CBinsights has released Q1 ’23 AI funding report. There’s a notable drop compared to the previous period, but that’s expected considering overall belt-tightening in the tech sector. At the same time three generative AI companied raised enough dough to gain a unicorn status, and only one of them from the US! Overall, M&A deals are up and funding is sure to return to the 2022 level or surpass it by the end of the year. Money doesn’t like standing still…
Heard of Steven Levy’s Plaintext newsletter? If not, sign up for it. If not, then after reading his latest conversation output with Gary Marcus, the AI critic turned into even more of oneself lately. Marcus has an interesting idea of forming one International Agency for AI, a non-profit to guide and guard after the industry and nation states alike.
Caryn AI is a girlfriend for hire service, I mean, a digital twin of a Snapchat influencer designed to reduce loneliness. Or that’s what its creator states whilst hoping to pull in $5m a month at the engagement rate of $1 per minute. “CarynAI is a step in the right direction to allow my fans and supporters to get to know a version of me that will be their closest friend in a safe and encrypted environment,” Caryn Marjorie added. No, there’s no altruism in play here, pure capitalism. Sex sells.
Responsible AI is a theme that all major developers aim to invest in. After all, the trust or lack of it thereof, can change the users perception of a company and encourage them to look for alternatives. When an AI system recommends us more positive tone in messages, we are likely to receive more positive response. The technique is called latent persuasion. The same applies when the tone and messages of the chatbot are negative or biased (again, the bias may be by design). And biased they are, reflecting the values of the creators and validators. A study called Whose opinions do LLM’s really reflect? covers how we, the users of these systems, behave based on the tools we use. So our choice of tools will impact how we are perceived by others.
Who’s on the bus and who’s still trying to catch it? Ben Thompson covers Google I/O and related regulatory topics in his excellent Stratchery post.
Google has been in news with its Bard AI chatbot, but not so much with the work its been doing with pharmaceuticals industry attempting to cut the lengthy process of discovery/trial and time to market.
A subset of US voters are scared of the AI race. However, I have to agree with the words of founder of Anyscale, a UC Berkeley professor Ion Stoica “Americans may not realize how pervasive AI already is in their daily lives, both at home and at work”. Unknown raises fears, but are your congressmen any wiser than an average Joe on the potential benefits and threats the AI race can pose to your future? Ask them.
How very true! Corporate L&D often focuses on desired outcomes from the management, not from the people (those to be trained). Are we providing the most accurate skills training at the people who need it most at their time? Often we don’t. How to improve it?
Grammarly was chosen by many as their go-to tool for churning out readable coherent content. As tech giants are eating its lunch, Grammarly is desperate not to lose (paying) customers and claims it’s there for good. It feels that deep integration with Microsoft’s Azure infrastructure is a step towards showing off its product capabilities and eventually being acquired by MSFT. Agree with me?
An interesting peek into the future of content generation and publishing. At which point will the customers of the ‘content mills’ stop caring about the human touch? Is it when they can’t distinguish between human and machine created content or when the deluge of AI-generated stuff always beats theirs for the attention? AI is already writing books, websites and online recipes – The Washington Post
Regulation is all the rage this spring. And for a good reason, as race to the bottom gains momentum. And what about the US-China rivalry in the space as the roadblock to regulation? Will the US be driven by the FOMA or by the prospects of angry out-of-job mobs on streets? AI Regulation Fever Sweeps EU, US, and China (foreignpolicy.com)
As I search for this, Bing retrieves information and I won’t bother looking any further. Is that good or bad?
Being frightened when you’re successfully flogged your firm to Google and ready to retire is OK. Yann LeCun counterargument doesn’t fill anyone with pure joy either “I completely disagree with the idea that machines will dominate humans simply because they are smarter, let alone destroy humans.” “Even within the human species, the smartest among us are not the ones who are the most dominating,” says LeCun. “And the most dominating are definitely not the smartest. We have numerous examples of that in politics and business.” Geoffrey Hinton tells us why he’s now scared of the tech he helped build | MIT Technology Review
Happy with the position of tech firms with regards to your data and privacy? Gideon Lichfield from Wired interviews Signal’s Meredith Whittaker in a “Have a nice future” podcast episode “Can we get a little privacy?“. Recommended listening.
Interesting use case for a chatbot, and a bit worrying. As an experiment, try asking these chatbots for an opinion on a PM of a not so friendly neighbouring country. Push it a bit and read the responses. People, whose main connection with the wider world is their smartphone, are especially susceptible to the messages the machine tells them. ChatGPT is spawning religious chatbots in India – Rest of World
An excellent NewYorker essay byTed Chiang exploring the bleak aspects of capitalism and how the AI race feeds the aspirations of said systems owners. “Today, we find ourselves in a situation in which technology has become conflated with capitalism, which has in turn become conflated with the very notion of progress. If you try to criticize capitalism, you are accused of opposing both technology and progress. But what does progress even mean, if it doesn’t include better lives for people who work? What is the point of greater efficiency, if the money being saved isn’t going anywhere except into shareholders’ bank accounts? We should all strive to be Luddites, because we should all be more concerned with economic justice than with increasing the private accumulation of capital. We need to be able to criticize harmful uses of technology—and those include uses that benefit shareholders over workers—without being described as opponents of technology.” Agree or not? Will A.I. Become the New McKinsey? | The New Yorker
As anyone with mild interest to the topic has noticed, there’s been a growing concern over our relationship with the AI systems. The fear is that these systems, when left to their own devices (pun intended) will at some point in not too distant future see us, the humans as obsolete and concoct a cocktail of measures to stop anyone or anything with potential to derail it. The ‘it’ being a artificial general intelligence or AGI system which has capacity to learn rapidly, design and deploy tools to execute it’s wishes. Sounds scary? Perhaps. Too sci-fy, definitely not.
