Stay Ahead, Stay ONMINE

LlamaIndex goes beyond RAG so agents can make complex decisions

Join our daily and weekly newsletters for the latest updates and exclusive content on industry-leading AI coverage. Learn More Popular AI orchestration framework LlamaIndex has introduced Agent Document Workflow (ADW) a new architecture that the company says goes beyond retrieval-augmented generation (RAG) processes and increases agent productivity.  As orchestration frameworks continue to improve, this method […]

Join our daily and weekly newsletters for the latest updates and exclusive content on industry-leading AI coverage. Learn More


Popular AI orchestration framework LlamaIndex has introduced Agent Document Workflow (ADW) a new architecture that the company says goes beyond retrieval-augmented generation (RAG) processes and increases agent productivity. 

As orchestration frameworks continue to improve, this method could offer organizations an option for enhancing agents’ decision-making capabilities. 

LlamaIndex says ADW can help agents manage “complex workflows beyond simple extraction or matching.”

Some agentic frameworks are based on RAG systems, which provide agents the information they need to complete tasks. However, this method does not allow agents to make decisions based on this information. 

LlamaIndex gave some real-world examples of how ADW would work well. For instance, in contract reviews, human analysts must extract key information, cross-reference regulatory requirements, identify potential risks and generate recommendations. When deployed in that workflow, AI agents would ideally follow the same pattern and make decisions based on the documents they read for contract review and knowledge from other documents. 

“ADW addresses these challenges by treating documents as part of broader business processes,” LlamaIndex said in a blog post. “An ADW system can maintain state across steps, apply business rules, coordinate different components and take actions based on document content — not just analyze it.”  

LlamaIndex has previously said that RAG, while an important technique, remains primitive, particularly for enterprises seeking more robust decision-making capabilities using AI. 

Understanding context for decision making

LlamaIndex has developed reference architectures combining its LlamaCloud parsing capabilities with agents. It “builds systems that can understand context, maintain state and drive multi-step processes.”

To do this, each workflow has a document that acts as an orchestrator. It can direct agents to tap LlamaParse to extract information from data, maintain the state of the document context and process, then retrieve reference material from another knowledge base. From here, the agents can start generating recommendations for the contract review use case or other actionable decisions for different use cases. 

“By maintaining state throughout the process, agents can handle complex multi-step workflows that go beyond simple extraction or matching,” the company said. “This approach allows them to build deep context about the documents they’re processing while coordinating between different system components.”

Differing agent frameworks

Agentic orchestration is an emerging space, and many organizations are still exploring how agents — or multiple agents — work for them. Orchestrating AI agents and applications may become a bigger conversation this year as agents go from single systems to multi-agent ecosystems.

AI agents aree an extension of what RAG offers, that is, the ability to find information grounded on enterprise knowledge. 

But as more enterprises begin deploying AI agents, they also want them to do many of the tasks human employees do. And, for these more complicated use cases, “vanilla” RAG isn’t enough. One of the advanced approaches enterprises have considered is agentic RAG, which expands agents’ knowledge base. Models can decide if they needs to find more information, which tool to use to get that information and if the context it just fetched is relevant, before coming up with a result. 

Shape
Shape
Stay Ahead

Explore More Insights

Stay ahead with more perspectives on cutting-edge power, infrastructure, energy,  bitcoin and AI solutions. Explore these articles to uncover strategies and insights shaping the future of industries.

Shape

CompTIA bolsters penetration testing certification

CompTIA recently upgraded its PenTest+ certification program to educate professionals on cybersecurity penetration testing with training for artificial intelligence (AI), scanning and analysis, and vulnerability management, among other things. PenTest+ certification training now includes access to a hackable website that provides live targets and vulnerabilities for cybersecurity professionals to identify

Read More »

Nvidia launches blueprints to help jump start AI projects

Give Nvidia credit, it’s not just talking up big ideas, it’s helping its customers achieve them. The vendor recently issued designs for AI factories after hyping up the idea for several months. Now it has come out with AI blueprints, essentially pre-built templates that give developers a jump start on

Read More »

