Perfect coffee recipes for true coffee lovers

AGRESSO SQL Functions Reference 2.0 released. This freeware reference provides a list of the functions available in AGRESSO SQL, their meanings and syntax. Version 2.0 contains many new entries; built-in hyperlinks allow easy navigation between entries.

Summary: We know that LLMs hallucinate. And we know that we can overcome some of that problem with better prompts. But can LLMs provide references for their work? I conducted an experiment.

Recently my friend Scott Mace asked this on X in response to a post about the evolution of software and how LLMs will likely follow that same trajectory:

Yes, but how trustworthy will it be? Can I at least see the links it used to create its response?

From X
Referenced 2024-05-21T18:09:06-0400

The short answer is "no", but the real answer is a bit more nuanced because of how LLMs like ChatGPT work. First the short answer: LLMs don't understand what they're saying so they can't reference the material that it used to create a response. They don't work like that. They don't go out, do a bunch of research and then create a response. Instead lots (and I mean LOTS) of material is fed into the program that creates the model, a multi-dimensional matrix of word orders. Then when you ask a question ("give it prompt" in LLM-speak), it processes the question and generates text based on the probabilities of words in its model¹. There's no way it can satisfy Scott directly because the model doesn't—can't, as far as I know—include the references that it used to create the text because it's generating it on the fly from material that has been thoroughly blended together.

But, in fairness, that's not what people do most of the time either. If you asked me over lunch or at the end of a tech presentation to describe zero trust and its pros and cons, I'd start talking. I wouldn't start looking up things on the web and somehow weave them into text complete with references. I'd go look for references if you asked me to back up something I said. So, let's try that with ChatGPT 4o. I gave it the following prompt:

You are a writer for a website focusing on technology. Your specialty is security. Write a 150 word explanation of zero trust with three pros and three cons.

ChaptGPT answered with this text:

Zero Trust is a security model based on the principle of "never trust, always verify." Unlike traditional security models that assume everything inside the network is safe, Zero Trust assumes that threats can exist both inside and outside the network. It requires strict identity verification for every user and device attempting to access resources, regardless of their location.

Pros:

1. Enhanced Security: By continuously verifying users and devices, Zero Trust reduces the risk of breaches and unauthorized access.
2. Minimized Attack Surface: It limits access to only what is necessary, reducing potential entry points for attackers.
3. Improved Compliance: Helps meet regulatory requirements by ensuring strict access controls and logging all access attempts.

Cons:

1. Complex Implementation: Deploying Zero Trust can be complex and time-consuming, requiring a significant overhaul of existing systems and processes.
2. Increased Costs: The initial investment in technology and training can be high.
3. User Experience Impact: Continuous verification can lead to friction and inconvenience for users if not implemented smoothly.

Zero Trust is essential for modern cybersecurity, but it requires careful planning and resources to implement effectively.

That's pretty good. But what if we need some references to other material to back up the pros and cons? I asked ChatGPT to supply them:

Now repeat that task, but this time include references as hyperlinks to back up each pro and con.

ChaptGPT answered with this text:

Zero Trust is a security model based on the principle of "never trust, always verify." Unlike traditional security models that assume everything inside the network is safe, Zero Trust assumes that threats can exist both inside and outside the network. It requires strict identity verification for every user and device attempting to access resources, regardless of their location.

Pros:

1. Enhanced Security: By continuously verifying users and devices, Zero Trust reduces the risk of breaches and unauthorized access (CSO Online).
2. Minimized Attack Surface: It limits access to only what is necessary, reducing potential entry points for attackers (NIST).
3. Improved Compliance: Helps meet regulatory requirements by ensuring strict access controls and logging all access attempts (Gartner).

Cons:

1. Complex Implementation: Deploying Zero Trust can be complex and time-consuming, requiring a significant overhaul of existing systems and processes (Forrester).
2. Increased Costs: The initial investment in technology and training can be high (ZDNet).
3. User Experience Impact: Continuous verification can lead to friction and inconvenience for users if not implemented smoothly (TechRepublic).

Zero Trust is essential for modern cybersecurity, but it requires careful planning and resources to implement effectively.

That looks great! Nice references for each bullet. There's just one problem. All the links, except the NIST reference, are dead. I don't know if they're wrong, made up, or stale. I tried finding content on a few of the sites by searching and came up dry. As I heard Johannes Ernst say once, ChatGPT is a "large language model" not a "large fact model" and this bears that out.

