data privacy – for the procurement and use of AI systems by federal agencies.

Those policies are expected to significantly skew the market within the US and possibly further afield in terms of which systems are “approved,” with those that are being able to leverage significant market force on the back of their “safe-listing” for use by federal organizations, or potentially becoming federal-only suppliers, locking high standards of security into the AI systems used by local and national government agencies.

That in turn is expected to lead to a consistent level of AI security and experience across the likes of government and agency websites, as well as at things like security checkpoints (including potentially border points and airport security).

The second strand of the plan is to allow the National Science Foundation to spend $140 million on promoting research and development in AI. The idea behind that research will be to create a handful of research centers, investigating how AI can be used to advance the nation as a whole in several areas, setting it to problems like climate change, agriculture, and public health.

The double-stranded plan aims to both “legitimize” AI to some extent through the research centers and the multiplicity of essentially government-funded applications for the technology, and to set rules around what the technology needs to be able to deliver in terms of security, truth, and genuine assistance if it’s to be allowed near government systems.

The fold-back on that is that when it is used by government systems, there will be at last some level of certainty and legitimacy conferred on the technology as a whole.

Meeting the superstars.

The double-stranded plan was announced as Vice President Kamala Harris met with high profile figures from the already rapidly-expanding AI industry, including the CEOs of Google, Microsoft, and ChatGPT-creator OpenAI. The meeting was to underscore the importance of ethical, responsible, believable AI.

As yet, no announcement has been made on how, for instance, the AI technology used for federal systems will apply truth models, in the absence of an objective truth in things like ChatGPT, GPT-4, Bard and other similar generative AI.

READ NEXT

AWS joins the generative AI arms race. Here’s what it’s providing

After the meeting, VP Harris said “Government, private companies, and others in society must tackle these challenges together. President Biden and I are committed to doing our part — including by advancing potential new regulations and supporting new legislation — so that everyone can safely benefit from technological innovations.”

White House Press Secretary Karine Jean-Pierre, meanwhile, described the discussions between the Vice President and the AI supremos as “honest” and “frank.” It’s worth noting that had the word “productive” been in any reasonable sense useable following the meeting, she would have used it to instil a sense of positivity in the audience.

Threats and responsibilities.

The meeting is understood to have dealt with a range of pressing issues arising from AI technology, including: AI-created deepfakes and misinformation, the likes of which could be used to sway opinion in democratic elections; potential job losses linked to the rise of automation and AI; the possibility of biased algorithmic decision-making; physical injuries or deaths in autonomous vehicles; and, naturally, the rise and rise of AI-powered malicious hackers and hack-sellers, the like of which are already operating on the dark web to “democratize” the hacking process.

Vice President Harris said generative AI companies had an “ethical, moral and legal responsibility to ensure the safety and security of their products,” and that they would be held accountable under existing US laws, while she was willing, if need be, to create new laws to meet the needs of the age.

President Biden, who apparently “stopped by for a surprise visit” – Washington code for “threw his weight behind his VP without officially taking the meeting” – is said to have “underscored that companies have a fundamental responsibility to make sure their products are safe and secure before they are deployed or made public.”

Reading the room, it feels as though the Biden-Harris administration read the AI industry a new-fangled version of the Riot Act, ensuring the companies understood that if they were going to make millions of dollars from this technology, and have it integrated into systems upto and including federal level, there was a burden of significant responsibility that would come with it.

READ NEXT

Alibaba launches generative AI chatbot – just before China lays down prescriptive rules

Other plans.

The US is in no sense alone in looking for a way to deal with the rapidly evolving opportunities and dangers of generative AI. In fact, it could almost said to be late to the party – the EU has been in the process of getting an AI Act together since 2021, which would set up rules for the use and function of artificial intelligence within the bloc.

The UK, which could reasonably have been said to have other things on its To-Do List since 2016, but which still aims to become what it calls a “cyber-superpower,” has been holding a parliamentary inquiry into AI technology throughout 2023, examining both the risks and the opportunities of the technology, similarly trying to find a coherent path on the governance of AI, both existing and emergent.

While these ongoing inquiries and “discussions” take place, more and more AI is being deployed in an environment of relative freedom from the responsibilities that the likes of the White House are assessing.