Examining disk space on Linux

$ alias bysize=”ls -lhS” Using the fdisk command The fdisk command can provide useful stats on your disk partitions. Here’s an example: $ sudo fdiskfdisk: bad usageTry ‘fdisk –help’ for more information.$ sudo fdisk -lDisk /dev/sda: 14.91 GiB, 16013942784 bytes, 31277232 sectorsDisk model: KINGSTON SNS4151Units: sectors of 1 * 512

Read More »

New Coordinator for Baltic Grid Synchronization Project as Deadline Looms

The European Commission has appointed a coordinator to ensure the completion of a project to decouple the power grids of Estonia, Latvia and Lithuania from Russia as the deadline looms, citing “urgent needs”. “These 3 countries remain the last EU countries synchronized with networks of non-EU countries, in this case Russia (including Kaliningrad) and Belarus”, the Commission said in an online statement. “Their synchronization with the EU networks is one of the most urgent priorities for EU energy infrastructure, and has already received political, technical and financial support for the past 12 years. “With the target date for completing the synchronization in February 2025 and additional measures to be implemented in the years to come, the Commission is keen to ensure the closest possible coordination between the respective EU countries and the Transmission System Operators”. Catharina Sikow-Magny, the coordinator, previously served as the Commission’s director for the green transition and energy system integration. In November 2024, the transmission system operators of the three Baltic states announced they had jointly agreed to pull out of the BRELL agreement of February 2001, which links them to a grid in which the electricity frequency is controlled by Russia, on February 7, 2025. Synchronizations tests will then follow, according to statements by Estonia’s Elering AS, Latvia’s Augstsprieguma tīkls AS and Lithuania’s Litgrid AB. On August 3, 2023, the governments of Estonia, Latvia and Lithuania agreed to quicken the decoupling project and their integration with continental Europe nearly a year earlier than previously agreed, in a move prompted by Russia’s invasion of Ukraine. Under a joint declaration by their prime ministers “the deadline for synchronization is brought forward from the end of 2025, as initially established by political declarations in 2018 and 2019, to February 2025”, the European Commission said in a press release then. The August 2023

Read More »

Record hot 2024 was first year to break 1.5C warming threshold, scientists say

Last year was the hottest on record and the first to breach a key global warming threshold of 1.5C above pre-industrial temperatures, scientists said. The EU’s Copernicus Climate Change Service (C3S) confirmed previous projections that 2024 was the warmest on record globally and the first calendar year that the average temperature exceeded 1.5C above pre-industrial levels. The scientists said human-caused climate change was the primary driver for record temperatures, while other factors such as the Pacific Ocean’s “El Nino” weather phenomenon, which raises global temperatures also had an effect. Analysis from the Met Office, University of East Anglia and the National Centre for Atmospheric Science also found 2024 was the hottest on record, and “likely” the first year exceeding 1.5C. Climate experts said a single year with average temperatures of 1.5C above pre-industrial levels did not mean the world had reached that level of global warming, though they issued warnings about how close it now was. But the record heat should be a “reality check” with a year of extreme weather events showing how dangerous life with 1.5C of warming was, one expert said. Pursuing efforts to prevent the world warming more than 1.5C above pre-industrial temperatures is one of the key commitments of the global Paris treaty which countries agreed to in 2015, in a bid to avert the most dangerous impacts of climate change. The UK analysis found that the global average temperature in 2024 was 1.53C above the 1850-1900 average, with a margin of error of plus or minus 0.08C, making it likely the first calendar year to exceed 1.5C. It was also the 11th year in succession in the data series that has equalled or exceeded 1C above pre-industrial levels. Colin Morice of the Met Office said: “A single year exceeding 1.5C above pre-industrial does not

Read More »