The following is reflection of the content I’ve consumed over the past weeks:
Industry insiders are potentially terrified yet over-excited with regards to their creations.
There are multiple open letters calling on a temporary pause for further training the current models with capabilities of Chat-GPT4 and above. Some were late to the game, others want to help the industry leaders to justify taking the time off necessary for the guardrail to be developed.
AI regulation. China, US, EU – all are taking different approaches to regulating the AI with the US trailing behind. Brussels has sprinted ahead of the US and is designing a broad, risk-based approach. Many others are looking in envy. The rivalry between the US and China may become a stumbling block as the fears of losing out drive the US capitalist model forward, and maybe not towards the best outcomes. I can’t fully agree with Foreign Policy when it writes“The East is almost exclusively focused on building up its R&D capacity and is largely ignoring the traditional ‘guardrails’ of technology management,” the authors wrote. “By contrast, the West is almost exclusively focused on ensuring that these guardrails are in place”. The West approach, as it often happens with tech regulation, is divided between the EU, the US and the UK relevant authorities keeping their political-economic interest in mind.
…and finally, every major media outlet is covering the topic. Also, a number of niche outlets/portals have emerged, which is good as their coverage is specific and articles longer than 2 minutes. I wonder if this is scaring people too far leading to mass protests (fear of losing jobs and part of identity) or masses will remain oblivious to the oncoming changes, lost in doom-scrolling.
With so much to cover I turned to ChatGPT with its view on AI risks. The output is concise and self-explanatory:
There are several risks associated with the AI race, some of which include:
Safety risks: As AI systems become more sophisticated, they could pose a threat to human safety. This could occur if the AI systems malfunction, are hacked, or are used for malicious purposes.
Job displacement: As AI systems become more capable, there is a risk that they could replace human workers in many jobs. This could lead to high levels of unemployment and economic disruption.
Ethical concerns: The development and deployment of AI systems raise a number of ethical concerns, including privacy violations, algorithmic bias, and the potential for AI systems to be used for surveillance or control.
Geopolitical tensions: There is a risk that the AI race could fuel geopolitical tensions between countries, as each country seeks to gain an edge in AI development and deployment.
Arms race: The development of AI systems for military applications could lead to an arms race, with countries competing to develop the most advanced and powerful AI weapons.
Unintended consequences: As AI systems become more advanced, there is a risk that they could cause unintended consequences that are difficult to predict. For example, an AI system that is designed to optimize a certain task could end up causing unintended harm or creating unforeseen problems.
Next prompt is obvious for a curious person – OK, how do we tackle these concerns?
Addressing the risks associated with the AI race will require a multi-faceted approach involving collaboration between different stakeholders, including governments, industry leaders, researchers, and civil society. Here are some strategies that could help tackle these concerns:
Regulation: Governments can play a key role in regulating the development and deployment of AI systems, setting standards for safety and ethical considerations. This could include establishing regulatory bodies to oversee AI development, as well as implementing laws and regulations to ensure accountability and transparency.
Ethical guidelines: The development of ethical guidelines and best practices for AI systems could help to mitigate the risk of unintended consequences and ethical concerns. This could involve the creation of industry-wide standards for data privacy, algorithmic bias, and transparency.
Research: Continued research into AI safety and ethics is essential to address the risks associated with AI. This could involve developing new techniques for verifying and validating AI systems, as well as exploring ways to make AI more transparent and explainable.
International collaboration: International collaboration and cooperation between governments, researchers, and industry leaders can help to mitigate the risk of geopolitical tensions and an arms race. This could involve the establishment of international agreements on the development and deployment of AI systems.
Education and awareness: Raising awareness about the potential risks and benefits of AI systems is essential to ensure that the public is informed about the implications of AI development. This could involve educating the public about the potential risks of AI, as well as promoting AI literacy among policymakers and industry leaders.
Overall, addressing the risks associated with the AI race will require a coordinated and collaborative effort from multiple stakeholders, involving a range of strategies including regulation, ethical guidelines, research, international collaboration, and education and awareness.
What should we make of it? I really like the views of Max Tegmark covered by Lex Friedman in one of his longform conversations. Max’s point is that what’s happening currently isn’t arms race when the winner takes all, but a suicide race to the bottom where at the end everybody loses. There’s an excellent parallel Max brings out when comparing the current leading systems in the AI race as cute and adorable baby nobody wants to see as a risk to incumbents (the us). Lex’s podcast is one of the really good sources to aid thinking.
What will the near future look like?
This is a clear sign of what industries will be affected by the AI being connected to the internet.
Skills and education. We absolutely need to focus our education system on what skills are needed in the future. We mustn’t lull ourselves into believing the AI won’t stand up for it’s own interests (and we can’t be sure of what that is). Teaching students how to manage to AI systems from core infrastructure to security to prompt engineering is necessary. We can manage the systems only when we understand how they operate. It’s harder with a learning system that can adapt to the changes in the environment (objects around it, users, conditions) and hence we need to focus on what the world of tomorrow looks like. And to teach students to design it.
Regulation is being developed in the EU. I totally agree with the position of Margrethe Vestager, Executive Vice-President for a Europe fit for the Digital Age “On artificial intelligence, trust is a must, not a nice to have.” Meanwhile, the US begins to study of possible rules to regulate AI. Whilst the EU likes to regulate everything, supposedly for the better future, the US doesn’t really want to do anything that might give others edge over its technological prowess. Biden views the responsibility laying squarely with the tech companies and self-regulation. Not really a solid strategy when they all race to the bottom… China, on the other hand has been at the front of the pack. In an article dating to 2022, Natlawreview covers Chinese activities in regards to regulation. “China has taken the lead in moving AI regulations past the proposal stage. In March 2022, China passed a regulation governing companies’ use of algorithms in online recommendation systems, requiring that such services are moral, ethical, accountable, transparent, and “disseminate positive energy.”