The second half of 2023 is likely to see a shift in the focus of generative AI companies from the gold rush period of getting the technology out there and integrated into every conceivable system, to a more stabilizing period where the rules and responsibilities as they eventually emerge are met and demonstrated across the board – with a natural rate of fall-out in terms of companies that cannot or will not comply.

The post White House underscores responsibilities of the generative AI industry appeared first on TechHQ.

Excel is the world’s leading spreadsheet, used in millions of businesses around the globe. If you run a business, or manage one, or have any dealings with its Excel function, and you don’t think you need to know how to perform basic data analysis in the program, you’re only getting a fraction of the value you can get from your Excel spreadsheet. So we put together a guide to basic data analysis on Excel, to maximize your power over your spreadsheet investment.

READ NEXT

How Best To Increase Your Excel Power Use

The most important elements of data analysis on Excel.

There are a handful of basic data analysis elements every business needs to know how to handle, including sorting, filtering, charts, and pivot tables. Let’s take a whirlwind tour of those elements, so you’ll have a good idea of your way around basic data analysis on Excel.

Sorting.

Sorting is the fundamental process of getting your data in the order in which you need it.

There’s a simple sort and a complex sort.

The simple sort allows you to sort data in one column easily. You simply click on any cell in the column, select the Data option from the ribbon at the top of the page, and press one of two buttons in the top left of the screen. AZ will sort the column’s data in alphabetical order. ZA will do the same thing but in reverse alphabetical order (the same applies to numerical columns – AZ will sort in ascending numerical value, ZA in descending numerical value).

READ NEXT

Should you use Microsoft Excel as a database?

The complex sort involves highlighting all the columns you want to sort.

Then you click the Sort button (next to the AZ and ZA buttons). That opens up a dialog box that allows you to customize levels of sorting. If you want to sort by salesperson’s surname first, and then amount sold by people with similar names, you can specify your primary, secondary and even tertiary sort criteria, so you can build a sort engine that applies to your particular spreadsheet, and with the click of a couple of buttons, manipulate your data so that it displays in the most useful, at-a-glance way for your purposes.

Custom sorting.

So far, so good – if you have alphabetic or numeric values, you can simple sort or complex sort them. But not everything in your spreadsheet will have a value attributable to, for instance, the way they’re spelled. If you have classifications of sales performance like High, Medium, and Low, an easy way to see how your company’s sales are going is to sort by these attributions. For that, you’ll need a custom sort.

The process is similar to a complex sort – select the columns you want to apply the sort to, select the Data tab, and go into the Sort drop-down. In the Order drop-down, you’ll see the tantalizing “Custom List…” option. Select that.

That opens up a separate dialog box, where you can build custom lists – enter the words in the order of priority you want to sort by, for instance high, medium, low, or low, medium, high. Add your new list and click OK to sort your highlighted data by the criteria you’ve selected. Building a number of custom lists is a useful way to bring your data under your control, whatever you need it for.

READ NEXT

A Beginner’s Guide To Programming Excel Macros In VBA

These lists can also be used for things like monthly formatting (If you tried to do monthly formatting based on alphabetical sorting of course, April and August would show first).

Filtering.

So now you’re a data-sorting wizard. The next step in your basic data analysis training on Excel is filtering. Filtering is how you pick and choose results to be highlighted based on their meeting advanced criteria.

The great thing about filtering is that it can give you deeper levels of insight than straightforward sorting, but in Excel, the process begins in very much the same way.

Highlight the data you want to filter, or click inside a cell if you want to apply the filtering to the whole sheet.

Open the Data tab. Next to the Sort function, you’ll see the Filter button, which looks like a funnel.

What you’ll see now is that arrows have appeared in each of the column headings in your sheet. Click the heading that defines how you want to filter – for instance, if you sell to multiple countries, but you want to filter for US sales only, click on the column heading for by-country sales.

You’ll open a dropdown that allows you to select which of the types of results you want to filter for – eg US sales. Check the box or boxes you want to filter for, click OK, and your spreadsheet will only display results for US sales. Whereas with custom sorting, all your data will continue to be shown, just in the sorted order you want, filtering lets you cut to the chase for custom reports. Once you have your filtered dataset, you can of course then continue to sort it as you wish.

Charts.

They say a picture paints a thousand words, which is why sometimes you want your data displayed graphically.

Fortunately, Excel has an easy way to turn your data into charts.

