In the demo, which was posted by Google on Twitter for demonstrate the capabilities of their chatbot Bard, which is currently considered the main competitor to ChatGPT Astronomers and astrophysicists, however, immediately noticed a factual error in the chatbot’s response: the AI wrote that the James Webb telescope took the very first pictures of an exoplanet outside the solar system. In fact, the first image of an exoplanet was taken in 2004 using the Very Large Telescope (VLT) complex.

The mistake cost the company dearly: Shares in parent company Alphabet, which owns Google, plunged more than 7%, hurting the company's market value by $100 billion.

Bard’s blunder highlights the challenge for Google as it races to integrate the same AI technology that underpins Microsoft-backed ChatGPT into its core search engine. In trying to keep pace with what some think could be a radical change spurred by conversational AI in how people search online, Google now risks upending its search engine’s reputation for surfacing reliable information.

Like ChatGPT, Bard is built on a large language model, which is trained on vast troves of data online in order to generate compelling responses to user prompts. Experts have long warned that these tools have the potential to spread inaccurate information.

![](img/microsoft_artificial_intelligence_13340.avif)

In an apparent attempt to address that concern, Google previously said Bard would first be opened up to “trusted testers” this week, with plans to make it available to the public in the coming weeks.

> ### **“This highlights the importance of a rigorous testing process, something that we’re kicking off this week with our Trusted Tester program,” a Google spokesperson told CNN in a statement Wednesday about the factual error. “We’ll combine external feedback with our own internal testing to make sure Bard’s responses meet a high bar for quality, safety and groundedness in real-world information.”**

Google unveiled Bard earlier this week as part of an apparent bid to compete with the viral success of ChatGPT, which has been used to generate essays, song lyrics and responses to questions that one might previously have searched for on Google. ChatGPT’s meteoric rise in popularity has reportedly prompted Google’s management to declare a “code red” situation for its search product.

### **Is the world not ready for AI chatbots yet?**

Many experts believe that AI tools are not yet ready for integration into search engines, and therefore you should not rush into this matter.

Carissa Veliz of the University of Oxford believes that this story shows once again that the transition to using AI-powered chatbots to provide web search results is happening too quickly, meaning that the potential for misinformation to spread is huge.


Discover the costly mistake made by Google's Bard Chatbot during its debut, resulting in a staggering $100 billion loss for the company. Learn about the implications and future of AI in our in-depth analysis at The Cymes.

Google's Bard Chatbot Fiasco: $100 Billion Loss After Factual Error in First Demo | The Cymes

CNN: Google’s much-hyped new AI chatbot tool Bard, which has yet to be released to the public, is already being called out for an inaccurate response it produced in a demo this week

Google's Bard chatbot made a factual error during its first demo: The mistake cost the company $100 billion

## Menu-based chatbots

The simplest chatbots do not bother with processing the text typed by the user. Instead, a user can choose from a limited set of predefined “phrases” by pressing the appropriate phrase-button. [Landbot.io](https://landbot.io/) constructor is a good example of such approach. Slash-command Slack bots also fall into this category.

These bots don’t require NLU and the complications it brings, and thus are extremely easy to implement. In many cases, you don’t need to write even a single line of code. There are tools that allow creating such a bot and designing the dialogue flows in visual editors.

Menu-based chatbots are successfully used by a lot of businesses, but they are not nearly as engaging as other types of bots. Still, for basic customer service with simple queries and predefined conversation flows, they provide the best value for the money. Also, they are a great option for a quick test of a market or idea along the lines of lean approach.

Now, let’s step out from the comfort zone of controlled user behaviour into the realm of unrestricted free text input. And here comes…

## Rule-based chatbots

The simplest thing you can do when processing the free text input is to detect keywords and phrase patterns and then to react based on them. Given the complexity and variability of natural language, this approach is very simplistic. Nevertheless, it is impressive how far you can get with it if you need a highly specialised bot for queries with limited and very specific vocabulary.

Rule-based chatbots rely on simple text processing tools (read: regular expressions), and thus can be up and running quickly without any knowledge of modern NLU science. Unfortunately, as the project expands with additional functions and broader vocabulary, a bot becomes too complex to maintain and develop.

Poor scalability coupled with the inability to fully embrace the richness of natural language makes this approach the least recommended. But if you still want to try it, check out [ChatScript](https://github.com/bwilcox-1234/ChatScript).