What about the generative AI relationship to the energy? Training the models can use huge amount of energy to start with. On the other hand the AI systems can detect, highlight and correct the inefficiencies in industrial and energy systems. Take it as an investment in the future.
And lastly, the compensation mechanisms for everyone else. As with any tectonic shift, there will be small amount of winners and many losers in the AI race. In my view, the universal basic income (UBI) should be actively discussed in parliaments of the most digitally advanced countries. This will be the key measure tackling potential job loss created by the task automation. I recommend reading the opening position of the study released in August, 2021. I wonder how much have the position of UBI opponents changed over the past six months?
What can you do now?
Learn to understand how these systems impact you, think along, learn to identify auto-created content especially one that plays on our worst fears and hatred and call it out to authorities. Talk to your elected MP and ask their and their political party’s position with explanation on what they will do to tackle the areas GPT highlighted as a response to my prompt above. Educate the ones around you who discard the risks as nonsense or simple take ‘not-gonna-happen-to-us/in-our-lifetime’ approach. Consider that no industry will be untouched by the changes in technology landscape, some will be beneficial to us, others not so.
Aasta alguses paluti mul kirjeldada ühe riigisektori asutuse IT lähitulevikuvaade. Asutuse nime ma siin ei maini, kuid sisu ühtib paljude asutuste hetkeseisuga. Kui tunned, et saad seda kasutada, siis palun.
Sinu asutuse infotehnoloogia valdkonna ja osakonna põhilised väljakutsed ja fookusteemad lähiaastatel.
IT ei ole enam ammu lihtsalt abivahend töö tegemisel. See on muutunud peamiseks tööülesannete ja vabaaja sisustamise platvormiks, mis on endaga kaasa toonud nii jõudluse kasvu kui ka piiri hägustumise töö ja vaba aja vahel. V.a. piiratud teabega tehtavad ülesanded, on tänapäeval töötajal võimalik suuremat osa oma tööst teha seal, kus ta parasjagu aegruumis asub. Asutuse IT ning töökeskkonna struktuur ja eripära seavad terve hulga piire modernsete töökohateenuste ning koostöövahendite kasutuselevõtuks. Kui esimesed puudutavad peamiselt meie oma töötajaid ning kliente, siis teine hõlmab lisaks eelnimetatule veel väliseid partereid. Sõltumata teenustest on kõigil osapooltel sarnased ootused – pakutav peab olema kasutajasõbralik, modernne ja turvaline. Tuleviku vaates on märksõnadeks kindlasti küberturvalisuse tõstmine, koostöö riigi kesksete IT asutustega ning efektiivne arenduste ja raha juhtimine.
Mida see tegelikkuses tähendab?
Töökoha teenuste üksus peab valima seadmed ja teenused, mis tagavad kasutajatele parima võimaliku kasutajakogemuse sõltuvalt nende töö ja IT profiilist. Kasutajaseadmed peavad ’lihtsalt toimima’ nagu aastaid on Apple seadmete kohta öeldud ning tänased äriklassi arvutid koos Windows 11 ja eduka juurutusega suudavad pakkuda. Mobiilsed seadmed peavad tekitama kasutajates tunde, et see on parim nende töö tarbeks ning kasutajad ei hakka otsima alternatiivseid lahendusi. Kõike seda peab tegema eelarve piirides ning hankekorrast ja infoturbe nõuetest lähtudes. Kasutajaid tuleb pidevalt harida parimaid praktikaid rakendama ning kasutama teenuskataloogis pakutavat. Baastarkvara jt lõppkasutajale suuantud rakenduste ajakohastamine koostöös keskse teenuspakkuja kasutajatoe üksusega aitab töövõidud kiiremini koju tuua. Kindlasti peab kaaluma ühtselt juhitud 24/7 tugiteenuse sisseseadmist hiljemalt 2024 aastal. Me ei tohi unustada, et meid hinnatakse peamiselt kasutajakogemuse järgi võrreldes kasutaja eelmise kogemusega.
Fookuses parim võimalik kasutajakogemus meie tingimustes, olemasolevate süsteemide kaasajastamine ja kasutaja teadlikkuse tõstmine. Esimene eesmärk on fookuses 2023-24, teine ja kolmas on püsitegevused.
Infrastruktuuride üksus peab tagama alustaristu toimimise selliselt, et ühendused oleksid kiired, turvalised ja tagaksid kasutajatele võrreldava kogemuse sõltumata asukohast. Samuti peab tagama alustaristu toimimise ning turvalisuse ja vastavuse arendatavate ärirakendustega. Hea koostöö infoturbe, alustaristu ja kasutajatoe inimeste vahel on kriitilise tähtsusega tagamaks parimat võimalikku kasutajakogemust meile kõigile. Samuti peab hästi toimima koostöö väliste partneritega. Nendega koostöös peaks keskenduma ka infoturbe nõuetele ning vastavate lahenduste, sh keskse logihalduse juurutamisele. Peame kõigis arendustes silmas pidama ka keskse teenusepakkuja poolt pakutavaid lahendusi ja teenuseid ning koostöös nende ekspertidega juurutama lahendused, mille saaks neile üle anda vastavalt tänasele migratsioonikavale.