As usual, highlight the columns of data you want to represent as a chart.

Click the Insert tab. Find the Charts group – you’ll see representations of different types of chart and graph – and click the type you want to use. There are pie charts, various bar graphs, and several types of line graph you can choose from. Once you’ve clicked to choose your chart type, your data will be represented as that type of chart. Add a title to it, for ease of explanation, and you’re good to go.

If it turns out you want to use a different type of chart instead, simply select your chart, open the Chart Design tab, and you’ll see a dropdown list of all the chart types available. Clicking on any of them will give you a sneak preview of how your data will look in each chart type. Select the one you want, press OK, and you’ll replace your previous graph with your new graph.

This can be one of the more satisfying aspects of basic data analysis on Excel, because it can make dry data instantly understandable in a graphical format.

Pivot tables.

Pivot tables are one of the favorite data analysis tools of longstanding Excel users – they’re almost like magic spells for data. If you have a large dataset, getting meaningful takeaways from it can be difficult. Pivot tables make it easy.

Say you sell wing nuts, lug nuts, cross head screws, flat head screws, six types of screwdriver and three varieties of hammer, all with different unit costs. Say you sell domestically and export to ten different countries too. Now imagine you wanted the data for how many lug nuts you sold to France and Germany in the last month. That’s a combination of four data points – lug nuts, Germany, France, and last month.

Pivot tables are how you stop wading through masses of sales data to display only want you want to know.

Click any cell in the data sheet. Open the Insert tab, and click PivotTable. That opens up a dialog box, and pre-fills the most likely data – the whole sheet – and pre-selects the option that lets you create your pivot table in a new sheet, rather than overwriting your current spreadsheet.

Click OK and you open a second dialog box, where you get to specify those elements you want – Product: lug nuts. Country: France and Germany. Month: December, for instance.

You’re effectively telling Excel which data fields you want to combine into the query in your pivot table. When you click OK, you’ll generate your pivot table that will show you your sales numbers of lug nuts in each of your selected countries last month. Pivot tables really are the magic spells of Excel – they allow you to specify the results you want from potentially vast data fields, and to get your answers in seconds, with no calculation on your part.

Setting you free in Excel.

With these four basic data analysis disciplines under your belt, you should be able to do most of the things you need to do on a day-to-day basis, as far as your Excel data is concerned.

With simple sorts, you can clarify your data in a way that makes sense. With complex sorts, you can begin to bring order to the data. With filtering, you can focus on particular elements of the data and only show those elements, for a significant boost in clarity and an easy way to actively interrogate your large data fields.

Pivot tables take you to a whole other level of data interrogation, because you can create relatively complex queries in seconds, that will cut through even enormous data fields and present you concisely with the results you need. And charts help you turn any amount of data into easily digestible graphical representations, be they sales charts, staff costs, overall outgoings or revenue trends.

With these four data analysis power moves in your pocket, you’re able to run your business, getting access to all the data you need in just a handful of heartbeats.

The post Our guide to basic data analysis on Excel appeared first on TechHQ.

Microsoft has disclosed that it plans to loosen its licensing requirements with cloud companies as it seeks to fight off regulators after growing complaints of monopolistic practices. The tech titan is trying to avoid a replay of its epic battles against EU and US antitrust enforcers in the late 1990s that ended in major court cases and big fines.

READ NEXT

More cloud complaints against Microsoft Azure in Europe

At the heart of the controversy is a 2019 decision that made it more expensive for cloud companies to access Microsoft’s Office 365 when they were running through data centers operated by rivals, such as Amazon or Alibaba. European cloud companies including French cloud computing services provider OVHcloud filed an antitrust complaint against Microsoft Corp to the European Commission, the EU’s antitrust regulator, accusing Microsoft cloud unit Azure of abusing its dominant position, undermining fair competition, while limiting consumer choice in the cloud computing services market.

They also said the user experience was made worse and that there are incompatibilities with certain other Microsoft products when not running on Azure, the company’s own data operating system. Last month, Italian cloud provider Aruba SpA came forward to admit that it also has issues with Microsoft practices in bundling services in the region and undercutting competitors.