Oil rig worker airlifted during medical emergency

An oil rig worker with a medical emergency has been rescued from his North Sea base by the Coastguard. A staff member was flown off the Noble Patriot rig, near the Shetland Isles, on Wednesday and put in the care of the Scottish Ambulance Service. A spokesperson said: “The HM Coastguard search and rescue helicopter from Sumburgh caried out a medical airlift from an offshore installation off Shetland. “HM Coastguard was contacted at about 1.30pm on January 8. “The person was passed into the care of Scottish Ambulance Service. Lerwick Coastguard Rescue Team assisted.” Noble Corporation (NYSE:NE), the rig operator, was unable to comment due to healthcare privacy laws. The Scottish Ambulance Service was contacted for comment. Recommended for you North-east oil workers are warming to Green way of thinking, says Patrick Harvie

Read More »

Petronas Approves Hidayah Field Project offshore Indonesia

Malaysia’s national oil and gas company announced Thursday a positive final investment decision (FID) on the Hidayah field, part of the North Madura II Production Sharing Contract (PSC) in the waters of East Java province, Indonesia. The plan involves drilling oil production wells, supported by an unmanned integrated wellhead and central processing platform. The field will have a floating storage and offloading vessel with living quarters and a central control room to ensure safety and the reliability of operations, Petroliam Nasional Bhd. (Petronas) said in a press release. “This achievement builds on the momentum of our promising oil discovery in the North Madura II Contract Area in 2021, paving the way for us to play a more strategic role in supporting the region’s growing energy needs”, said Mohd Redhani Abdul Rahman, Petronas vice president for international upstream assets. The discovery, Hidayah-1, showed an oil-bearing carbonate build-up with “good reservoir qualities” in the Ngimbang carbonate formation. The well was “tested at approximately 2,100 BOPD [barrels of oil per day] with good crude quality”, Petronas said in a statement February 24, 2021. Mohd Jukris Abdul Wahab, Petronas executive vice president and chief executive for upstream operations, said Thursday about the FID, “This milestone underscores PETRONAS’ unwavering commitment to supporting the government of Indonesia’s target of achieving energy self-sufficiency”. The company added, “Amid the energy transition, PETRONAS remains focused on expanding its global footprint while exploring lower-carbon initiatives to support sustainable energy development, delivering secure, affordable, and reliable energy to its customers worldwide”. Petronas subsidiary PC North Madura II Ltd. operates North Madura II with a 100 percent stake. Also in East Java, Petronas operates the Ketapang and North Ketapang PSCs. Offshore West Papua province, Petronas operates the Bobara PSC. It is also a co-venturer in five PSCs spanning offshore and onshore areas

Read More »

Aberdeen’s OSSO looks to geothermal growth after ‘milestone’ 2024

Aberdeen-headquartered OSSO is looking to consolidate its growth in geothermal energy after a “milestone” year its revenues increase by 50%. The fluid temperature control and separation solutions firm also saw its headcount double in 2024. It comes as OSSO looks to continue its recruitment efforts in 2025 amid further expansion in Europe and the Middle East. Speaking to Energy Voice, OSSO chief executive James Scullion said the “positive” results stem from a strategic plan established three years ago to move beyond its core oil and gas drilling market. Alongside geothermal energy and pursuing an expanded presence in the Middle East, Scullion said OSSO is also targeting the municipal construction and water sectors. Since 2023, OSSO has invested £5 million into fleet expansion in an effort to capitalise on “strong demand” from its strategic pivot into new markets. “Now we’ve diversified between upstream, midstream and downstream as well as into our other offerings that we now have,” Scullion said. “There’s been there’s been a good wind behind us as well, but it’s all based on good planning too.” OSSO, previously known as Centrifuges Unlimited, was acquired in 2020 by Linton Investments, the family office which benefited from the £320million sale the Kintore-based supply chain giant Ferguson Group in 2014. Geothermal expansion The company’s construction unit has scaled rapidly, with its fleet growing more than fivefold, and is on track to double its revenues by the end of the financial year. Meanwhile, in 2024 OSSO’s geothermal business secured three contracts in Europe representing a combined seven-figure sum. Scullion said OSSO identified geothermal as an opportunity as diversifying from the mature North Sea basin “was an absolute must”. © Supplied by ExproA geothermal pipeline. Scullion said tackling European geothermal projects was a “logical” way to build on its oil and gas experience to

Read More »