Still, asking for references or evidence for statements is something people are going to want. So, I tried a different tack. This time I asked this:

Why do you say complex implementation is a problem for zero trust? Can you give me a few references on that I can read myself?

ChatGPT responded with this:

Implementing a Zero Trust security model can be challenging for several reasons:

1. Overall Complexity: Zero Trust requires a comprehensive understanding of your network's intricacies, including users, devices, applications, and data. This can involve significant changes to existing infrastructure, which can be disruptive and costly. Organizations need to be prepared for the extensive planning and resources required for successful implementation​ (Help Net Security)​​ (Enterprise Networking Planet​).
2. Legacy Systems: Many organizations have legacy systems that are not designed to operate within a Zero Trust framework. These systems might require different security measures or even complete replacement, adding to the complexity and cost (Help Net Security)​​ (Enterprise Networking Planet​)
3. Cultural Shift: Zero Trust is not just a technological shift but also a cultural one. It requires continuous verification and strict access controls, which can lead to user frustration and resistance if not managed properly. Ensuring user buy-in and minimizing disruption to workflows through training and communication is essential (Deloitte United States)​​ (Guidehouse).
4. Resource Intensive: Implementing and maintaining Zero Trust can put a strain on IT resources due to the need for continuous monitoring and management. The need for advanced security tools and ongoing updates further adds to the resource demands (Help Net Security)​​ (Enterprise Networking Planet​).
5. Stakeholder Alignment: Achieving buy-in from all stakeholders and aligning them with the Zero Trust principles is critical. This requires a coordinated effort to educate stakeholders, prioritize gaps, and ensure consistent understanding and application of Zero Trust principles across the organization (Deloitte United States)​​ (Guidehouse).

These challenges highlight the importance of a phased and well-planned approach to Zero Trust implementation, considering both technological and human factors. For more detailed insights, you can refer to articles from Help Net Security and Guidehouse.

Much better. The links in the bullets all work, but the ones at the end don't. The articles it references aren’t very detailed, so I wouldn’t say they’re stellar references, but at least there’s a pointer to outside material that discusses similar challenges. So, partial success.

I've found that when you're using ChatGPT to do research, treating it like a librarian and asking questions that follow up are the best way to gain confidence that the material is correct and find the supporting material, just as I did above. I'm sure you could wrap additional helper functions around an LLM to make getting references easier. But for now interrogation through chat is the best way to get comfortable with the results.

Notes

1. Yeah, this is really simplified and thus wrong, but it's directionally correct. For a better explanation, see What Is ChatGPT Doing … and Why Does It Work?.

Photo Credit: Older Man Talking to Robot Librarian from DALL-E (public domain) Prompt: draw me a rectangular picture of an older man talking with a robot librarian. Use earth tones.

Tags: genai llm chatgpt prompt+engineering

Siemens is well known for ambitious efforts in knowledge management, providing a series of innovative tools and applications within the intranet. References@BT is such a web-based application with currently more than 7,300 registered users from more than 70 countries. Its goal is to support the sharing of knowledge, experiences and best-practices globally within the Building Technologies division. Launched in 2005, References@BT features structured knowledge references, discussion forums, and a basic social networking service. In response to use demand, a new microblogging service, tightly integrated into References@BT, was implemented in March 2009. More than 500 authors have created around 2,600 microblog postings since then. Following a brief introduction into the community platform References@BT, we comprehensively describe the motivation, experiences and advantages for an organization in providing internal microblogging services. We provide detailed microblog usage statistics, analyzing the top ten users regarding postings and followers as well as the top ten topics. In doing so, we aim to shed light on microblogging usage and adoption within a globally distributed organization.

This longitudinal, quasi-experimental study investigated students’ cognitive personality type using the Myers-Briggs personality Type Indicator (MBTI) in Internet-based Online and Face-to-Face (F2F) modalities. A total of 1154 students enrolled in 28 Online and 32 F2F sections taught concurrently over a period of fourteen years. The study measured whether the sample is similar to the national average percentage frequency of all 16 different personality types; whether specific personality type students preferred a specific modality of instructions and if this preference changed over time; whether learning occurred in both class modalities; and whether specific personality type students learned more from a specific modality. Data was analyzed using regression, t-test, frequency, and Chi-Squared. The study concluded that data used in the study was similar to the national statistics; that no major differences in preference occurred over time; and that learning did occur in all modalities, with more statistically significant learning found in the Online modality versus F2F for Sensing, Thinking, and Perceiving types. Finally, Sensing and Thinking (ST) and Sensing and Perceiving (SP) group types learned significantly more in Online modality versus F2F.

