AI is developing all the time. Here are some picks from several articles what is expected to happen in AI and around it in 2025. Here are picks from various articles, the texts are picks from the article edited and in some cases translated for clarity.
AI in 2025: Five Defining Themes
https://news.sap.com/2025/01/ai-in-2025-defining-themes/
Artificial intelligence (AI) is accelerating at an astonishing pace, quickly moving from emerging technologies to impacting how businesses run. From building AI agents to interacting with technology in ways that feel more like a natural conversation, AI technologies are poised to transform how we work.
But what exactly lies ahead?
1. Agentic AI: Goodbye Agent Washing, Welcome Multi-Agent Systems
AI agents are currently in their infancy. While many software vendors are releasing and labeling the first “AI agents” based on simple conversational document search, advanced AI agents that will be able to plan, reason, use tools, collaborate with humans and other agents, and iteratively reflect on progress until they achieve their objective are on the horizon. The year 2025 will see them rapidly evolve and act more autonomously. More specifically, 2025 will see AI agents deployed more readily “under the hood,” driving complex agentic workflows.
In short, AI will handle mundane, high-volume tasks while the value of human judgement, creativity, and quality outcomes will increase.
2. Models: No Context, No Value
Large language models (LLMs) will continue to become a commodity for vanilla generative AI tasks, a trend that has already started. LLMs are drawing on an increasingly tapped pool of public data scraped from the internet. This will only worsen, and companies must learn to adapt their models to unique, content-rich data sources.
We will also see a greater variety of foundation models that fulfill different purposes. Take, for example, physics-informed neural networks (PINNs), which generate outcomes based on predictions grounded in physical reality or robotics. PINNs are set to gain more importance in the job market because they will enable autonomous robots to navigate and execute tasks in the real world.
Models will increasingly become more multimodal, meaning an AI system can process information from various input types.
3. Adoption: From Buzz to Business
While 2024 was all about introducing AI use cases and their value for organizations and individuals alike, 2025 will see the industry’s unprecedented adoption of AI specifically for businesses. More people will understand when and how to use AI, and the technology will mature to the point where it can deal with critical business issues such as managing multi-national complexities. Many companies will also gain practical experience working for the first time through issues like AI-specific legal and data privacy terms (compared to when companies started moving to the cloud 10 years ago), building the foundation for applying the technology to business processes.
4. User Experience: AI Is Becoming the New UI
AI’s next frontier is seamlessly unifying people, data, and processes to amplify business outcomes. In 2025, we will see increased adoption of AI across the workforce as people discover the benefits of humans plus AI.
This means disrupting the classical user experience from system-led interactions to intent-based, people-led conversations with AI acting in the background. AI copilots will become the new UI for engaging with a system, making software more accessible and easier for people. AI won’t be limited to one app; it might even replace them one day. With AI, frontend, backend, browser, and apps are blurring. This is like giving your AI “arms, legs, and eyes.”
5. Regulation: Innovate, Then Regulate
It’s fair to say that governments worldwide are struggling to keep pace with the rapid advancements in AI technology and to develop meaningful regulatory frameworks that set appropriate guardrails for AI without compromising innovation.
12 AI predictions for 2025
This year we’ve seen AI move from pilots into production use cases. In 2025, they’ll expand into fully-scaled, enterprise-wide deployments.
https://www.cio.com/article/3630070/12-ai-predictions-for-2025.html
This year we’ve seen AI move from pilots into production use cases. In 2025, they’ll expand into fully-scaled, enterprise-wide deployments.
1. Small language models and edge computing
Most of the attention this year and last has been on the big language models — specifically on ChatGPT in its various permutations, as well as competitors like Anthropic’s Claude and Meta’s Llama models. But for many business use cases, LLMs are overkill and are too expensive, and too slow, for practical use.
“Looking ahead to 2025, I expect small language models, specifically custom models, to become a more common solution for many businesses,”
2. AI will approach human reasoning ability
In mid-September, OpenAI released a new series of models that thinks through problems much like a person would, it claims. The company says it can achieve PhD-level performance in challenging benchmark tests in physics, chemistry, and biology. For example, the previous best model, GPT-4o, could only solve 13% of the problems on the International Mathematics Olympiad, while the new reasoning model solved 83%.