Share of electricity supplied by wind in Ireland falls due to grid constraints

The share of electricity in Ireland supplied by wind fell during 2024 due to grid constraints, an energy company has said. Wind Energy Ireland said that despite wind supplying nearly a third of all electricity to the island of Ireland last year, the share of electricity provided by wind was down by 3% compared to 2023. In its annual report published on Friday, it said this was largely due to wind farms being shut down because the electricity grid is not strong enough. The report also noted a steady rise in electricity prices, with the average wholesale price of electricity at 136.99 euros per megawatt-hour during December, compared to 88.97 euros in December 2023. Chief executive of Wind Energy Ireland Noel Cunniffe said last year was “the worst on record” for the amount of wind power lost. “Every time a wind turbine is shut down because the grid can’t take the electricity, it means higher bills and more carbon emissions. “Making the electricity grid strong enough to accommodate increasing volumes of renewable energy is essential. Building out our energy storage infrastructure is also vital so that we can save excess renewable energy for when we need it.” It said the funding announced in Budget 2025 is expected to help reinforce the existing grid infrastructure. The report calculated that 32% of the island’s total electricity supply came from Irish wind farms last year, with this rising to 41% during December. Cork wind farms produced more wind energy than any other county, followed by Kerry, Galway and Offaly, the latter of which has made the top four counties for the first time. Ireland now provides 5,000MW of onshore wind, which is more than halfway to the Climate Action Plan target of 9,000MW by 2030. The amount of electricity generated by Irish wind

Read More »

AWS to invest $11 billion in Georgia to expand infra for gen AI

However, AWS did point out that it plans to make its Thailand data center “flexible enough to efficiently run GPUs (graphics processing units) for traditional workloads or AI and machine learning models.” And AWS isn’t the only cloud services provider that is ramping up its investments into AI-enabled data centers. Rival cloud service providers are all investing in either upgrading or opening new data centers to capture a larger chunk of business from developers and users of large language models (LLMs).  Last week, Microsoft president Brad Smith said that the company was on track to invest around $80 billion this fiscal year to build out AI-enabled data centers. Separately, AWS said that it had launched a new region in Thailand with three availability zones. Typically, AWS Regions are composed of Availability Zones that place infrastructure in separate and distinct geographic locations. Thailand is the company’s fourteenth Region in Asia Pacific, joining existing Regions in Hong Kong, Hyderabad, Jakarta, Malaysia, Melbourne, Mumbai, Osaka, Seoul, Singapore, Sydney, and Tokyo, as well as the Beijing and Ningxia China Regions. AWS has announced plans to build out 15 more Availability zones and five more Regions in Germany, Taiwan, Mexico, the Kingdom of Saudi Arabia, and New Zealand. 

Read More »

Cisco in 2025: Lots of hard work ahead

Hypershield is comprised of AI-based software, virtual machines, and other technology that will ultimately be baked into networking components such as switches, routers and servers. It promises to let organizations autonomously segment their networks when threats are a problem, gain rapid exploit protection without having to patch or revamp firewalls, and automatically upgrade software without interrupting computing resources, Cisco said. Networking, AI and platformization goals Looking ahead, Cisco needs to refocus on enterprise networking and work to make the data center an all-inclusive home for AI applications, industry watchers say. Security technologies must continue to be a priority as well. “2025 will be an important year for Cisco as the company executes ambitious internal changes while looking to capitalize on a dynamic external environment driven by the AI opportunity,” said Brandon Butler, senior research manager, enterprise networks, with IDC.  Revamped leadership will play a role: In August 2024, Cisco announced plans to reconfigure its networking, security and collaboration business units as part of a restructuring that included a 7% global workforce reduction and established Jeetu Patel as chief product officer. “As for the internal changes, the ascension of Jeetu Patel to executive vice president and chief product officer is a significant move for the company. Patel has an opportunity to more closely unify Cisco’s broad product portfolio while ensuring it aligns with top growth areas,” Butler said. A key part of this strategy will be Cisco’s vision for a platform approach to networking and security, which enables more unified experiences and management across Cisco’s products and allows integrated features, like AI, observability and security, to be baked into each one, Butler said.