Aim/Purpose: This study aims to develop a solution for personalized tourism recommendations that addresses information overload, data sparsity, and the cold-start problem. It focuses on enabling tourists to choose the most suitable tourism-related facilities, such as restaurants and hotels, that match their individual needs and preferences. Background: The tourism industry is experiencing a significant shift towards digitalization due to the increasing use of online platforms and the abundance of user data. Travelers now heavily rely on online resources to explore destinations and associated options like hotels, restaurants, attractions, transportation, and events. In this dynamic landscape, personalized recommendation systems play a crucial role in enhancing user experience and ensuring customer satisfaction. However, existing recommendation systems encounter major challenges in precisely understanding the complexities of user preferences within the tourism domain. Traditional approaches often rely solely on user ratings, neglecting the complex nature of travel choices. Data sparsity further complicates the issue, as users might have limited interactions with the system or incomplete preference profiles. This sparsity can hinder the effectiveness of these systems, leading to inaccurate or irrelevant recommendations. The cold-start problem presents another challenge, particularly with new users who lack a substantial interaction history within the system, thereby complicating the task of recommending relevant options. These limitations can greatly hinder the performance of recommendation systems and ultimately reduce user satisfaction with the overall experience. Methodology: The proposed User-based Multi-Criteria Trust-aware Collaborative Filtering (UMCTCF) approach exploits two key aspects to enhance both the accuracy and coverage of recommendations within tourism recommender systems: multi-criteria user preferences and implicit trust networks. Multi-criteria ratings capture the various factors that influence user preferences for specific tourism items, such as restaurants or hotels. These factors surpass a simple one-star rating and take into account the complex nature of travel choices. Implicit trust relationships refer to connections between users that are established through shared interests and past interactions without the need for explicit trust declarations. By integrating these elements, UMCTCF aims to provide more accurate and reliable recommendations, especially when data sparsity limits the ability to accurately predict user preferences, particularly for new users. Furthermore, the approach employs a switch hybridization scheme, which combines predictions from different components within UMCTCF. This scheme leads to a more robust recommendation strategy by leveraging diverse sources of information. Extensive experiments were conducted using real-world tourism datasets encompassing restaurants and hotels to evaluate the effectiveness of UMCTCF. The performance of UMCTCF was then compared against baseline methods to assess its prediction accuracy and coverage. Contribution: This study introduces a novel and effective recommendation approach, UMCTCF, which addresses the limitations of existing methods in personalized tourism recommendations by offering several key contributions. First, it transcends simple item preferences by incorporating multi-criteria user preferences. This allows UMCTCF to consider the various factors that users prioritize when making tourism decisions, leading to a more comprehensive understanding of user choices and, ultimately, more accurate recommendations. Second, UMCTCF leverages the collective wisdom of users by incorporating an implicit trust network into the recommendation process. By incorporating these trust relationships into the recommendation process, UMCTCF enhances its effectiveness, particularly in scenarios with data sparsity or new users with limited interaction history. Finally, UMCTCF demonstrates robustness towards data sparsity and the cold-start problem. This resilience in situations with limited data or incomplete user profiles makes UMCTCF particularly suitable for real-world applications in the tourism domain. Findings: The results consistently demonstrated UMCTCF’s superiority in key metrics, effectively addressing the challenges of data sparsity and new users while enhancing both prediction accuracy and coverage. In terms of prediction accuracy, UMCTCF yielded significantly more accurate predictions of user preferences for tourism items compared to baseline methods. Furthermore, UMCTCF achieved superior coverage compared to baseline methods, signifying its ability to recommend a wider range of tourism items, particularly for new users who might have limited interaction history within the system. This increased coverage has the potential to enhance user satisfaction by offering a more diverse and enriching set of recommendations. These findings collectively highlight the effectiveness of UMCTCF in addressing the challenges of personalized tourism recommendations, paving the way for improved user satisfaction and decision-making within the tourism domain. Recommendations for Practitioners: The proposed UMCTCF approach offers a potential opportunity for tourism recommendation systems, enabling practitioners to create solutions that prioritize the needs and preferences of users. By incorporating UMCTCF into online tourism platforms, tourists can utilize its capabilities to make well-informed decisions when selecting tourism-related facilities. Furthermore, UMCTCF’s robust design allows it to function effectively even in scenarios with data sparsity or new users with limited interaction history. This characteristic makes UMCTCF particularly valuable for real-world applications, especially in scenarios where these limitations are common obstacles. Recommendation for Researchers: The success of UMCTCF can open up new avenues in personalized recommendation research. One promising direction lies in exploring the integration of additional contextual information, such as temporal (time-based) or location-based information. By incorporating these elements, the model could be further improved, allowing for even more personalized recommendations. Furthermore, exploring the potential of UMCTCF in domains other than tourism has considerable significance. By exploring its effectiveness in other e-commerce domains, researchers can broaden the impact of UMCTCF and contribute to the advancement of personalized recommendation systems across various industries. Impact on Society: UMCTCF has the potential to make a positive impact on society in various ways. By delivering accurate and diverse recommendations that are tailored to individual user preferences, UMCTCF fosters a more positive and rewarding user experience with tourism recommendation systems. This can lead to increased user engagement with tourism platforms, ultimately enhancing overall satisfaction with travel planning. Furthermore, UMCTCF enables users to make more informed decisions through broader and more accurate recommendations, potentially reducing planning stress and leading to more fulfilling travel experiences. Future Research: Expanding upon the success of UMCTCF, future research activities can explore several promising paths. Enriching UMCTCF with various contextual data, such as spatial or location-based data, to enhance recommendation accuracy and relevance. Leveraging user-generated content, like reviews and social media posts, could provide deeper insights into user preferences and sentiments, improving personalization. Additionally, applying UMCTCF in various e-commerce domains beyond tourism, such as online shopping, entertainment, and healthcare, could yield valuable insights and enhance recommendation systems. Finally, exploring the integration of optimization algorithms could improve both recommendation accuracy and efficiency.