If AI can reason better, then it will make it possible for AI agents to understand our intent, translate that into a series of steps, and do things on our behalf, says Gartner analyst Arun Chandrasekaran. “Reasoning also helps us use AI as more of a decision support system,”
3. Massive growth in proven use cases
This year, we’ve seen some use cases proven to have ROI, says Monteiro. In 2025, those use cases will see massive adoption, especially if the AI technology is integrated into the software platforms that companies are already using, making it very simple to adopt.
“The fields of customer service, marketing, and customer development are going to see massive adoption,”
4. The evolution of agile development
The agile manifesto was released in 2001 and, since then, the development philosophy has steadily gained over the previous waterfall style of software development.
“For the last 15 years or so, it’s been the de-facto standard for how modern software development works,”
5. Increased regulation
At the end of September, California governor Gavin Newsom signed a law requiring gen AI developers to disclose the data they used to train their systems, which applies to developers who make gen AI systems publicly available to Californians. Developers must comply by the start of 2026.
There are also regulations about the use of deep fakes, facial recognition, and more. The most comprehensive law, the EU’s AI Act, which went into effect last summer, is also something that companies will have to comply with starting in mid-2026, so, again, 2025 is the year when they will need to get ready.
6. AI will become accessible and ubiquitous
With gen AI, people are still at the stage of trying to figure out what gen AI is, how it works, and how to use it.
“There’s going to be a lot less of that,” he says. But gen AI will become ubiquitous and seamlessly woven into workflows, the way the internet is today.
7. Agents will begin replacing services
Software has evolved from big, monolithic systems running on mainframes, to desktop apps, to distributed, service-based architectures, web applications, and mobile apps. Now, it will evolve again, says Malhotra. “Agents are the next phase,” he says. Agents can be more loosely coupled than services, making these architectures more flexible, resilient and smart. And that will bring with it a completely new stack of tools and development processes.
8. The rise of agentic assistants
In addition to agents replacing software components, we’ll also see the rise of agentic assistants, adds Malhotra. Take for example that task of keeping up with regulations.
Today, consultants get continuing education to stay abreast of new laws, or reach out to colleagues who are already experts in them. It takes time for the new knowledge to disseminate and be fully absorbed by employees.
“But an AI agent can be instantly updated to ensure that all our work is compliant with the new laws,” says Malhotra. “This isn’t science fiction.”
9. Multi-agent systems
Sure, AI agents are interesting. But things are going to get really interesting when agents start talking to each other, says Babak Hodjat, CTO of AI at Cognizant. It won’t happen overnight, of course, and companies will need to be careful that these agentic systems don’t go off the rails.
Companies such as Sailes and Salesforce are already developing multi-agent workflows.
10. Multi-modal AI
Humans and the companies we build are multi-modal. We read and write text, we speak and listen, we see and we draw. And we do all these things through time, so we understand that some things come before other things. Today’s AI models are, for the most part, fragmentary. One can create images, another can only handle text, and some recent ones can understand or produce video.
11. Multi-model routing
Not to be confused with multi-modal AI, multi-modal routing is when companies use more than one LLM to power their gen AI applications. Different AI models are better at different things, and some are cheaper than others, or have lower latency. And then there’s the matter of having all your eggs in one basket.
“A number of CIOs I’ve spoken with recently are thinking about the old ERP days of vendor lock,” says Brett Barton, global AI practice leader at Unisys. “And it’s top of mind for many as they look at their application portfolio, specifically as it relates to cloud and AI capabilities.”
Diversifying away from using just a single model for all use cases means a company is less dependent on any one provider and can be more flexible as circumstances change.
12. Mass customization of enterprise software
Today, only the largest companies, with the deepest pockets, get to have custom software developed specifically for them. It’s just not economically feasible to build large systems for small use cases.
“Right now, people are all using the same version of Teams or Slack or what have you,” says Ernst & Young’s Malhotra. “Microsoft can’t make a custom version just for me.” But once AI begins to accelerate the speed of software development while reducing costs, it starts to become much more feasible.
9 IT resolutions for 2025
https://www.cio.com/article/3629833/9-it-resolutions-for-2025.html
1. Innovate
“We’re embracing innovation,”
2. Double down on harnessing the power of AI
Not surprisingly, getting more out of AI is top of mind for many CIOs.