Although the complaints come at a time of recent heightened government oversight in the cloud market, Microsoft in particular has been fortunate enough to have not been at the center of attention, unlike its fellow rivals. That is mainly due to its ‘playing-it-safe’ nature following its own antitrust battles two decades ago when the US Department of Justice and the EU sued Microsoft for its business practices. But now some of Microsoft’s customers and a handful of its fiercest rivals are giving the software and cloud computing behemoth a renewed focus in the European fair markets spotlight.

“We’re just changing the licensing terms so that at their heart, cloud providers that are based in Europe can run Microsoft software pretty much the same way Microsoft can,” company president and vice-chair Brad Smith told reporters this week in Brussels. Smith insisted that the changes were a “first step” and that “we probably have some more things that we’re going to need to do.”

Microsoft over the years accumulated fines of 1.6 billion euros in the EU for anti-competitive practices regarding its Internet Explorer browser, Windows operating system, and software licensing rules. Besides the complaint by OVHcloud and other unnamed companies, there have also been other complaints in recent years within the region itself, alleging Microsoft for bundling its cloud products in a manner that complicates and made things difficult for competitors. For instance, in 2020, San Francisco-based business-messaging app Slack Technologies Inc. complained to the EU about Microsoft’s bundling of its rival Teams workplace collaboration product with its popular Office software. 

The Redmond, Washington state-based company is also the subject of an earlier 2021 complaint to the European Commission by a different set of companies led by the German Nextcloud. They denounced the “ever-stronger integration” of Microsoft cloud services, which it said complicated the development of competing offers.

YOU MIGHT LIKE

AMAZON

Is Amazon dodging US lawmakers and their antitrust probe?

“The changes we are making today on behalf of European Cloud Providers are grounded in feedback we heard in meetings with several of those providers across Europe,” Smith outlined in his Microsoft blog detailing the licensing alterations as well as Microsoft’s sweeping strategy in Europe. “I joined other senior Microsoft business leaders so I could participate myself in remote meetings with the CEOs of two European providers.

“Some of the most compelling feedback for me personally came from a CEO who said that he felt that he “was a victim of friendly fire in Microsoft’s competition with Amazon.” It was hard to hear this – but he was right,” Smith admitted. “Over the past few years, our focus on competing with the largest technology providers has resulted in us not being as attentive to the impact on our cloud provider partners. We are making changes to remedy this, beginning today.”

Amidst the complaints, the EU has just finalized legislation that would designate several large US-based companies, including Microsoft, as “gatekeepers” that would need to abide by a new set of rules for how they deal with competitors and consumers. In contrast, reports are claiming that the US is pressing the EU to revise the rules and make them focus on other tech firms too, not just American companies. 

 

The post Microsoft makes cloud changes to avoid EU antitrust clash appeared first on TechHQ.

Microsoft this week reported strong quarterly earnings, powered by demand for cloud computing. The tech titan said it made a profit of US$16.7 billion on revenue of US$49.4 billion in the first three months of this year, 8% and 18% respectively, more than in the period a year earlier.

READ NEXT

Microsoft flexes speech recognition muscle with US$19.7B Nuance acquisition

“Going forward, digital technology will be the key input that powers the world’s economic output,” said Microsoft chief executive Satya Nadella. “Across the tech stack, we are expanding our opportunity and taking share as we help customers differentiate, build resilience, and do more with less.”

Microsoft shares rose more than 4% to US$282.44 on the earnings figures, which came with an optimistic outlook for the current financial quarter. Revenue in the company’s “intelligent cloud” unit that meshes datacenter-hosted software with artificial intelligence surged from the same period a year earlier, Microsoft reported.

“Continued customer commitment to our cloud platform and strong sales execution drove better-than-expected commercial bookings growth” along with cloud computing revenue, Microsoft chief financial officer Amy Hood said in the earnings release.

The pandemic accelerated a shift to relying on the internet for work, education, shopping, socializing and entertainment, with Microsoft seemingly positioned to benefit from lifestyle changes that will remain even as people return to being out and about.

A business and productivity unit at Microsoft that includes its online suite of Office 365 software saw revenue grow with the help of a 34% increase in money taken in by career-focused online social network LinkedIn, the earnings report showed.

“Growth for LinkedIn was the most surprising,” CFRA equity research vice president John Freeman told AFP. “LinkedIn continued to be Microsoft’s lower profile success story. That acquisition is looking better and better every year and every quarter.”