Fookuses robustne ja toimiv alustaristu nii peamajas kui välisesindustes, mis on arendatud koostöös kesksete IT asutuste ning väliste ekspertidega, infoturve ja automaatika. Kõik kolm on püsitegevused; infoturbe nõuetele vastavus, alustaristu värskendamine ja pilvekõlbulikuks muutmine ning logimine/infoturve on fookuses 2023-25;
Arenduste üksuse peamine fookus peab olema infosüsteemide ja ärirakenduste arendusportfelli efektiivsel juhtimisel. Koostöös keskse IT teenuste pakkujaga ning oma IT kolleegide ja riskihaldusega tuleb üle vaadata ning vajadusel muuta mittefunktsionaalseid nõuded. Kuna need puudutavad peamiselt arendatavaid ärirakendusi, peaks just arenduste üksuse arhitektid nende ajakohastamise eest seisma. Moraalselt ja tehnoloogiliselt vananenud süsteemid tuleb uuendada, et tagada nende toimimine, kasutatavus ja turvalisus. Uute süsteemide kavandamisel tuleb kindlasti arvestada agiilsete arenduspõhimõtetega – kasutajakesksus, tagasiside, kiired arendustsüklid ja etapiviisiline lähenemine. Need tagavad tunnetatava väärtuse kõige kiirema realiseerimise. Samuti tuleb koostöös infrastruktuuri üksuse ja keskse teenusepakkujaga juurutada vajalik keskkond tagamaks ärirakenduste tehnoloogilise pilvekõlbulikkuse – see aitab meil lihtsustada haldust ning valmistada rakendusi ette migratsiooniks hübriidpilve taristule. Tarneahelat on alati võimalik optimeerida ning koostööd parandada. Efektiivne kommunikatsioon aitab tagada rollide selguse, protsessidest arusaamise ja ootuste juhtimise nii asutuses, kui majast väljas.
Fookuses äriteenuste ja infosüsteemide ajakohastamine ja jätkusuutlik arendamine, tehnoloogilise võla vähendamine ja protsesside automatiseerimine. Esimene prioriteet (2023) on selge IT nõudluse ülevaate koondamine ja hindamine. Sellele järgneb äriteenuste ja rakenduste teekaarti koostamine (2023) ja planeeritud kava elluviimine (2024-27)
Tooksin välja mõned võtmesõnad, mis on kriitilise tähtsusega kõigi üksuste vaates:
Tehnoloogilise võla vähendamine. MKMi digiarengu asekantsleri hinnangul on riigisektori IT tehnoloogiline võlg sel aastal €100m+. Iga värskendamata süsteem ja kasutaja seade on turvanõrkus, mis suurendavad asutuse riske ning vähendavad usaldusväärsust. Meie eesmärk on kasutada meile pakutavaid vahendeid (RES ja SF) tagamaks tehnoloogiline ajakohastatus.
IT nõudluse keskne juhtimine. Meie kasutajad ei pruugi olla teadlikud, mida nende poolt esitatud pöördumine endaga kaasa toob. Kindlasti ei ole mõistlik, kui kogu nõudlus ilmneb vahetult enne eelarvestamise perioodi. Olen oma eelnevatel positsioonidel julgustanud kolleege varakult oma vajadused välja tooma. IT otsustab siis oma ressurssidele ja oskustele toetudes, kuidas neid vajadusi hallata ning millises mahus infot on tarvis otsuste tegemiseks. See eeldab IT analüütiku olemasolu, kes on suuteline suhtlema nii kasutajatega ja nende soovid/vajadused vormistama ühtsesse IT keelde kui ka arhitektidega ja lahenduskäigu kirjeldama. Koostöös keskse teenusepakkujaga saame luua turvalisi keskkondi (PaaS), kus ka vähese IT oskusega töötajad saavad oma töö tarbeks mikrolahendusi luua. Teeme seda aga nii, et andmed on turvatud, varundatud ja IT neist arengutest teadlik. Head näited on tuua RMK’st ja Tervisekassast, kus mittetundlike andmetega rakendused on viidud Microsoft PowerPlatform’ile hoides kokku kümneid tuhandeid eurosid ja kuude kaupa arendusaega. Lisaväärtuseks on lihtne jätkuarenduste tegemine.
Efektiivne suhtlus ja koostöö asutuse sees ja väliste partneritega – ratta (taas)leiutamine ei ole mõistlik, kui teistel on see juba olemas. Valime parimat võimalikku väärtust pakkuvad teenused ja teostaja – kõiki teenuseid ei pea ise osutama ning tulevikus peaks koostöö keskse teenusepakkujaga ainult kasvama.
Avalikud ja hübriidpilved. Pilveplatvormid on meiega ja võimaldavad meil turvaliselt ning kuluefektiivselt pakkuda teenuseid oma töötajatele ning klientidele. EITS võimaldab erinevalt ISKE’st pilveteenuste kasutuselevõtu ning 2024 algul eeldatavalt jõustuv pilvemäärus seab sellele raamid. Andmete turvalisuse ning pilveteenuste sobivuse hindamine lasub jätkuvalt andmete omanikul, kuid ka siin tuleb keskne teenusepakkuja pädeva asutusena appi.
Küberturbe riskide tuvastamine ja haldus. Küberrünnakud Eesti riigiasutuste vastu on viimasel 12 kuul jõudsalt kasvanud. Meie kohus on tagada oma andmete ja kasutajate turvalisus töökohal.
