This month, IBM had a briefing on its Power platform for AI, which currently is in use by over 40K users. This may not seem like a lot, but with AI failures outnumbering AI successes, it is important to look […]
The post IBM Power: Doing Hybrid by Choice appeared first on TechSpective.
On Friday 22 November, IEEE Robotics and Automation Society will be hosting an online science communication training session for robotics and AI researchers. The tutorial will introduce you to science communication and help you create your own story through hands-on activities.
Date: 22 November 2024
Time: 10:00 – 13:00 EST (07:00 – 10:00 PST, 15:00 – 18:00 GMT, 16:00 – 19:00 CET)
Location: Online – worldwide
Registration
Website
Science communication is essential. It helps demystify robotics and AI for a broad range of people including policy makers, business leaders, and the public. As a researcher, mastering this skill can not only enhance your communication abilities but also expand your network and increase the visibility and impact of your work.
In this three-hour session, leading science communicators in robotics and AI will teach you how to clearly and concisely explain your research to non-specialists. You’ll learn how to avoid hype, how to find suitable images and videos to illustrate your work, and where to start with social media. We’ll hear from a leading robotics journalist on how to deal with media and how to get your story out to a wider audience.
This is a hands-on session with exercises for you to take part in throughout the course. Therefore, please come prepared with an idea about a piece of research you’d like to communicate about.
Part 1: How to communicate your work to a broader audience
Part 2: How to make videos about your robots
Part 3: Working with media
Speakers:
Sabine Hauert, Professor of Swarm Engineering, Executive Trustee AIhub / Robohub
Lucy Smith, Senior Managing Editor AIhub / Robohub
Laura Bridgeman, Audience Development Manager IEEE Spectrum
Evan Ackerman, Senior Editor IEEE Spectrum
Sign up here.
After speaking with hundreds of AI teams across the globe, one thing is clear: the only certainty is uncertainty.
From Boston to Dubai, I hear the same stories: AI teams feel stuck.
Leaders are forced into two bad options—build AI from scratch or buy a point solution that doesn’t quite fit.
The trust in AI simply isn’t there yet; it’s not reliable enough for most businesses to fully depend on.
And across the board, many teams lack the complete set of skills or expertise needed to truly deliver on AI’s promise.
At DataRobot, we understand the stakes. Since our inception, we’ve focused on AI that drives meaningful impact and tackles tough AI problems, which is why I am excited to announce the DataRobot Enterprise AI Suite.
Our commitment to helping organizations achieve meaningful outcomes with AI led us to create the enterprise AI suite—a comprehensive solution made up of customizable AI applications built on a flexible platform.
This suite is designed to give you everything you need to infuse AI into your business, secure your AI outcomes, and empower your AI teams.
AI that works where and how your business teams want.
We intimately understand the complex, multifaceted challenges AI teams wrestle with when trying to ensure AI fits seamlessly into stakeholder workflows, tools of choice, and exact business requirements.
That’s why we built a fully customizable suite of AI apps to address your unique business needs, making it easy to embed AI wherever your users work—whether in a standalone app, SAP applications, or tools like Slack and Microsoft Teams.
Multiple AI techniques at your fingertips.
We also appreciate that your organization’s needs aren’t one-size-fits-all. You need different AI techniques to create outcomes that make sense for your business.
Our suite gives you and your team the flexibility to apply the AI techniques that align with your business goals—whether it’s agentic flows, predictive insights, or retrieval-augmented generation (RAG)—enabling you to tackle multiple use cases with confidence.
Streamline collaboration.
One thing we hear often is how challenging it is for teams to collaborate effectively when developing, deploying, and governing AI outcomes. Pipelines are often brittle and complex, and handing off projects from one team to another can feel like an uphill battle, making it difficult to get AI solutions into production efficiently.
To help ease this burden, we designed our AI app development platform with bespoke tools that equip each team member with what they need—without the hassle of stitching together multiple tools.
You have the flexibility and control to integrate and work with the tools you prefer, accessing the most popular LLMs and models, or bringing your own.