Finally, we are entering the realm of true NLU. But this does not need to be too hard since you can create…

## Chatbots based on NLU-as-a-Service

Everything is simpler with SaaS. And thanks to Clouds, we have a good selection of SaaS NLU providers. Not surprisingly, most the famous names come from FAMGA:

* [Wit.AI](https://wit.ai/) by Facebook;
* [LUIS](https://www.luis.ai/) by Microsoft;
* [DialogFlow](https://dialogflow.com/) by Google;
* [Lex](https://aws.amazon.com/lex/) by Amazon.

There are some promising startups in the field too, [Recast.AI](https://recast.ai/) and [Craft.AI](http://www.craft.ai/) being just a few worth mentioning.

Most of these services provide APIs for intent classification. Here’s how they work. First, you define a model. The model basically contains a set of intents the user may express while chatting with the bot and some sample utterances the user may use for that (the more the better). Then, you let the service learn on this model. After that, the NLU-as-a-Service will be able to analyse the actual user input in real time and tell you to which intent it most likely corresponds. Unlike a rule-based bot, this service can recognise the intent even if the real user’s message is quite different from what the developers have provisioned.

The actual development process is somewhat more nuanced, and you better entrust it to the experts that understand the concepts behind it. But apart from this, everything is still straightforward, and the project kick-off is as fast as with the rule-based approach. At the same time, NLU-as-a-Service bots scale better as their functionality grows.

Chatbots of this type provide a middle ground between the cost of development and the potential of the bot. NLUaaS gives you good results with interpreting user goals from conversational queries, but that may still be not enough. If you need a universal mechanism for entities recognition, support for complex contexts, ability to nest dialogues, etc., you will want to go with…

## Chatbots with custom NLU stack

If you need more flexibility in the way your NLU works, you have to build your own stack from the open-source, free, or purchased components. You can choose the [Rasa Stack](https://rasa.com/) that is a drop-in replacement for the abovementioned intent classification services.

> **"You will need to roll out your own infrastructure, but for this additional cost you will also get the ability to fine-tune the NLU pipeline to the exact domain you need to get better results. SaaS solutions cannot do that as they are created to work for a broad range of customers", says Andriy Skuratov, R&D Manager at ELEKS** 

Or, you can drop the intent classification altogether and build your bot logic directly around Name Entity Recognition process using, for example, [NLP4J](https://emorynlp.github.io/nlp4j/) from Emory University, or [CoreNLP](https://stanfordnlp.github.io/CoreNLP/) from Stanford—whatever works best for you.

The amazing things such bots can do don’t come for free. Projects of this type tend to take longer, need more infrastructure, and require the [engineers with specific skills](https://eleks.com/services/data-science-services/) that are not so widespread. In general, such projects are more expensive compared to the SaaS approach.

But as a result, you get a more flexible system, NLU that can become incrementally better, higher product quality, and thus the ability to create a more advanced and engaging experience for your users.

So, if you are about quality, this is the way to go. But if you need to take the quality over the top or the problem you are solving is very specific, you will need to…

## Build your NLU from scratch

To do this, you need to involve the experts in the NLU field. They will use the achievements of modern Data Science to create a custom, low-level solution for your problem. Naturally, creating your chatbot from scratch is the most expensive and time-consuming option. We will not go into great detail here as each case is individual and there are no general guidelines. To get a glimpse of the level of tasks solved by this kind of project, we will once again refer you to [our previous article](https://labs.eleks.com/2018/02/how-to-build-nlp-engine-that-wont-screw-up.html).

Now, we will finish our bird’s-eye overview. As you can see, when it comes to creating the chatbot, there is a range of options from the simplest and budget-friendly to the most sophisticated and expensive. [Let us know](https://eleks.com/contact-us/) if you have a choice to make and we will smoothly lead you through the process.

https://labs.eleks.com/


Chatbots are the hot topic. There are lots of articles that explain how to create a chatbot without coding. At the same time in our article, we just recently explored the complexity of Natural Language Understanding (NLU) and how to deal with it

How to Create a Chatbot to Fit Your Needs and Budget

Digital energy consumption now rivals aviation. Discover the principles of Green Coding, from algorithmic efficiency to real-time profiling with tools like PowerAPI, and see how Big Tech is turning lean code into a competitive advantage.