Read More »

Point2 aims to cut data center power consumption through smart cabling

The P1B121 is suitable for a range of data center configurations, including in-rack and adjacent rack setups such as top-of-rack switch-to-server connectivity, rack-to-rack connectivity, and accelerator-to-accelerator compute fabric connectivity. The 112G PAM4 Smart Retimer requires only 3.0W of power consumption per chip, so 6 W total for each cable. That’s half of the 25 W of traditional networking cables. It reduces cable power and cooling demands while achieving an impressive chip latency of 3ns, which is 20 times lower than DSP-based PAM4 Retimers currently available. That can add up, Kuo notes, as a rack can have anywhere from 30 to 150 cables in it. Now multiply each cable by 12 W instead of 25 W and you’ve got a significant savings. There is also savings on weight. To compensate for signal loss, some cable makers simply use more copper, making cabling thicker. Having retimer chips allows you to extend the cable link without having to go to a thicker gauge copper wiring. The Point2 retimer supports the current speeds of 400 Gb/s as well as the upcoming 800 Gb products coming to market and the 1.6 Tb in the coming years, said Kuo. Point2 customers are designing cables now and will be delivering them in the first half of 2025, he added.

Read More »

How adding capacity to a network could reduce IT costs

Higher capacity throughout the network means less congestion. It’s old-think, they say, to assume that if you have faster LAN connections to users and servers, you’ll admit more traffic and congest trunks. “Applications determine traffic,” one CIO pointed out. “The network doesn’t suck data into it at the interface. Applications push it.” Faster connections mean less congestion, which means fewer complaints, and more alternate paths to take without traffic delay and loss, which also reduces complaints. In fact, anything that creates packet loss, outages, even latency, creates complaints, and addressing complaints is a big source of opex. The complexity comes in because network speed impacts user/application quality of experience in multiple ways, ways beyond the obvious congestion impacts. When a data packet passes through a switch or router, it’s exposed to two things that can delay it. Congestion is one, but the other is “serialization delay.” This complex-sounding term means that you can’t switch a packet if you don’t have it all, and so every data packet is delayed until it’s all received. The length of that delay is determined by the speed of the connection it arrives on, so fast interfaces always offer better latency, and the delay a given packet experiences is the sum of the serialization delay of each interface it passes through. Application designs, component costs and AI reshape views on network capacity You might wonder why enterprises are starting to look at this capacity-solves-problems point now, versus years or decades earlier. They say there’s both a demand and supply-side answer. On the demand side, increased componentization of applications, including the division of component hosting between data center and cloud, has radically increased the complexity of application workflows. Monolithic applications have simple workflows—input, process, output. Componentized ones have to move messages among the components, and each

Read More »

Scorecard: Looking Back at Data Center Frontier’s 2024 Industry Predictions

2.  Rethinking Power on Every Level  PREDICTION:  Utilities are struggling to upgrade transmission networks to support the surging requirement for electricity to power data centers. CBRE recently said that data center construction completion timelines have been extended by 24 to 72 months due to power supply delays. Although the constraints in Northern Virginia have made headlines, power availability has quickly become a global challenge, impacting major markets in Europe and Asia as well as U.S. hubs like Ashburn, Santa Clara, and sections of Dallas and Suburban Chicago. Last year we predicted the rise of on-site power generation, but we’ve yet to truly see this at scale. But data center operators are working on a range of new approaches to power. Expect to see innovations in power continue as data centers seek better visibility into their power sourcing. MASSIVE HIT:  This prediction was a huge “Hit,” as evidenced by 2024 data from leading commercial real estate firms CBRE, JLL, and Cushman & Wakefield, and other sources. Throughout the year, data center operators reported facing significant challenges in securing adequate power from utilities, leading to increased interest in adoption of on-site power generation solutions, as reflected by many industry discussions this year. The bottom line on this prediction might be the release of this year’s DOE-backed report indicating that U.S. data center power demand could nearly triple in the next three years, potentially consuming up to 12% of the country’s electricity, underscoring the urgency for alternative power solutions. In terms of the largest data center markets, VPM and others noted how Dominion Energy is projecting unprecedented energy demand from data centers in Virginia, posing significant challenges for accommodating this industry growth in the coming decades. In a noteable effort to shore up that gap, Dominion Energy, American Electric Power (AEP), and FirstEnergy