IT juhi fookuses on oma valdkonna efektiivne juhtimine ning teenuste toimimise tagamine. See toetub neljale sambale – inimeste arendamine, suhtekorraldus, efektiivne raha juhtimine ja ministeeriumi huvide eest seismine oma vastutusala raames. Harutan neid valdkondi pisut lahti:
Inimesed. Tehisintellekti (AI) areng viimasel kahel aastal on olnud muljetavaldav. Palju valdkondi, kus varem pidi palkama tippspetsialiste, on saanud endale täiendust AI ja masinõppe vallas. See ei tähenda inimeste töö kadumist, vaid osakaalude muutumist – inimene peab keskenduma masina treenimisele ning reeglite loomisele. Tootjate pingutused tähendavad aga seda, et suuresti tuleb valida juba loodud poliitikate vahelt ning rakendada neid, mis asutuse infoturbe poliitikat ellu viia aitavad. Inimesed peaksid saama rohkem aega, et oma teadmisi täiendada ja muutustele reageerida suutma. Palju tuge pakutakse meile juba täna parterite, nt. Microsofti poolt. Uudishimulik ja õppimisvõimeline töötaja tähendab keskses perspektiivis ka IT pöördumiste muutumist väärtusahelas kõrgemale. Muutuv IT roll eeldab inimesi, kes on suutelised kavandama tulevikku ning hoidma olemasolevaid süsteeme töös ja turvalisena. Juhi roll on leppida üksuste juhtidega kokku nende valdkondade arengusuunad ning leida vajalikud vahendid nende inimeste arendamiseks. Samuti toetada üksuste juhte värbamisel ja valikul ning nende endi arengul.
Suhtekorraldus. Seondud tihedalt esimese punktiga nii osakonna sees, kui majas ja väljaspool. Meil on hankijad, partnerid, kliendid ja teised üksused asutuse sees inimestega, kel on oma ootused ja eelarvamused. Juhi roll on tagada harmoonia oma meeskonnas ning toetada neid oma meeskondade juhtimisel. Samuti on tema hea seista väliste suhete hea toimimise eest.
Raha. Paar elementi, mis on vääramatud on kommertstarkvara hinnatõus, palgatõus ning arenduste ja halduskulude kasv. Tänase eelarve kohaselt rahastatakse enamusi arendusi RES’ist. Ootaksin kindlasti suuremat SF kasutust, kuni see võimalus on meil kasutada. Juhi roll on tagada IT nõudluse efektiivne juhtimine ning vajalikele ressurssidele toetuse leidmine juhtkonnas ja MKM’s.
Ministeeriumi huvid. See punkt seondub kolme eeltooduga. RIT’i, RIA jt. riigi IT majade ning väliste partneritega saame koostööd parandada ja koos veelgi paremat digiriiki luua. Juhi roll on leida võimalused pakutava ja ministeeriumi vajaduste ning ootuste vahel. Samuti otsustada, mida teha ise ja mida sisse osta.
One of the topics that keeps coming up in the social events I go to, is an effective IT strategy.
A short answer, given by a few friends and colleagues – if in doubt, look at organisation strategy and and align with this. You can always build on that as your IT capability matures and you take on more responsibilities. I’d argue it’s more important to start with a solid vision and mission statements for your IT organisation. Relevant strategies (architecture, development, demand, delivery, operations, CSI et al) can be built on those statements. Not to be forgotten that mostly the IT is enabling function. If it doesn’t deliver the basics well enough it becomes irrelevant – either the organisation neglect it and seek help elsewhere or go out of business.
Some of the best IT strategy examples I’ve seen are displayed on a single page. There the focus is on the following items:
core purpose of IT (kind of obvious but often lost in translation)
key capabilities and operating model (what IT does and doesn’t do)
core values (how the unit behaves)
These areas provide answers to basic questions – what IT is, why it exists and how IT operates. I’ve run workshops in the past with aim of defining the IT strategy. We’ve started with the three points above using familiar language to the organisation. As an example it could read:
“The purpose of organisation X IT department is to ensure the IT systems and services consumed by the organisation meet its needs by being designed with the user in mind, adequately provisioned, secure, available and resilient. The IT department does this by developing mix of in-house and external capabilities. We partner with subject matter experts in the field to develop and support key business applications, and integrate those via API interface with supply chain and customer facing resources.”
Or something similar that is relevant to your case.
What makes a suitable operating model for your organisation?
It is really down to you to define. Whilst the statement may seem blunt you shouldn’t try to emulate your competitors or other types of organisation you are not.
IT leadership need to understand the mission of the organisation theirs is key part of and become one with it. Not just align, but be integral part of. It helps to write down the purpose of an IT organisation / department / team and ensure everyone (at least in it and wider SLT) buy into it. The purpose stems from what the parent organisation needs IT for and at what level.
IT vision could read as “IT is to ensure company X will reach market domination within 5 years. This will be achieved by continuously investing into robust products and services that form the backbone for the company. IT aspire to become the partner of choice for the organisation when it comes to [your strengths] enterprise architecture [cloud platforms, integration of data, reporting], business processes [improvement, automation] and … We do this by understanding the business challenges and aspirations, and partnering with the right organisations to deliver desired outcomes.”
So the operating model need to reflect the capabilities parent company need IT to provide. It does help to have the IT organisation development mapped out. Regardless of aspirations being honest with oneself is a must here. We may choose to believe the business views IT as trusted partner or peer, but its unlikely to be that if we fail to provide basic services and lack processes around demand, commercial and change management. Hiding behind failing service provider will only reduce the value of IT in the eyes of those approving investments.
Depending on the size and type of the organisation there are some key areas to keep in house and to outsource.
Once you have defined the desired future state you need to work out how to get there. That’s about developing delivery strategy.
A friend penned a post on millennial workforce and currently prevalent business culture asking a number of questions at each section. I thought about it and felt need to chip in. As I do.