Privacy: Our analog parents’ dating preferences were considered a most private of matters. For our digital children, their dating preferences is a wholesale harvesting opportunity for marketing purposes. How did this terrifying shift come to be?

I believe the first big harvester of dating preferences was the innocent-looking site hotornot.com 18 years ago, a site that more seemed like the after-hours side work of a frustrated highschooler than a clever marketing ploy. It simply allowed people to rate their subjective perceived attractiveness of a photograph, and to upload photographs for such rating. (The two founders of this alleged highschool side project netted $10 million each for it when the site was sold.)

Then the scene exploded, with both user-funded and advertising-funded dating sites, all of which cataloged people’s dating preferences to the smallest detail.

Large-scale pornography sites, like PornHub, also started cataloging people’s porn preferences, and contiously make interesting infographics about geographical differences in preferences. (The link is safe for work, it’s data and maps in the form of a news story on Inverse, not on Pornhub directly.) It’s particularly interesting, as Pornhub is able to break down preferences quite specifically by age, location, gender, income brackets, and so on.

Do you know anyone who told Pornhub any of that data? No, I don’t either. And still, they are able to pinpoint who likes what with quite some precision, precision that comes from somewhere.

And then, of course, we have the social networks (which may or may not be responsible for that tracking, by the way).

It’s been reported that Facebook can tell if you’re gay or not with as little as three likes. Three. And they don’t have to be related to dating preferences or lifestyle preferences — they can be any random selections that just map up well with bigger patterns.

This is bad enough in itself, on the basis that it’s private data. At a very minimum, our digital childrens’ preferences should be their own, just like their favorite ice cream.

But a dating preferences are not just a preference like choosing your flavor of ice cream, is it? It should be, but it isn’t at this moment in time. It could also be something you’re born with. Something that people even get killed for if they’re born with the wrong preference.

It is still illegal to be born homosexual in 73 out of 192 countries, and out of these 73, eleven prescribe the death penalty for being born this way. A mere 23 out of 192 countries have full marriage equality.