“I am excited about the potential of generative AI, particularly in the security space,”
3. And ensure effective and secure AI rollouts
“AI is everywhere, and while its benefits are extensive, implementing it effectively across a corporation presents challenges. Balancing the rollout with proper training, adoption, and careful measurement of costs and benefits is essential, particularly while securing company assets in tandem,”
4. Focus on responsible AI
The possibilities of AI grow by the day — but so do the risks.
“My resolution is to mature in our execution of responsible AI,”
“AI is the new gold and in order to truly maximize it’s potential, we must first have the proper guardrails in place. Taking a human-first approach to AI will help ensure our state can maintain ethics while taking advantage of the new AI innovations.”
5. Deliver value from generative AI
As organizations move from experimenting and testing generative AI use cases, they’re looking for gen AI to deliver real business value.
“As we go into 2025, we’ll continue to see the evolution of gen AI. But it’s no longer about just standing it up. It’s more about optimizing and maximizing the value we’re getting out of gen AI,”
6. Empower global talent
Although harnessing AI is a top objective for Morgan Stanley’s Wetmur, she says she’s equally committed to harnessing the power of people.
7. Create a wholistic learning culture
Wetmur has another talent-related objective: to create a learning culture — not just in her own department but across all divisions.
8. Deliver better digital experiences
Deltek’s Cilsick has her sights set on improving her company’s digital employee experience, believing that a better DEX will yield benefits in multiple ways.
Cilsick says she first wants to bring in new technologies and automation to “make things as easy as possible,” mirroring the digital experiences most workers have when using consumer technologies.
“It’s really about leveraging tech to make sure [employees] are more efficient and productive,”
“In 2025 my primary focus as CIO will be on transforming operational efficiency, maximizing business productivity, and enhancing employee experiences,”
9. Position the company for long-term success
Lieberman wants to look beyond 2025, saying another resolution for the year is “to develop a longer-term view of our technology roadmap so that we can strategically decide where to invest our resources.”
“My resolutions for 2025 reflect the evolving needs of our organization, the opportunities presented by AI and emerging technologies, and the necessity to balance innovation with operational efficiency,”
Lieberman aims to develop AI capabilities to automate routine tasks.
“Bots will handle common inquiries ranging from sales account summaries to HR benefits, reducing response times and freeing up resources for strategic initiatives,”
Not just hype — here are real-world use cases for AI agents
https://venturebeat.com/ai/not-just-hype-here-are-real-world-use-cases-for-ai-agents/
Just seven or eight months ago, when a customer called in to or emailed Baca Systems with a service question, a human agent handling the query would begin searching for similar cases in the system and analyzing technical documents.
This process would take roughly five to seven minutes; then the agent could offer the “first meaningful response” and finally begin troubleshooting.
But now, with AI agents powered by Salesforce, that time has been shortened to as few as five to 10 seconds.
Now, instead of having to sift through databases for previous customer calls and similar cases, human reps can ask the AI agent to find the relevant information. The AI runs in the background and allows humans to respond right away, Russo noted.
AI can serve as a sales development representative (SDR) to send out general inquires and emails, have a back-and-forth dialogue, then pass the prospect to a member of the sales team, Russo explained.
But once the company implements Salesforce’s Agentforce, a customer needing to modify an order will be able to communicate their needs with AI in natural language, and the AI agent will automatically make adjustments. When more complex issues come up — such as a reconfiguration of an order or an all-out venue change — the AI agent will quickly push the matter up to a human rep.
Open Source in 2025: Strap In, Disruption Straight Ahead
Look for new tensions to arise in the New Year over licensing, the open source AI definition, security and compliance, and how to pay volunteer maintainers.
https://thenewstack.io/open-source-in-2025-strap-in-disruption-straight-ahead/
The trend of widely used open source software moving to more restrictive licensing isn’t new.
In addition to the demands of late-stage capitalism and impatient investors in companies built on open source tools, other outside factors are pressuring the open source world. There’s the promise/threat of generative AI, for instance. Or the shifting geopolitical landscape, which brings new security concerns and governance regulations.
What’s ahead for open source in 2025?