And to accelerate development and delivery even further, our platform automates the most labor-intensive steps, from data prep and testing to CI/CD pipelines and governance.
Think of the efficiency, collaboration, reliability, transparency, and quality assurance DevOps has provided for software developers.
That’s what we’re doing for AI.
By giving everyone on your AI team the exact tooling and techniques to work how and where they want, while ensuring seamless collaboration between project hand-offs, we’re ensuring your AI model integrity is maintained from end-to-end.
The combination of our AI app-building platform, diverse AI techniques, and fully customizable apps that integrate seamlessly into business workflows is why leading Fortune 500 companies turn to DataRobot. We’re able to help them augment their hyperscaler investments and scale AI, delivering 10x the number of use cases.
As part of our enterprise AI suite, we’ve also launched over 30 new, industry-leading features.
You’ll gain deeper insights into what these are in future blog posts but, because there are ones I believe will be massively impactful I want to highlight a few that I’m most excited about.
Despite billions invested in AI, only a third of AI teams feel equipped with the tools needed to meet their business objectives. Generative AI app experience and implementing AI into the business were two of the primary unmet needs facing teams.
Two new features are designed to address these specific challenges.
Customizable AI apps and agents
We’ve codified the most common technology patterns in AI use cases into fully customizable templates, drawing from a decade of applied AI experience and thousands of diverse deployments.
This gives you and your team complete control over business logic, app logic, security, governance, and UX, allowing you to focus on outcomes instead of piecing together pipelines.
Once built, apps can be shared as templates or added to our AI App Gallery for others to use and build upon.
One-click embedding of AI into popular business applications
Because AI isn’t always used in standalone apps, we’ve added one-click embedding for Slack, Microsoft Teams, and SAP.
As SAP’s only AI partner of choice, we’ve made it effortless to embed your applications and monitoring agents into the SAP ecosystem. With direct access to SAP Datasphere and AI Core, your models are closer to your data, which means faster, more efficient scoring.
For over a decade, we’ve worked with AI leaders in highly regulated industries like finance, healthcare, and government, making AI security and governance a central focus.
This experience has shaped our approach to managing regulatory, security, and operational risks, and sharpened our understanding that as you scale, your risk exponentially grows with your AI surface area.
Now, as generative AI and agentic workflows add new layers of complexity, we’re applying our experiences to help you keep your AI solutions secure and compliant in production.
Our new industry-first tools help you ensure consistent, reliable oversight as you expand:
Regulation-ready AI and one-click generative AI compliance reports
With regulations like the EU AI Act, NYC Law No. 144, and California Law AB-2013 on the rise, compliance can be complex and time-consuming.
Our one-click generative AI compliance reports simplify this process by mapping key requirements directly to your documentation, streamlining model risk management (MRM) processes and regulatory adherence.
And because we know that achieving compliance is only the first step, we’ve introduced governance testing and alerts to help you maintain compliance, adapt to evolving standards, and reduce manual review time.
We’ve provided compliance documentation for predictive AI for years and have seen firsthand how it speeds up MRM processes, scales operations, and increases AI solutions in production tenfold. Extending this capability to generative AI was a natural next step.
AI red-team testing and add-on observability shield
Brand reputation and risk management are top of mind for AI leaders implementing generative AI, and manual security checks can’t always keep pace.
To address this, our new red-team testing flags vulnerabilities like PII leaks, prompt injections, toxicity, and bias, so you can maintain safety and compliance with less effort.
In addition, our new add-on observability offers real-time monitoring for any generative AI application built off the DataRobot platform. With just a single line of code, you can:
Unlocking AI’s full potential requires overcoming technical hurdles that can stretch model development to an average of seven months. And with most AI projects passing through five different teams, using an average of seven different tools and twelve coding languages, the process is often fragmented and complex.
This fractured approach leaves teams tangled in tooling rather than driving results and expanding their skills.
We’ve always prioritized giving teams the flexibility to work in the environments they prefer, with smooth transitions between code and GUI, predictive and generative.