Further, although the policy direction is quite one-way toward more tolerance, acceptance, and inclusion at this point in time, that doesn’t mean the policy trend can’t reverse for a number of reasons, most of them very bad. People who felt comfortable in expressing themselves can again become persecuted.

Genocide is almost always based on public data collected with benevolent intent.

This is why privacy is the last line of defense, not the first. And this last line of defense, which held fast for our analog parents, has been breached for our digital children. That matter isn’t taken nearly seriously enough.

Privacy remains your own responsibility.

Every three years, in alignment with the building code cycle, the Gypsum Association issues new editions of the Association’s three code-referenced publications: GA-600 Fire Resistance and Sound Control Design Manual, GA-216 Application and Finishing of Gypsum Panel Products, and GA-253 Application of Gypsum Sheathing.

In its continual endeavors to keep its industry documents up to date, the association reviews the latest.

Washington – OSHA issued a correction and technical amendment to its Hazard Communication Standard to change references of “Material Safety Data Sheets” to the updated “Safety Data Sheets.”

The 2024A Z-Wave Specification Package includes several documents that have undergone an Intellectual Property Rights (IPR) review as well as clarifications and fixes.

Camden Door Controls has released two new publications to support its line of industry-leading locking products, including maglocks, strikes, and cabinet locks.

Global concerns over obesity, diabetes, and cardiovascular disease will usher in the new year’s health and wellness initiatives. Consumers will engage in the annual effort to seek out food and beverage choices with more moderate amounts of nutritive sweeteners (i.e., sucrose and fructose), lower amounts of “undesirable” fats, and fewer calories. 

The rapidly expanding worldwide population along with reduced nutrition awareness will increase the preference for natural food ingredients.

Children's Geographies; 02/01/2022
(AN 154441559); ISSN: 14733285
Academic Search Premier

Abstract Through the lens of evolutional psychology, mate preferences are posited into a three “G” framework (good genes, good resources, and good persons/parents/partners) that captures genetic quality, resource acquisition, and personality and caregiving qualities. Previous research acknowledged that adult children had different mate preferences from their parents, but had no consensus on how such differences […]

The post Parent–child discrepancies in mate preferences: A three‐level meta‐analysis was curated by information for practice.

The post How Do Financial Attitudes and Preferences Vary among Latine Consumers? was curated by information for practice.

The post CfP: Patient preferences in psychotherapy (Deadline for expressions of interest: Oct 31) was curated by information for practice.

[Economy] :
Sino-U.S. decoupling is forecast to intensify and preference for U.S. interests to expand under the incoming Donald Trump administration. This outlook was put forth Wednesday at a seminar hosted by the Korea International Trade Association(KITA). Kyung Hee University Professor Seo Jung-kun pointed to a ...

[more...]

Panelists in a discussion on ‘Mobility Megatrends 2050’, highlighted that in the next decade, with electrification, autonomous driving, smart and connected infrastructure, modal diversity, and mobility that is integrated, resilient, shared, and sustainable – powered by disruptive business models, will transform and shape up of the automotive industry. The industry is racing towards a new world, driven by sustainability and changing consumer behaviour, encompassing electric vehicles, autonomous cars, mobility fleet sharing, and always connected.

A new report from the National Academies of Sciences, Engineering, and Medicine outlines how to examine whether specific levels of nutrients or other food substances (NOFSs) can ameliorate the risk of chronic disease and recommends ways to develop dietary reference intakes (DRI) based on chronic disease outcomes.

A new report from the National Academies of Sciences, Engineering, and Medicine reviews current evidence and updates intake recommendations known as the Dietary Reference Intakes (DRIs) for sodium and potassium that were established in 2005.

With many people following different diets such as gluten-free or dairy-free, NCSolutions conducted a survey to know how consumers are embracing new lifestyle-friendly dishes this holiday season.

Shopping for an EDC pocket knife, lately, can get quite complicated. There are tons of options with lots of features described in very illustrious terms. 

Continuing Medical Education for Nurse Practitioners, Physician Assistants & Physicians

Ready for Proof of Value

Continuing our election-eve counterprogramming, here’s another post with no political content. It comes from Constantine Frangakis, who writes: I think I have found something new and interesting. In studying the topic of “evidence” for my class, where the typical principles … Continue reading →

The U.S. Centers for Medicare and Medicaid Services updated its work comp set-aside reference guide to add expand a section that addresses coordinating benefit payments with other health insurers. CMS on…

The implementation of Telecom Infra Project (TIP) Open Optical & Packet Transport (OOPT) Mandatory Use Case Requirements for SDN for Transport (MUST) in ETSI TeraFlowSDN cloud native SDN Controller will make it possible to accelerate network innovation in packet-optical networks.