More Consolidation, More Licensing Changes
The Open Source AI Debate: Just Getting Started
Security and Compliance Concerns Will Rise
Paying Maintainers: More Cash, Creativity Needed
Kyberturvallisuuden ja tekoälyn tärkeimmät trendit 2025
https://www.uusiteknologia.fi/2024/11/20/kyberturvallisuuden-ja-tekoalyn-tarkeimmat-trendit-2025/
1. Cyber infrastructure will be centered on a single, unified security platform
2. Big data will give an edge against new entrants
3. AI’s integrated role in 2025 means building trust, governance engagement, and a new kind of leadership
4. Businesses will adopt secure enterprise browsers more widely
5. AI’s energy implications will be more widely recognized in 2025
6. Quantum realities will become clearer in 2025
7. Security and marketing leaders will work more closely together
Presentation: For 2025, ‘AI eats the world’.
https://www.ben-evans.com/presentations
Just like other technologies that have gone before, such as cloud and cybersecurity automation, right now AI lacks maturity.
https://www.securityweek.com/ai-implementing-the-right-technology-for-the-right-use-case/
If 2023 and 2024 were the years of exploration, hype and excitement around AI, 2025 (and 2026) will be the year(s) that organizations start to focus on specific use cases for the most productive implementations of AI and, more importantly, to understand how to implement guardrails and governance so that it is viewed as less of a risk by security teams and more of a benefit to the organization.
Businesses are developing applications that add Large Language Model (LLM) capabilities to provide superior functionality and advanced personalization
Employees are using third party GenAI tools for research and productivity purposes
Developers are leveraging AI-powered code assistants to code faster and meet challenging production deadlines
Companies are building their own LLMs for internal use cases and commercial purposes.
AI is still maturing
However, just like other technologies that have gone before, such as cloud and cybersecurity automation, right now AI lacks maturity. Right now, we very much see AI in this “peak of inflated expectations” phase and predict that it will dip into the “trough of disillusionment”, where organizations realize that it is not the silver bullet they thought it would be. In fact, there are already signs of cynicism as decision-makers are bombarded with marketing messages from vendors and struggle to discern what is a genuine use case and what is not relevant for their organization.
There is also regulation that will come into force, such as the EU AI Act, which is a comprehensive legal framework that sets out rules for the development and use of AI.
AI certainly won’t solve every problem, and it should be used like automation, as part of a collaborative mix of people, process and technology. You simply can’t replace human intuition with AI, and many new AI regulations stipulate that human oversight is maintained.
7 Splunk Predictions for 2025
https://www.splunk.com/en_us/form/future-predictions.html
AI: Projects must prove their worth to anxious boards or risk defunding, and LLMs will go small to reduce operating costs and environmental impact.
OpenAI, Google and Anthropic Are Struggling to Build More Advanced AI
Three of the leading artificial intelligence companies are seeing diminishing returns from their costly efforts to develop newer models.
https://www.bloomberg.com/news/articles/2024-11-13/openai-google-and-anthropic-are-struggling-to-build-more-advanced-ai
Sources: OpenAI, Google, and Anthropic are all seeing diminishing returns from costly efforts to build new AI models; a new Gemini model misses internal targets
It Costs So Much to Run ChatGPT That OpenAI Is Losing Money on $200 ChatGPT Pro Subscriptions
https://futurism.com/the-byte/openai-chatgpt-pro-subscription-losing-money?fbclid=IwY2xjawH8epVleHRuA2FlbQIxMQABHeggEpKe8ZQfjtPRC0f2pOI7A3z9LFtFon8lVG2VAbj178dkxSQbX_2CJQ_aem_N_ll3ETcuQ4OTRrShHqNGg
In a post on X-formerly-Twitter, CEO Sam Altman admitted an “insane” fact: that the company is “currently losing money” on ChatGPT Pro subscriptions, which run $200 per month and give users access to its suite of products including its o1 “reasoning” model.
“People use it much more than we expected,” the cofounder wrote, later adding in response to another user that he “personally chose the price and thought we would make some money.”
Though Altman didn’t explicitly say why OpenAI is losing money on these premium subscriptions, the issue almost certainly comes down to the enormous expense of running AI infrastructure: the massive and increasing amounts of electricity needed to power the facilities that power AI, not to mention the cost of building and maintaining those data centers. Nowadays, a single query on the company’s most advanced models can cost a staggering $1,000.