Microsoft bought LinkedIn for slightly more than US$26 billion in 2016. Money taken in for content and services at Microsoft’s Xbox video game division rose 4% in the recently ended quarter as the company works to beef up its cloud-based games subscription offering.

Microsoft is seeking regulatory approval for its US$69 billion deal to buy video game powerhouse Activision Blizzard. Merging with troubled Activision will make Microsoft the third-largest gaming company by revenue, behind Tencent and Sony, the technology behemoth said — a major shift in the booming world of games.

YOU MIGHT LIKE

CYBERSECURITY

Google beats Microsoft to buy security specialists Mandiant

Activision, the California-based maker of Candy Crush, has been hit by employee protests, departures, and a state lawsuit alleging it enabled toxic workplace conditions and sexual harassment.

“Acquiring Activision will help jump-start Microsoft’s broader gaming endeavors and ultimately its move into the metaverse with gaming the first monetization piece of the metaverse in our opinion,” Wedbush analysts said after the news broke.

 

 

© Agence France-Presse

The post Cloud computing helps power Microsoft to strong profitability appeared first on TechHQ.

• Microsoft cybersecurity campaign and initiative will skill and recruit workers in additional 23 countries
• Cybersecurity Ventures predicts that there will be 3.5 million cybersecurity jobs open globally by 2025
• In countries where Microsoft is expanding its campaign, only 17% of the cybersecurity workforce are female

READ NEXT

Microsoft to address cybersecurity skills dearth with quarter million new jobs

Microsoft has announced that it will expand its cybersecurity skilling initiative to include an additional 23 countries from Europe, Asia, and Africa.

Due to their elevated cyberthreat risk, the company aims to get ahead of the demand in their skilling initiative in countries like Australia, Brazil, Canada, India, Colombia, France, Germany, New Zealand, South Africa, Sweden, Switzerland, and the United Kingdom.

These countries have a significant gap in their cybersecurity workforces regarding the number of professionals employed versus the demand and a lack of diversity.

Microsoft to close the Cybersecurity gap

The initiative, first launched last year, is an effort by the tech giant to help plug the global shortfall of cybersecurity professionals. One of their company goals is to ensure traditionally excluded populations have opportunities to enter the cybersecurity workforce, including women.

Kate Behncken, vice president and lead of Microsoft Philanthropies, wrote in her blog that in countries where the company is expanding its campaign, only 17% of the cybersecurity workforce are female.

Deloitte Global predicts that sizeable global technology firms will only reach nearly 33% overall female representation in their workforces in 2022, up slightly more than two percentage points from 2019.

To fully understand the skills gap and share best practices, Microsoft is also launching a new partnership with the Organization for Economic Cooperation and Development (OECD).

The collaboration will create a detailed study on the skills gap in selected countries and improve the ability to grow cybersecurity workforces through postsecondary education and training.

Microsoft cybersecurity campaign aims to skill and recruit workers

The skilling campaign saw the company partnering with 135 community colleges to skill and recruit workers into the cybersecurity industry. Microsoft provides access to free curriculum, educator training, and tools for teaching. The company also shares cybersecurity best practices with schools through the American Association of Community Colleges.

The first of three cohorts are provided grants for funding technical assistance to accelerate their cybersecurity programs. Finally, the company grants scholarships to students seeking a degree or certification in a cybersecurity field.

Meanwhile, in Colombia, Microsoft cybersecurity skills work to support the government’s initiative to increase its national cybersecurity capacity. The collaboration is helping people acquire cybersecurity and digital skills needed for in-demand jobs.

Cybersecurity facing a workforce shortage

Cybersecurity is one of the most important and fastest-growing industries today. However, it has become an even more significant threat in the past few years as people become increasingly reliant on digital technologies.

Cybercriminals are increasingly sophisticated and the threat landscape more diverse. This is seen from supply chain disruptions to recent ransomware attacks that impacted thousands of people, businesses, and governments.

YOU MIGHT LIKE

CYBERSECURITY

Microsoft has been on a cybersecurity splurge to fight mounting threats

By 2025 there will be 3.5 million cybersecurity jobs open globally, according to Behncken quoting Cybersecurity Ventures’ prediction. Despite its growth, the field faces a workforce shortage and a widening skills gap among workers.