Sophia Antipolis, 22 February 2023

The ETSI TeraFlowSDN community has announced their commitment to the implementation of TIP’s Mandatory Use Case Requirements for SDN for Transport (MUST) Requirements in their innovative cloud native SDN Controller. This will position TeraFlowSDN as a reference implementation in the Telecom Infra Project Open Optical & Packet Transport group (TIP OOPT). This move will also make it possible to accelerate the adoption of SDN standards for IP/MPLS, Optical and Microwave transport technologies, which is one of the main objectives of MUST.

Read More...

Basic Office References - Books and software on psychological assessment, testing and practice management.

Last year, I highlighted Brazilians' dedication to recycling aluminum cans, and extended the discussion to include aluminum recycling efforts in New Orleans, known for Mardi Gras. Recent headlines and conversations with industry leaders confirm that the commitment to recycling remains strong in both New Orleans and Latin America.

People's Bank of China USD/CNY reference rate is due around 0115 GMT.

The People's Bank of China (PBOC), China's central bank, is responsible for setting the daily midpoint of the yuan (also known as renminbi or RMB). The PBOC follows a managed floating exchange rate system that allows the value of the yuan to fluctuate within a certain range, called a "band," around a central reference rate, or "midpoint." It's currently at +/- 2%.

How the process works:

• Daily midpoint setting: Each morning, the PBOC sets a midpoint for the yuan against a basket of currencies, primarily the US dollar. The central bank takes into account factors such as market supply and demand, economic indicators, and international currency market fluctuations. The midpoint serves as a reference point for that day's trading.
• The trading band: The PBOC allows the yuan to move within a specified range around the midpoint. The trading band is set at +/- 2%, meaning the yuan could appreciate or depreciate by a maximum of 2% from the midpoint during a single trading day. This range is subject to change by the PBOC based on economic conditions and policy objectives.
• Intervention: If the yuan's value approaches the limit of the trading band or experiences excessive volatility, the PBOC may intervene in the foreign exchange market by buying or selling the yuan to stabilize its value. This helps maintain a controlled and gradual adjustment of the currency's value.

Earlier:

• ICYMI - PBOC Governor warned on yuan slide, will 'guard against risk of overshoot'

People's Bank of China USD/CNY reference rate is due around 0115 GMT.

The People's Bank of China (PBOC), China's central bank, is responsible for setting the daily midpoint of the yuan (also known as renminbi or RMB). The PBOC follows a managed floating exchange rate system that allows the value of the yuan to fluctuate within a certain range, called a "band," around a central reference rate, or "midpoint." It's currently at +/- 2%.

How the process works:

• Daily midpoint setting: Each morning, the PBOC sets a midpoint for the yuan against a basket of currencies, primarily the US dollar. The central bank takes into account factors such as market supply and demand, economic indicators, and international currency market fluctuations. The midpoint serves as a reference point for that day's trading.
• The trading band: The PBOC allows the yuan to move within a specified range around the midpoint. The trading band is set at +/- 2%, meaning the yuan could appreciate or depreciate by a maximum of 2% from the midpoint during a single trading day. This range is subject to change by the PBOC based on economic conditions and policy objectives.
• Intervention: If the yuan's value approaches the limit of the trading band or experiences excessive volatility, the PBOC may intervene in the foreign exchange market by buying or selling the yuan to stabilize its value. This helps maintain a controlled and gradual adjustment of the currency's value.

Earlier re China:

• Green shoots in China? Excavator sales grew 15% in October
• It's not a pretty picture in China

Are reference architectures blueprints to be followed to the letter, or adaptable guidelines? A community panel discussion.

Is there a problem with reference architectures? Or is the problem in how people use them? The panel discussion continues.

The panel wraps up the discussion with a look at the relationship between reference architectures, reuse, and standards.

Sound-programme control, sub-control and send reference stations

Reference framework of converged service for identification and authentication for IoT devices in a decentralized environment

Objective Perceptual Assessment of Video Quality: Full Reference Television