Tekoäly edellyttää yhä nopeampia verkkoja
https://etn.fi/index.php/opinion/16974-tekoaely-edellyttaeae-yhae-nopeampia-verkkoja
A resilient digital infrastructure is critical to effectively harnessing telecommunications networks for AI innovations and cloud-based services. The increasing demand for data-rich applications related to AI requires a telecommunications network that can handle large amounts of data with low latency, writes Carl Hansson, Partner Solutions Manager at Orange Business.
AI’s Slowdown Is Everyone Else’s Opportunity
Businesses will benefit from some much-needed breathing space to figure out how to deliver that all-important return on investment.
https://www.bloomberg.com/opinion/articles/2024-11-20/ai-slowdown-is-everyone-else-s-opportunity
Näin sirumarkkinoilla käy ensi vuonna
https://etn.fi/index.php/13-news/16984-naein-sirumarkkinoilla-kaey-ensi-vuonna
The growing demand for high-performance computing (HPC) for artificial intelligence and HPC computing continues to be strong, with the market set to grow by more than 15 percent in 2025, IDC estimates in its recent Worldwide Semiconductor Technology Supply Chain Intelligence report.
IDC predicts eight significant trends for the chip market by 2025.
1. AI growth accelerates
2. Asia-Pacific IC Design Heats Up
3. TSMC’s leadership position is strengthening
4. The expansion of advanced processes is accelerating.
5. Mature process market recovers
6. 2nm Technology Breakthrough
7. Restructuring the Packaging and Testing Market
8. Advanced packaging technologies on the rise
2024: The year when MCUs became AI-enabled
https://www-edn-com.translate.goog/2024-the-year-when-mcus-became-ai-enabled/?fbclid=IwZXh0bgNhZW0CMTEAAR1_fEakArfPtgGZfjd-NiPd_MLBiuHyp9qfiszczOENPGPg38wzl9KOLrQ_aem_rLmf2vF2kjDIFGWzRVZWKw&_x_tr_sl=en&_x_tr_tl=fi&_x_tr_hl=fi&_x_tr_pto=wapp
The AI party in the MCU space started in 2024, and in 2025, it is very likely that there will be more advancements in MCUs using lightweight AI models.
Adoption of AI acceleration features is a big step in the development of microcontrollers. The inclusion of AI features in microcontrollers started in 2024, and it is very likely that in 2025, their features and tools will develop further.
Just like other technologies that have gone before, such as cloud and cybersecurity automation, right now AI lacks maturity.
https://www.securityweek.com/ai-implementing-the-right-technology-for-the-right-use-case/
If 2023 and 2024 were the years of exploration, hype and excitement around AI, 2025 (and 2026) will be the year(s) that organizations start to focus on specific use cases for the most productive implementations of AI and, more importantly, to understand how to implement guardrails and governance so that it is viewed as less of a risk by security teams and more of a benefit to the organization.
Businesses are developing applications that add Large Language Model (LLM) capabilities to provide superior functionality and advanced personalization
Employees are using third party GenAI tools for research and productivity purposes
Developers are leveraging AI-powered code assistants to code faster and meet challenging production deadlines
Companies are building their own LLMs for internal use cases and commercial purposes.
AI is still maturing
AI Regulation Gets Serious in 2025 – Is Your Organization Ready?
While the challenges are significant, organizations have an opportunity to build scalable AI governance frameworks that ensure compliance while enabling responsible AI innovation.
https://www.securityweek.com/ai-regulation-gets-serious-in-2025-is-your-organization-ready/
Similar to the GDPR, the EU AI Act will take a phased approach to implementation. The first milestone arrives on February 2, 2025, when organizations operating in the EU must ensure that employees involved in AI use, deployment, or oversight possess adequate AI literacy. Thereafter from August 1 any new AI models based on GPAI standards must be fully compliant with the act. Also similar to GDPR is the threat of huge fines for non-compliance – EUR 35 million or 7 percent of worldwide annual turnover, whichever is higher.
While this requirement may appear manageable on the surface, many organizations are still in the early stages of defining and formalizing their AI usage policies.
Later phases of the EU AI Act, expected in late 2025 and into 2026, will introduce stricter requirements around prohibited and high-risk AI applications. For organizations, this will surface a significant governance challenge: maintaining visibility and control over AI assets.