First things first. I think the behaviours Nicolas describes in his post do not only apply to the Generation Y and Z, they are seen to take root across the business landscape. Not everyone is directly contributing to digital economy yet many are affected by the changes it has brought about. Take any traditional trade. A brief look at its state today shows how much has changed within past 15 years. Supply chain has become global, primary distribution channel is online, delivery often by gig-economy workers who get paid per delivery and are not seen taking pride in their work as the quality suffers. Many early retirees have returned after realising the type of lifestyle their pension actually supports. Many are freelancing – not out of choice but necessity. Often they have no option but to as the organisations they work with (not for!) have their business models dependent on reduced staff overheads. Add what we sued to call “cost of doing the business” and you have no business. In some areas its global trade, in others high business rates. We have moved from stable, permanent positions to short term contracts. Many of us who have spent around 20 years working have changed their jobs three times at least, some even more. Even those of us on permanent positions don’t tend to stay with the organisations for more than three years on average. Careers built merely on longevity are out, sharp minds and clear objectives in. Or at least should be so. We are likely to see inequality in workplace for some time until the Big Reset comes. And it will come, either in form of Universal Income or nationalisation of (by then still traditional) industries.
I personally favour UI route. When set at 70% minimum wage it will enable people to just get by (on council property – hey, different topic!) and top up their earnings by freelancing and working with the organisations of their choosing. Some argue that it should be minimum wage, though latter camp will have hard time standardising this even in EU context (€1400 as minimum in France is above average in Estonia). Money will be digitised and all income over certain threshold is taxed as now, hopefully reducing incentive and options for fraud. Getting rid of physical money will also reduce the asset ownership cost to central bank and thus should again leave more to fund UI. Quartz @ Work has a very timely piece on full employment and fulfillment. Full employment is felt as cornerstone for Western society and people find usually hard explaining the gaps in their careers. Instead being out of work should choice when people feel they need a break followed by successful return to work provided people have necessary skills and attitude to perform as expected.
The themes Nicolas writes about are well covered by many – empowerment, ownership, flexibility, purpose, opportunities and new types of work. Let’s look at each once more then.
Many, not just younger expect to be empowered to make and have ownership about their decision making and outcomes. They expect to be treated as equals. Not equally capable and experienced but to get equal opportunities. Many have argued, especially about apprenticeships schemes that it’s all about them and not us, the employers. But this statement is untrue. The young, when motivated and allowed to make small mistakes, learn from them and not be punished will pay back with energy they have and willingness to throw all they have to complete the project on time. They are willing to shed that shy self in order to achieve the deadlines. Many more seasoned colleagues would try to delegate the task to someone else and stay in mediocristan. Working with apprentices 18 years ago in my own small IT business and recently with fast -streamers has shown me time and again how much value these young people can deliver with right level of coaching, delegation and independence. But wait, this applies equally to more seasoned employees as well. To ensure they don’t actively avoid decision making and taking ownership however, the organisation need to have reached necessary level of maturity. Not quite teal level, but micro-management must be out and trust in.
Flexibility in workplace is nothing new. Also not new is the notion of flexibility when it comes to choosing the place of work. I have a few friends who have been working from home study since mid-nineties. Fine, their jobs enabled this (editor, consultant, marketer, software programmer) but were never seen as revolutionary, rather as their choice. What is new is not just where but when we choose to work. Dan Pink spoke in recent RSA event about timing. I can attest to his conclusion of timing the work. There are generally three stages – peak, through and recovery. In my case its a bit like this:
I’m usually switched on in the mornings and can stay focused for long periods of time until noon. Sometimes longer. This is the time to work on analysis and produce written content. Then comes the slump where I’n not the sharpest pencil in the box. That’s the good time for admin. Neither of the periods is suitable for meetings. When we are in focus mode, we find hard to accept others’ ideas. During the through we are simply unable to absorb any information. This is worst time for any meetings or workshops. Hence I try to schedule all my meetings (virtual or in person) either right before lunch or after 15:00. When the recovery kicks in, we are all more agreeable. This is flexibility we should grant to all our colleagues. We should deploy tools that allow people to submit the best time they are ready to collaborate in, and avoid any meetings outside this space.
You could say that people fall into two categories. First is static, second dynamic. The second crowd are after opportunities to prove how good they are. Get some testosterone going, tick that thing off the list and get dopamine kick. Feels good, right? It tends to be the younger crowd who are looking for ways to either gain some new knowledge or participate in that new venture. Perhaps it pays off. And if it didn’t, no biggie. Next time they’ll try again. What we need to encourage is looking for opportunities in the organisation. These may be incremental improvements to the process or product that drive our businessesuu forward. It’s very rare when a groundbreaking change is introduced and effectively managed to production. Th rest of the time everything is in beta. And changing. We need to create culture where risk is seen as both threat and opportunity, not just first.
Take all of these and… nothing works when people don’t have purpose in their working lives. Purpose and meaning is much coveted topic for the jobs over the threshold where increase in pay will have no effect on quality of output.
The types of work that existed in the fringe have become mainstream in Western economies and those previously taken for granted have disappeared. Manufacturing is a good example. Working for Saint-Gobain in late 90’s and first part of 21st century I saw automation and streamlining of supply chains in order to reduce the cost of product. Robotics found its way into assembly previously required highly skilled workforce performing tasks demanding precision. Need to reduce waste and not optimise but maximise output at highest level of quality will see new plants employing a handful of highly skilled operators work of many machines.