Investment in a cybersecurity workforce is critical

The investment in the cybersecurity workforce ensures there are enough people with the skills to protect digital infrastructure, economy, and way of life. A country or organization is only as strong as our weakest link, and right now, that weakest link is the lack of skilled cybersecurity professionals.

The post Microsoft wants to close the cybersecurity skills gap appeared first on TechHQ.

Google has beaten Microsoft to sign a definitive agreement to acquire Mandiant, a leader in dynamic cyberdefense and response, in an all-cash transaction valued at approximately US$5.4 billion.

READ NEXT

Why the ability to predict cybersecurity threats matter

Upon the close of the acquisition, Mandiant will join Google Cloud. However, this is where things can get a little tricky. Why exactly did Mandiant end up being acquired by Google and not Microsoft?

According to a report by Bloomberg a month earlier, Microsoft was in talks to acquire the cybersecurity research and incident response company. The deal was expected to bolster Microsoft’s efforts to protect customers from hacks and breaches.

A bit of history on Mandiant, the company was acquired by FireEye in 2013. Mandiant became a standalone company again when FireEye was acquired by Symphony Technology Group. Symphony then combined FireEye with McAfee Enterprise to form Trellix,

As Mandiant’s primary focus is on incident response and cyberintelligence cases, it was no surprise that tech giant Microsoft was interested in acquiring them. The potential deal would have given Microsoft even deeper insight into consequential hacks.

But now, it seems Google has emerged as the buyout winner. The acquisition of Mandiant will instead complement Google Cloud’s existing strengths in security.

Acquisitions are a sign of power and dominance

Acquisitions among big tech companies are common over the last couple of years. In fact, most big tech companies often acquire smaller tech startups to boost their own position in the market.

As most acquisitions among big tech companies often revolve around improving their product offerings, many of them are often criticized for monopolizing the space and eliminating competition.

The reality is though, the competition and monopolization by the big tech firms continue to impact how smaller players operate. Last year, one of the biggest tech acquisitions was supposed to be NVIDIA’s US$40 billion acquisition of ARM. However, the deal was terminated following significant regulatory challenges preventing the consummation of the transaction.

Last year also saw Oracle acquiring electronic medical records and healthcare IT services company Cerner for US$28.3 billion as well as Salesforce wrapping up its US27.7 billion acquisition of Slack. In October 2021, private equity firm Symphony Technology Group completed its US$1.2 billion acquisition of security company FireEye, combining it with McAfee Enterprise from Trellix.

This year, Microsoft acquired Activision Blizzard for US$68.7 billion in the biggest tech acquisition ever made. The deal however is also facing scrutiny by federal prosecutors and securities, eager to ascertain if another ‘big tech’ player is overstepping fair competition grounds.

Google vs Microsoft for Mandiant

Now, the deal is not completed yet as it will be subjected to regulatory approvals and such. And it won’t be surprising if Microsoft kicks up a fuss about the acquisition as well.

As Wedbush analyst Dan Ives puts it, the acquisition will have a major ripple impact across the tech space.

This is all about Mandiant being further integrated into Google Cloud with more cyber threats facing enterprises on the shift to cloud and Mandiant establishing itself as the Navy Seals of cyber security. We believe this deal will have a major ripple impact across the tech space.

— Dan Ives (@DivesTech) March 8, 2022

There is no denying that modern threats already require businesses to detect and respond to adversaries quickly; analyze and automate threat intelligence to scale threat detection across organizations; orchestrate and automate remediation; validate their protection against known threats, and visualize their IT environment in order to identify and to simulate solutions against new threats.

Hence, the cloud represents the best way to change the security paradigm by helping organizations address and protect themselves against entire classes of cyberthreats — while simultaneously accelerating digital transformations at a rapid pace.

YOU MIGHT LIKE

CYBERSECURITY

Stuxnet to DarkSide – Tracking the biggest cyber attacks in history

With the addition of Mandiant, Google Cloud will enhance its offerings to deliver an end-to-end security operations suite with even greater capabilities to support customers across their cloud and on-premise environments.

As a recognized leader in strategic security advisory and incident response services, Mandiant brings real-time and in-depth threat intelligence gained on the frontlines of cybersecurity with the largest organizations in the world. Combined with Google Cloud’s cloud-native security offerings, the acquisition will help its enterprise customers globally to stay protected at every stage of the security lifecycle.