Tracking the usage of standalone generative AI tools, such as ChatGPT or Claude, is relatively straightforward. However, the challenge intensifies when dealing with SaaS platforms that integrate AI functionalities on the backend. Analysts, including Gartner, refer to this as “embedded AI,” and its proliferation makes maintaining accurate AI asset inventories increasingly complex.
Where frameworks like the EU AI Act grow more complex is their focus on ‘high-risk’ use cases. Compliance will require organizations to move beyond merely identifying AI tools in use; they must also assess how these tools are used, what data is being shared, and what tasks the AI is performing. For instance, an employee using a generative AI tool to summarize sensitive internal documents introduces very different risks than someone using the same tool to draft marketing content.
For security and compliance leaders, the EU AI Act represents just one piece of a broader AI governance puzzle that will dominate 2025.
The next 12-18 months will require sustained focus and collaboration across security, compliance, and technology teams to stay ahead of these developments.
The Global Partnership on Artificial Intelligence (GPAI) is a multi-stakeholder initiative which aims to bridge the gap between theory and practice on AI by supporting cutting-edge research and applied activities on AI-related priorities.
https://gpai.ai/about/#:~:text=The%20Global%20Partnership%20on%20Artificial,activities%20on%20AI%2Drelated%20priorities.
1,005 Comments
Tomi Engdahl says:
Built to keep you in flow state
The first agentic IDE, and then some. The Windsurf Editor is where the work of developers and AI truly flow together, allowing for a coding experience that feels like literal magic.
https://codeium.com/windsurf
Flows – the way humans are meant to work with AI
Flows = Agents + Copilots
The Windsurf Editor is powered by an AI that can both collaborate with you like a Copilot and tackle complex tasks independently like an Agent. The AI is completely in sync with you, every step of the way.
Flows allow the dev and AI to operate on the same state at all times, creating a mind-meld experience beyond just an assistant.
Tomi Engdahl says:
Suomi on vahvoilla, kun kiinalainen Deepseek mullistaa tekoälykehityksen – luvassa voi olla iso kiihdytys talouskasvuun
https://yle.fi/a/74-20146144
Suomella on useiden lukujen valossa erityisen hyvät mahdollisuudet, kun sensaatioksi noussut Deepseek laittaa tekoälyn ja talouden uusiksi.
Kiinalainen tekoäly Deepseek aiheutti valtavan hälyn kuukausi sitten: tekoälyekspertit ällistyivät, pörsseistä haihtui satoja miljardeja ja ihmiset ryntäsivät puhelimiensa sovelluskauppoihin.
Deepseek onnistui kehittämään huipputekoälyn huomattavasti Amerikan jättejä pienemmillä resursseilla. Se murensi viime vuosien käsityksen, jonka mukaan yhdysvaltain teknologiajäteillä on tekoälyssä pitkä etumatka kaikkiin muihin.
Yhdysvaltain teknojäteille nämä olivat huonoja uutisia, mutta muille todella hyviä. Deepseekin innovaatiot nimittäin tasoittavat tekoälyn pelikenttää huomattavasti.
Sillä voi olla suuri vaikutus tuottavuus- ja talouskasvuun. Hyötyjiä? Kuluttajat, muut yhtiöt ja valtiot.
Useat numerot kertovat, että erityisen hyvät mahdollisuudet on Suomella.
Kiihdytys kasvuun?
Teknologiaoptimistit ovat pitkään julistaneet, että tekoäly kiihdyttää tuottavuus- ja talouskasvun aivan uuteen vauhtiin.
Viime vuosina tekoäly on ottanut suuria harppauksia ja se on jo todistetusti nostanut työntekijöiden tuottavuutta.
Hidasteena on kuitenkin ollut se, että tekoälyn kehitys on näyttänyt olevan lähes täysin Amerikan teknojättien käsissä.
Käsitys on ollut, että tekoälykehityksessä voi pärjätä vain jättimäisillä datakeskuksilla, joissa raksuttaa valtava määrä markkinoiden parhaimpia tietokonesiruja.
Tämän Deepseek näyttää muuttavan.
Kiinalaisyhtiö onnistui kehittämään tekoälynsä selvästi halvemmalla ja ilman suurta huippusirujen arsenaalia. Toiseksi sen käyttö kuluttaa paljon vähemmän laskentatehoa eli se on tehokkaampi ja halvempi ”ajattelija”.