We used to cook at home and only occasionally order takeaway food. Especially in urban environment this has become mainstream – people value their time and are willing to pay for food and delivery. The delivery has often been outsourced to likes of Deliveroo and fulfilled by men on bikes searching their way through maze. They are often as lost as Über drivers. Everyone as taxi driver on their spare time? That’s not really valuing ones time, it may be seen as the only option to earn enough to live in a modern metropolis. Are these jobs going to be here in 10 years? Probably not, technology will develop along with legal framework to automate these jobs.
What will the future of work look like for us in the knowledge work? We’ll have many jobs over our working lives, quite possibly will be looking for work every few years and working for and with many different organisations. This raises need to be adaptable to the change. I thought learning enough but not mastering a single skill was not sufficient. Shallow generalist over highly skilled specialist? A recent Medium post by Michael Simmons nicely builds the case for polymath as probably best placed to survive in the unknown future. It’s not just transferable skills we need. We need to be able to synthesise useful elements from different disciplines to meet the future challenges.
The journey of personal mobile devices started in early 1980’s with first Motorola, Nokia and Ericsson phones. I would recommend looking up those funky handsets. They teach us a lot about ergonomics and evolution of microprocessors.
Basically, this is what our journey looks like:
Motorola DynaTak was first truly portable mobile phone for civilian use. It’s fortunately history by now and you may read more about it here.
Latest Android phone comes from Google, weighs no more than any other handset we have seen in past five years and replaces your computer. Other major OS’s are Apple iOS and Microsoft Windows 10 Mobile (somewhat dead in the water now). We had Blackberry OS, but that’s pretty much gone – all new handsets are running Android. We also had Symbian, but that’s completely irrelevant these days. Nokia is trying to reinvent its mobile business, though they seem to side more with Android than MeeGo. Although Nokia C1 is more of an urban legend – many rumours but no sighting yet…
But none of it would have not happened without underlying infrastructure. Taking the risk of investing very large sums of money into covering has paid off and benefits manufacturers, service providers and consumers alike.
Signal coverage in the UK is relatively good with most areas having voice signal. 4G is confined to mostly urban areas but is growing faster than 3G.
4G standard has many advantages over its predecessors – data speed and improved voice quality. 4G connectivity has also helped many mobile virtual network operator (MVNO) companies to enter the market. There are ones that piggyback to major carriers for both voice and data or just data. In second option user would need to install and use an app to make and receive calls and send text messages. This option bypasses phone OS native apps and offers a few advantages to the provider – provide additional services and sell in-app advertising to keep package cost low.
Nokia, Ericsson and others have been hard at work developing 5G communications standard. Don’t expect that anytime soon near you as devices that support the standard are still not in personal but rather in machine-to-machine (M2M) and Internet-of-Things (IoT) market.
Where are we now?
It’s been an interesting journey people in most countries have been. In many places it has been led by technology rather than policy. And technology providers have been pushing their own (often proprietary) standards, which innovative at the beginning have caused countless hours of extra work to make it functional and integrate with other systems.
Most developed and developing countries have passed mobile phone revolution. Smartphones, however not taken over the mobile device market from feature phones yet, are on path to get there.
I don’t fully buy into Statista’s perception that feature phone numbers are on permanent raise. It’s likely though that what’s classified as a smartphone today won’t meet that designation in 2020. There’s another view that seems more likely, and that was view in early 2015.
My personal view is that feature phone numbers start dropping in next 24 months as African and Asian countries keep growing. Once a human being has had a taste of a smartphone they’d rather give up other goods and services than this. And why? Technically you have a small computer in your hand that puts world’s knowledge at your fingertips.
It’s not surprising that Android OS dominates the market. You can see interesting correlation between Android OS and Apple iOS. Every time Apple launches something new, there’s a surge and corresponding dip in shipments of Android devices. Yet it plateaus off very quickly and even takes a tumble after initial craze has faded. The gap between the market leader and second option is too vast to close at ease.
This dominance in turn gives Google enormous leverage over vast amounts of users. They are happy to share some insight with device manufacturers but all visible and hidden services of its client OS feeding information back to the company.
New gadgets, anyone?
Near Field Communication (NFC) has been on and off tech news. There are some services being adapted en masse now. Contactless bank cards? Check. Using your latest iPhone (or rather old Android and/or Blackberry) as bank card? Check. Having small contactless bank card companion chip (about square inch in size) attached to your old phone. Like this:
That’s now norm. But where to take this contactless future?
John Mclear was trying to get his NFC Ring off the ground using Kickstarter back in 2013. And what a marvelous idea it was! One ring, two functions – public and private. Public is the outer side of the ring, suitable for contactless payments and such. Inner side of the ring would be for authentication – as in handshake. No puns intended, though you could see two changing digital ID’s during physical handshake.
Then there are printable digital ID’s. These are the ones that can be tattooed or printed on the skin akin to 3D printing. Some films have featured characters with bar code tattooed to their bodies. That’s cool, but… what if your ID changes? Deliberately or not, but change is needed. What then? Well, you’d have to remove and replace old one. Rather painful exercise, I guess. Reprogramming embedded or printed NFC chip is not. And works perfectly so long as only certain authorities can do it. I’d rather travel without physical passport than with one.
Another example of this use – manufactured human spare parts. Ahem, organs and bones, that is. When I get into car accident and my leg gets crushed so badly that I need a new bone (provided that tissue is still usable) it should be crafted for me using suitable material and 3D printer. The cost of prosthesis manufacturing where and when it’s needed would go down radically and the only concern is how body reacts to it. Though manufacturing process would take into account personal characteristics minimising or removing potential negative effect completely.
What should we consider?
With masses of data being sensed, collected, analysed and presented we need to be aware of what we give away to improve our lives. It would be nice to provide 20% of input and reap 80% benefits but 80/20 rule doesn’t really work here. There are really two reasons for it.