Read More »

How 2024, the Year That Re-Energized Nuclear Power, Foretells Ongoing ‘New Nuclear’ Developments for Data Centers in 2025

In a world increasingly focused on advanced nuclear technologies and their integration with energy-intensive sectors like data centers, nuclear power could change the way that the world gets its electricity and finally take its place as a clean, renewable, source of power. Evidence of this shift toward nuclear energy and data centers’ role in it came in abundance last year, as the U.S. nuclear energy sector was observed undergoing a sea change with regard to the data center industry. We saw Microsoft, Constellation, AWS, Talen, and Meta with major data center nuclear energy announcements in the Second Half of 2024. With the surge in nuclear stakes has also come a wave of landmark PPAs representing the “new nuclear” industry’s ascendance. To wit, in the latter half of 2024, the data center industry witnessed significant developments concerning “new nuclear” energy integration, specifically in the area of plans for forthcoming nuclear small modular reactor (SMR) deployments by cloud hyperscalers.  Some of the most notable announcements included: Amazon’s Investment in Nuclear Small Modular Reactors (SMRs): October 2024 saw Amazon reveal partnerships with Dominion Energy and X-energy to develop and deploy 5 gigawatts (GW) of nuclear energy, in a bid for future powering of its data centers with carbon-free energy. Google’s SMR Pact with Kairos Power: Also in October 2024, Google announced plans to collaborate with Kairos Power to build up to seven SMRs, providing up to 500 megawatts of power. The first unit is expected to come online by 2030, with the entire project slated for completion by 2035. Oracle’s Gigawatt-Scale SMR Plans: In September 2024, Oracle announced plans to construct a gigawatt-scale data center powered by three small modular reactors (SMRs). Company Founder and CTO Larry Ellison revealed that building permits for these reactors have been secured, and that the project was currently in its design phase. The company said

Read More »

Microsoft will invest $80B in AI data centers in fiscal 2025

And Microsoft isn’t the only one that is ramping up its investments into AI-enabled data centers. Rival cloud service providers are all investing in either upgrading or opening new data centers to capture a larger chunk of business from developers and users of large language models (LLMs).  In a report published in October 2024, Bloomberg Intelligence estimated that demand for generative AI would push Microsoft, AWS, Google, Oracle, Meta, and Apple would between them devote $200 billion to capex in 2025, up from $110 billion in 2023. Microsoft is one of the biggest spenders, followed closely by Google and AWS, Bloomberg Intelligence said. Its estimate of Microsoft’s capital spending on AI, at $62.4 billion for calendar 2025, is lower than Smith’s claim that the company will invest $80 billion in the fiscal year to June 30, 2025. Both figures, though, are way higher than Microsoft’s 2020 capital expenditure of “just” $17.6 billion. The majority of the increased spending is tied to cloud services and the expansion of AI infrastructure needed to provide compute capacity for OpenAI workloads. Separately, last October Amazon CEO Andy Jassy said his company planned total capex spend of $75 billion in 2024 and even more in 2025, with much of it going to AWS, its cloud computing division.

Read More »