Nämä mullistukset leviävät nopeasti muille tekoälykehittäjille, koska Deepseek julkaisi tekoälynsä suurelta osin avoimella lähdekoodilla.
Luvassa pitäisi siis olla kasvavaa tehokkuutta ja uusia tekoäly-yhtiöitä eli kilpailua. Yhdessä ne tarkoittavat halpenevia hintoja.
Jyrkkä ja vielä jyrkempi kasvu
Taloustieteen professori Otto Toivanen sanoo, että tekoäly on niin sanottu yleiskäyttöteknologia, kuten höyrykone ja internet aiemmin. Yleiskäyttöteknologiat kiihdyttävät kasvua, koska ne ovat laajakäyttöisiä ja niiden päälle rakentuu paljon uusia keksintöjä.
Tekoäly voi nopeuttaa kasvua karkeasti kahta reittiä.
Jos se automatisoi vaikkapa sopimusten laatimista, pienempi työntekijäjoukko saa aikaan saman tuloksen kuin suurempi aiemmin. Jäljellä olevien tuottavuus kasvaa, ja työntekijöitä vapautuu muihin tehtäviin. Vaikkakin suuren, tällainen kehitys tuo kasvuun kuitenkin vain kertaloikan.
Merkittävämpi vaikutus tulee siitä, että tekoäly vaikuttaa itse innovointiin. Esimerkiksi tekoälyllä varustettu tuotekehittäjä voi saada aikaan huimasti enemmän aikaan vaikkapa lääkekehityksessä. Se tarkoittaisi jatkossakin nousevaa tuottavuutta uusien innovaatioiden kautta.
Toivanen antaa itselleen läheisen esimerkin: tekoäly on jo nyt iso apu ohjelmoinnissa, jota taloustieteilijät tekevät analyysejä tehdessään.
– Se voi vapauttaa tutkijoiden ajankäyttöä siihen, mihin aikaa pitäisi käyttää eli ideointiin, jolloin heillä menee vähemmän aikaa rutiinitehtävien pyörittämisen.
Kuinka suurta kasvua tekoäly voisi tuoda?
Laboren johtaja, taloustieteen professori Mika Maliranta kertoo, että tekoälyn kokonaistaloudellisista vaikutuksista on ainakin kaksi vakavasti otettavaa tutkimusta.
Taloustieteen tähtiprofessori, viime vuoden Nobel-voittaja Daron Acemoğlu arvioi tutkimuksessaan, että tekoäly nostaisi tuottavuuskasvua lähitulevaisuudessa niukasti, vain muutamia prosentin kymmenyksiä vuodessa.
Toinen tähtiekonomisti Philippe Aghion taas odottaa tekoälyltä huomattavasti suurempaa vaikutusta, jopa prosenttiyksikön kasvua tuottavuuteen vuositasolla.
– Se alkaisi olla suuruusluokaltaan sellainen, mikä tämä viestintäteknologinen murros oli Yhdysvalloissa vuosituhannen vaihteessa. Eli käytännössä internetin, sähköpostin ja kännyköiden laaja käyttöönotto, Maliranta sanoo.
Molemmat tutkimukset ovat ajalta ennen Deepseekin tehokkuusinnovaatioita.
Deepseek on tehnyt palvelun kuluttajille ja yhteiskunnille
Jos tekoälystä halutaan lisää tuottavuus- ja talouskasvua, sen kehityksestä ja käytöstä pitää tulla halvempaa.
Innovaatioista saatava hyöty nimittäin riippuu siitä, kuinka laajalle ne leviävät, Toivanen toteaa. Hän viittaa niin sanottuun Schumpeterin trilogiaan.
– Invention, innovation, diffusion. Eli ensin on idea, sitten tulee innovaatio eli tuote ja sitten se pitää saada laajaan käyttöön.
Tekoälyssä idea ja monia tuotteita on jo olemassa, mutta käyttö on vielä vähäistä. Yhdysvalloissa yrityksistä vain noin viisi prosenttia kertoo hyödyntävänsä tekoälyä.
Se, laajeneeko käyttö, riippuu ennen kaikkea hinnasta. Siinä avainasemassa on kilpailu – tai sen puute.
– Jos tekoälytekniikkaa tuottavilla firmoilla on vahva markkina-asema, ne hinnoittelevat sen kalliimmaksi. Se jarruttaa käyttöönottoa, Toivanen sanoo.