“Organizations around the world are facing unprecedented cybersecurity challenges as the sophistication and severity of attacks that were previously used to target major governments are now being used to target companies in every industry,” pointed out Thomas Kurian, the CEO of Google Cloud.

“There has never been a more critical time in cybersecurity. Since our founding in 2004, Mandiant’s mission has been to combat cyberattacks and protect our customers from the latest threats,” said Kevin Mandia, Mandiant’s chief executive. “To that end, we are thrilled to be joining forces with Google Cloud. Together, we will deliver expertise and intelligence at scale, changing the security industry.”

The acquisition is subject to customary closing conditions, including regulatory approvals and recipients by Mandiant stockholders. It is expected to close later this year.

The post Google beats Microsoft to buy security specialists Mandiant appeared first on TechHQ.

Microsoft courted the favor of antitrust regulators this midweek who are scrutinizing its plan to buy video game maker Activision Blizzard, promising that any app store it builds will treat developers fairly.

READ NEXT

Microsoft’s Activision acquisition – what it means for the metaverse & beyond

Microsoft president Brad Smith laid out a set of “Open App Store Principles” that will apply to the online shop it runs for Windows-powered computers and “the next-generation marketplaces we will build for games.”

“We have developed these principles in part to address Microsoft’s growing role and responsibility as we start the process of seeking regulatory approval in capitals around the world for our acquisition of Activision Blizzard,” Smith said in a statement. Microsoft’s US$69 billion deal to buy video game powerhouse Activision Blizzard needs to pass muster with regulators in Europe and the United States intent on reining in tech titans.

After the merger plans were announced last month, analysts told AFP the deal would certainly be scrutinized, but likely less intensely than would an acquisition by Amazon, Google, or Facebook-parent Meta. Microsoft appeared to be trying to differentiate itself from Apple and Google, who have been accused of tightly controlling their respective app stores and taking too big a bite out of revenue brought in by developers.

Principles outlined by Microsoft included allowing all developers access to its app store and not requiring them to use the technology firm’s payment system for in-app transactions. All apps in a Microsoft store will be treated equally, according to Smith.

“We want to encourage more innovation and investment in content creation and fewer constraints on distribution,” the Microsoft president insisted. “The world needs open app markets, and this requires open app stores.”

That being said, do the benefits of the Microsoft buyout really outweigh the risks of the acquisition, especially with the regulatory scrutiny? When TechHQ asked about this, Dexter Thillien, the lead analyst of technology and telecoms at the Economist Intelligence Unit, believes that the issues may have actually sweetened the deal for the X-Box maker instead.

“You’re right that it will increase regulatory scrutiny on Microsoft, and that there are several issues which need to be dealt with at Activision (and at Microsoft itself), but those issues potentially made the deal more attractive to Microsoft, as it lowered the price Activision could have asked for considering its assets and its content,” Thillien asserted.

“The Activision deal follows this strategy, and is perhaps a better fit considering Microsoft does have some prior experience in gaming,” he went on, adding that he believes Microsoft’s plan is to use gaming to boost its cloud offering, Azure, by having more customer data, thus boosting its AI capabilities. “This would also position the company for the metaverse in the future, where it will leverage both gaming and its core enterprise business.”

YOU MIGHT LIKE

PRIVACY

Instagram, Facebook, Uber Eats and more: The most invasive apps on iOS

Tech giants have come under fire from multiple fronts for app store controls. In January, Apple was fined five million euros (approximately US$5.6 million) by the Dutch consumer watchdog for failing to allow dating app operators to choose payment options other than the Apple Pay system in its Dutch App Store.

In November, a US federal court ordered Apple to loosen control of its App Store payment options after a legal clash with Fortnite creator Epic Games, which had accused the iPhone maker of operating a monopoly in its shop for digital goods or services. The US judge, however, said Epic had failed to prove that antitrust violations had taken place.

Epic Games is locked in bitter legal battles with Apple and Google, whose operating systems run nearly all the smartphones in the world. Both companies charge what they deem appropriate fees on transactions made on Apple’s App Store and Google Play. But app makers have become increasingly furious in recent years over the cut taken by the tech giants.

 

 

 

 

 

© Agence France-Presse

The post Microsoft boss vows app store equality after Activision buyout appeared first on TechHQ.