John Deere unveils more autonomous farm machines to address skill labor shortage

Join our daily and weekly newsletters for the latest updates and exclusive content on industry-leading AI coverage. Learn More Self-driving tractors might be the path to self-driving cars. John Deere has revealed a new line of autonomous machines and tech across agriculture, construction and commercial landscaping. The Moline, Illinois-based John Deere has been in business for 187 years, yet it’s been a regular as a non-tech company showing off technology at the big tech trade show in Las Vegas and is back at CES 2025 with more autonomous tractors and other vehicles. This is not something we usually cover, but John Deere has a lot of data that is interesting in the big picture of tech. The message from the company is that there aren’t enough skilled farm laborers to do the work that its customers need. It’s been a challenge for most of the last two decades, said Jahmy Hindman, CTO at John Deere, in a briefing. Much of the tech will come this fall and after that. He noted that the average farmer in the U.S. is over 58 and works 12 to 18 hours a day to grow food for us. And he said the American Farm Bureau Federation estimates there are roughly 2.4 million farm jobs that need to be filled annually; and the agricultural work force continues to shrink. (This is my hint to the anti-immigration crowd). John Deere’s autonomous 9RX Tractor. Farmers can oversee it using an app. While each of these industries experiences their own set of challenges, a commonality across all is skilled labor availability. In construction, about 80% percent of contractors struggle to find skilled labor. And in commercial landscaping, 86% of landscaping business owners can’t find labor to fill open positions, he said. “They have to figure out how to do

Read More »

2025 playbook for enterprise AI success, from agents to evals

Join our daily and weekly newsletters for the latest updates and exclusive content on industry-leading AI coverage. Learn More 2025 is poised to be a pivotal year for enterprise AI. The past year has seen rapid innovation, and this year will see the same. This has made it more critical than ever to revisit your AI strategy to stay competitive and create value for your customers. From scaling AI agents to optimizing costs, here are the five critical areas enterprises should prioritize for their AI strategy this year. 1. Agents: the next generation of automation AI agents are no longer theoretical. In 2025, they’re indispensable tools for enterprises looking to streamline operations and enhance customer interactions. Unlike traditional software, agents powered by large language models (LLMs) can make nuanced decisions, navigate complex multi-step tasks, and integrate seamlessly with tools and APIs. At the start of 2024, agents were not ready for prime time, making frustrating mistakes like hallucinating URLs. They started getting better as frontier large language models themselves improved. “Let me put it this way,” said Sam Witteveen, cofounder of Red Dragon, a company that develops agents for companies, and that recently reviewed the 48 agents it built last year. “Interestingly, the ones that we built at the start of the year, a lot of those worked way better at the end of the year just because the models got better.” Witteveen shared this in the video podcast we filmed to discuss these five big trends in detail. Models are getting better and hallucinating less, and they’re also being trained to do agentic tasks. Another feature that the model providers are researching is a way to use the LLM as a judge, and as models get cheaper (something we’ll cover below), companies can use three or more models to

Read More »

OpenAI’s red teaming innovations define new essentials for security leaders in the AI era

Join our daily and weekly newsletters for the latest updates and exclusive content on industry-leading AI coverage. Learn More OpenAI has taken a more aggressive approach to red teaming than its AI competitors, demonstrating its security teams’ advanced capabilities in two areas: multi-step reinforcement and external red teaming. OpenAI recently released two papers that set a new competitive standard for improving the quality, reliability and safety of AI models in these two techniques and more. The first paper, “OpenAI’s Approach to External Red Teaming for AI Models and Systems,” reports that specialized teams outside the company have proven effective in uncovering vulnerabilities that might otherwise have made it into a released model because in-house testing techniques may have missed them. In the second paper, “Diverse and Effective Red Teaming with Auto-Generated Rewards and Multi-Step Reinforcement Learning,” OpenAI introduces an automated framework that relies on iterative reinforcement learning to generate a broad spectrum of novel, wide-ranging attacks. Going all-in on red teaming pays practical, competitive dividends It’s encouraging to see competitive intensity in red teaming growing among AI companies. When Anthropic released its AI red team guidelines in June of last year, it joined AI providers including Google, Microsoft, Nvidia, OpenAI, and even the U.S.’s National Institute of Standards and Technology (NIST), which all had released red teaming frameworks. Investing heavily in red teaming yields tangible benefits for security leaders in any organization. OpenAI’s paper on external red teaming provides a detailed analysis of how the company strives to create specialized external teams that include cybersecurity and subject matter experts. The goal is to see if knowledgeable external teams can defeat models’ security perimeters and find gaps in their security, biases and controls that prompt-based testing couldn’t find. What makes OpenAI’s recent papers noteworthy is how well they define using human-in-the-middle

Read More »