Kilpailua lisäämällä Deepseek on siis saattanut tehdä suuren palveluksen kuluttajille ja yhteiskunnille.
Esimerkiksi useat kiinalaiset sähköautovalmistajat, kuten Teslan kilpailija BYD, ilmoittivat jo ottavansa Deepseekin käyttöön autoissaan.
Syksyllä Deepseekin aiempi, vähemmän mullistava versio lisäsi jo hintakilpailua. Siihen vaihtoi amerikkalaisesta Claude-tekoälystä esimerkiksi kasvuyhtiö, joka ennustaa sijoitustuottoja tekoälyllä. Suorituskyky oli samaa luokkaa, hinta vain neljänneksen Clauden hinnasta.
– Emme halua maksaa suorituskyvystä, jota emme tarvitse, yhtiön toimitusjohtaja Anthony Poo sanoi Wall Street Journalille.
Uusimmissa malleissa hintaero eturivin amerikkalaistekoälyihin on vielä paljon jyrkempi.
ChatGPT:hen verrattuna Deepseek on kymmeniä kertoja halvempi. Halvempiinkin yhdysvaltalaisiin verrattuna hintaero on moninkertainen.
Suomi on vahvoilla
Laboren Mika Maliranta sanoo, että uuden teknologian kehittävä maa saa keksinnöstä kilpailuetua. Silti tärkeintä valtioiden ja yritysten kasvun kannalta on kyky ottaa käyttöön muualla jo kehitettyjä teknologioita.
Jos kasvukiihdytyksen siis haluaa, tekoäly pitää ottaa käyttöön, sitä ei tarvitse keksiä itse.
Suomessa valmiudet tähän näyttävät Malirannan mukaan erityisen vahvoilta.
Ensinnäkin työntekijöillä on Suomessa vahvat kyvyt teknologioiden käyttöönotossa, kertovat esimerkiksi ”aikuisten Pisa-testit” ja muut mittaukset.
https://www.businessinsider.com/all-chinese-automakers-adding-deepseek-ai-ev-cars-2025-2
Tomi Engdahl says:
https://futurism.com/bernie-sanders-issues-warning-about-elon-musks-plans-for-ai-you-will-be-out-on-the-street?fbclid=IwY2xjawI4vG9leHRuA2FlbQIxMQABHUOm5pb_GQtMptQXpNgh-ZXixMxOBRQdsTRa8Tc_HxFchR6QfrnjBzWxYg_aem_lvFnSLK3hvP5kZhf7DQE4w
Tomi Engdahl says:
https://www.facebook.com/share/p/16C7sbtVDe/
At an international tech conference in Barcelona, Melbourne-based startup Cortical Labs has launched CL1, the world’s first commercial biological computer. The system, which operates in a cloud-based “Wetware-as-a-Service” model, contains lab-grown human neurons capable of learning from inputs.
CL1 builds on the company’s earlier success in teaching neurons to play Pong in 2022. Dr. Brett Kagan, Cortical Labs’ chief science officer, envisions disease modeling, drug testing, and AI development applications that leverage neurons’ efficiency and learning speed.
While researchers acknowledge the potential of biological AI, they also highlight its limitations. Unlike traditional AI models, CL1 uses significantly less power and can process small amounts of data more efficiently. Scientists continue to explore how these lab-grown neurons could revolutionize computing and medical research.
Tomi Engdahl says:
Keikahduspiste
Historian merkittävin teknologiamullistus saattaa tulla jo vuoden tai kahden päästä, uskoo huippuhakkeri Mikko Alasaarela. Kun kone on kaikessa ajattelussa ja ideoinnissa ihmistä parempi, mikään ei ole niin kuin ennen.
https://www.hs.fi/visio/art-2000011079703.html
Olen kohta työtön ja niin olet sinäkin, jos teet töitä aivoillasi. Näin käy, mikäli teknologia-alalla yleistynyt väite pitää paikkansa.
Se tarkoittaisi, että teknologiayhtiöt onnistuvat kehittämään tietokoneohjelman, joka kykenee tekemään kaikki ajattelua vaativat tehtävät paremmin kuin ihminen. Tällaista kutsutaan yleiseksi tekoälyksi, englanniksi artificial general intelligence (AGI).