First, most smartphone users have dozens of apps on their devices. We are actually really dependent on our devices. Where average amount has been limited to their niche time spent on using the mobile apps has doubled over five years.Those apps as mentioned in previous part collect behavioural information and pass it back to the service providers. he more time we spend on our devices the fuller picture app / service providers have about us.
Secondly, AI and analytics algorithms are improving but are not smart enough yet to provide the service at the cost of contact acquisition. It won’t take too long considering Google AI improvements in navigating London Underground. I can see these services powering the user analytics and being integrated into personal assistants.
What lies ahead?
What should we expect from the connected future? Is it good or bad, and should we be worried or happy?
There’s been an explosion of apps and services designed for smartphone users. Many are duplicating each other, many are using open data, some mash together open and personal data, some work with data providers and others allow user to enhance their experience by linking together services that make up our digital footprint.
We tend to trust our service providers. Or we don’t but compromise as a means of using a particular service. Take Google, Microsoft or Facebook as identity providers. Now add everything these companies know about you – that’s often rather a substantial digital footprint and you need to know what do with it.
There are always privacy concerns related “free” services. Data misuse is a big deal and major organisations have taken steps to deal wit it. Though it manifests itself a bit like this:
The consumer needs to be aware of what information they give away about themselves, who they trust and what benefits they receive in return.
Google wants to be my personal assistant. So does Microsoft with Cortana, Apple with Siri and Amazon with Echo. And plethora of other services that are always listening using the gadgets we have amassed in our homes.
So with that in mind, how can I benefit from their knowledge about me?
Consider a scenario when your city has been kitted out with connected interactive displays, let’s call them smart screen. Those smart screens are equipped with sensors and connected to each other. The devices we carry are technically beacons which also serve as ID providers. My smart watch is associated with one of my digital ID’s. The smart screen senses me approaching and gives me useful snippet.
Or if I’m rushing to catch my train and smart screen tells me there’s a delay with my train and I’ve got to fill 15 minutes somehow.
Useful? Frightening? Amazing? Whatever we feel about these services penetrating our everyday lives they are here to stay for the foreseeable future. And they are not going to be less smart. They will reduce complexity at the point of delivery making it easier for the users to go about their daily lives and adding useful layer of information.
Should we be afraid of future or jump up and down of excitement when today’s tech news highlights become part of everyday life next week?
I think we should embrace the technology, work with it and reap benefits. When parts of it become too intrusive, we need to make conscious decision to stop using those parts. Not becoming Luddites but understand what is good and what is bad for us.
There’s a transformation going on in many organisations. The focus is less on conventional wisdom and more on what’s actually needed to achieve targets, objectives or need.
New initiatives should always be driven by need. User needs are driven by aspirations, desires and previous experience in situations people find themselves in. In a well functioning organisation needs should stem from personal or team objectives that align with organisational purpose. Overall flow should look like one below.
Still I’m regularly asked “Do you know a tool we could use to do this?”. Default response is to “quantify and define your business problem, and state it clearly”. This is the business analysis phase where business needs to understand their problem, or what they believe is a problem. This is also a point where people often need help form an outsider who is not aware of all the intricacies of the situation or need and thus are not dismissing various options.
Many seasoned professionals tend to stick to tools or vendors they’ve used in the past rather than looking out to market for the most appropriate tool or service that meets their needs. This, however, expects needs and drivers to be identified, listed and weighted against each other, and existing tools – again, what’s your business problem? Is there perhaps a tool in the organisation that will already met this need? Will it meet 75-80% of your must-have’s and the rest can be done using something else? does this tool need to meet 100% of your need? Are you clear on your need?
Concentrating on user needs gives organisation ability to understand its current capabilities and will potentially highlight training needs.
Focusing on existing tooling limits the choice before it’s clear what drives the user need.
How often do we ask ourselves or others – why are we here? What’s the purpose of this organisation, working group or project? Do we understand this or were we asked to be part of it? Have we worked out the problem(s) we are looking to deal with? Do we have terms of reference agreed?
Purpose is a tricky subject and many I speak to are mildly confused about it. How my output contributes to the cause of this organisation?
I think these are fundamental questions people who make up an organisation need to ask themselves. This sometimes happens naturally, especially during the economic downturns or when people feel stuck. In an ideal situation this should take place during the good times – then this is something to hang onto when things go south.
Processes and visibility
When organisations mature business processes are being drawn up to govern the flow of work. It’s important that those processes are reusable by different parts of the organisation, succinct and easy to understand. Often (if not always) it’s also useful to visualise the business process. People process information differently and pictorials help a lot. However it doesn’t help to discover process works against everyone involved.
In mature organisations the process flows often get muddled and people don’t really see at which stage things are. Is it with me or some other party? Who is responsible for this piece of work? Who needs to do what to progress it to the next level?
This is where business process management comes in. If you are interested to find out how to align your initiatives organisational purpose, get in touch.
I stumbled upon an article on a new trend in he US to scan the streets with cars equipped with thermal cameras. It’s all in the interest of public and energy providers to tell the homeowners how inefficient their house is and how much or little it leaks.
Reading this raise two questions for me.
1. How accurate is the measurement as the buildings are scanned mainly from the front. Will the rest be rough guesstimate or scientifically calculated accurate u figure?
2. How will the results be used? Will it be to advise homeowners of potential savings they may be making? Or will the aim be more sinister – to sell the information to insulation installers and impose fines on those who won’t budge?
On the surface nothing seems to be wrong with this initiative. However it’s likely to face resistance from the privacy advocates. As this comes as extra cost to the energy suppliers, someone has to pay for this. My money is on customer.