That’s why we’ve prioritized giving teams flexibility to work in their preferred environments, ensuring smooth transitions between code and GUI, predictive and generative models.
Our latest release goes even further, with new building blocks that simplify the development process from start to finish.
In addition, built-in optical character recognition (OCR) transforms unstructured documents into generative AI-ready data, accelerating model training and enhancing outcomes.
The future of AI is about more than just technology — it’s about solving real business challenges in a way that makes sense for your organization.
Imagine AI seamlessly integrated into your workflows, evolving with your needs, and empowering your teams to make smarter decisions faster.
This is just the beginning. With the right tools and techniques, you can unlock new potential, streamline processes, and drive real value.
The path forward is full of possibilities, and the next step is yours to take.
To learn more, check out DataRobot’s full suite of products.
The post The DataRobot Enterprise AI Suite: driving the next evolution of AI for business appeared first on DataRobot.
Today is an exciting and historic day at DataRobot. As Debanjan shared, it’s time for a new approach to AI. One that is focused on business outcomes.
With the rapid advances in machine learning and generative AI, you’re likely seeing AI become essential to your strategy and bottom line. It’s more critical than ever to integrate AI into your business to stay competitive.
This requires an evolution in what we deliver with our enterprise AI suite and how we tell our story at DataRobot — carrying our history of innovation and impact forward in a new way that meets the AI needs of businesses today.
At DataRobot, our mission is to deliver AI that maximizes impact and minimizes risk for your business.
And the way we do that is by focusing on what matters most to you — by making AI work for your business, not making your business work for AI.
We infuse AI into your business. We do this by helping organizations seamlessly integrate AI into their existing processes with an open platform, user-friendly tooling, and high-impact applications.
We secure your AI outcomes. We do this by enabling organizations to scale AI with confidence using built-in interoperability, governance, and observability capabilities.
We empower your AI teams. We do this by maximizing team impact with AI workflows, built-in collaboration, orchestration, and a rich array of capabilities that unite models, teams, and individual needs.
While our mission is one component of the DataRobot story, how we show up every day is also key to who we are and our brand.
Today, we unveiled a new visual identity:
Our new logo is made up of building blocks that illustrate many meanings: simplifying AI complexity into actionable insights; weaving and infusing AI into your business; and the coming together of teams, processes, and technology that businesses want and need.
We’ve also introduced a new palette of bright, fresh colors that represent clarity and match the energy of market momentum and innovation at DataRobot.
And a new typography system that balances technical innovation and approachability.
DataRobot was founded to make AI useful and accessible to businesses in every industry.
For 12 years, we have spent each day working and learning from our customers and industry experts.
As we look ahead, our vision is to make business better with AI.
To our customers and partners, thank you for your partnership. We wouldn’t be here without you, and we’re thrilled to continue innovating together.
To our team, past and present, thank you for the contributions that continue to make DataRobot what it is today.
To learn more about our new approach to AI:
The post The next evolution of AI for business: our brand story appeared first on DataRobot.
We introduce Anthology, a method for conditioning LLMs to representative, consistent, and diverse virtual personas by generating and utilizing naturalistic backstories with rich details of individual values and experience.
What does it mean for large language models (LLMs) to be trained on massive text corpora, collectively produced by millions and billions of distinctive human authors?
In “Language Models as Agent Models”, compelling evidence suggests that recent language models could be considered models of agents: provided with a textual context, LLMs are capable of generating conditional text that represents the characteristics of an agent likely to have produced that context. This suggests that, with appropriate conditioning, LLMs could be guided to approximate the responses of a particular human voice, rather than the mixture of voices that otherwise emerges. If realized, this capability of LLMs would have significant implications for user research and social sciences—conditioned language models as virtual personas of human subjects could serve as cost-effective pilot studies and supporting best practices in human studies, e.g. the Belmont principles of justice and beneficence.
In this work, we introduce Anthology, an approach for steering LLMs to representative, consistent, and diverse virtual personas by providing richly detailed life narratives of individuals as conditioning context to models. Read More