Green Coding: Reducing the Carbon Footprint of Software & AI

Why Inefficient Algorithms Are the New Carbon Emissions—and How Developers Can Use Energy-Aware Design to Build a More Sustainable Digital Future.

Green Code: The Hidden Climate Cost of Your Software

One of the best things about open source is the ability to collaborate and build on the work of others. This leads to rapid innovation and the creation of top-notch software that can do all sorts of amazing things. The human face of open source includes developers, designers, documentation writers, and other volunteers who lend their skills and expertise to the cause.

**The Open-Source Community: A Melting Pot of Talents**

Open-source projects often have a really strong sense of community, with contributors coming from all sorts of different backgrounds and locations. This diversity brings new perspectives and approaches to problem-solving, which can lead to even more innovation and progress. The open-source community is a melting pot of talent, where people from various disciplines, such as software development, UX/UI design, technical writing, and project management, come together to build something great.

![An illustration showcasing a diverse group of people, representing developers, designers, documentation writers, and other contributors working together on an open-source project. This image highlights the collaborative nature of open-source communities.](img/jud-mackrill-of_m3hmsoaa-unsplash.jpg "Diverse group of people working together")

**The Importance of Mentorship and Collaboration**

Within the open-source community, mentorship plays a crucial role in nurturing talent and fostering collaboration. Experienced members guide newcomers and help them find their footing in the project. They share their knowledge, answer questions, and assist with troubleshooting, thus ensuring that everyone can contribute to the project's success.

**Open-Source Projects and Events: Bringing People Together**

Various open-source events, such as hackathons, conferences, and meetups, provide opportunities for community members to come together, share ideas, and work on projects. These events encourage networking, collaboration, and skill-building, which can result in stronger bonds within the community and better software development.

![An illustration demonstrating different ways users can engage with open-source projects, such as reporting bugs, providing feedback, or using the software. This image will help convey that user participation is a crucial aspect of open-source success.](img/daria-nepriakhina-_xr5rkprhqu-unsplash.jpg "User engagement with open-source software")

**The Users: The Unsung Heroes of Open Source**

But the human face of open source isn't just about the people who create the software - it's also about the people who use it! Open-source projects rely on the support and participation of users to be successful. Whether it's reporting bugs, giving feedback, or simply using the software, every bit of involvement helps make the project better. Users often become advocates for open-source projects, promoting them within their networks and helping to spread the word about the software's benefits.

**The Impact of Open Source on the World**\
\
The dedication, creativity, and collaboration within the open-source community have led to the development of countless tools and technologies that we rely on every day. From operating systems like Linux to content management systems like WordPress, open-source software powers much of the digital world. Moreover, the open-source approach has also influenced other industries, such as biotechnology, education, and scientific research, where sharing knowledge and resources has led to groundbreaking discoveries and advancements.

![An illustration showing a world map with pins or lines connecting different locations, representing the diverse and geographically distributed nature of open-source contributors. This image highlights the global nature of open-source communities.](img/annie-spratt-kzo9xqmo_ta-unsplash.jpg "A global map with pins or connecting lines")

**The Challenges and Rewards of Open Source**

Despite the many benefits of open-source projects, there are also challenges that contributors face. These can include a lack of financial support, time constraints, and the need to balance personal and professional commitments. However, the rewards of contributing to open-source projects often outweigh the challenges. Contributors can gain invaluable experience, build their portfolios, expand their networks, and, most importantly, create a positive impact on the world through their work.

**In Conclusion: Celebrating the Human Face of Open Source**

In short, the human face of open source is all about dedication, creativity, and collaboration. Without the hard work and passion of these amazing people, many of the tools and technologies we rely on every day simply wouldn't exist. By celebrating the contributions of developers, designers, writers, users, and all the other individuals who make open-source projects successful, we not only recognize their achievements but also encourage others to join in and help make the world a better place through open source.


Discover the people behind open-source projects - from developers to users - and learn how their collaboration, diversity, and sense of community drive innovation and create top-notch software. Explore the human side of open source with Open Source Insights.

The Human Face of Open Source: Collaboration, Diversity, and Community | Open Source Insights

Open source software isn't just about code - it's about people! Behind every open source project are real human beings who pour their time, skills, and passion into making it happen. These people are the human face of open source, and they're a crucial part of what makes these projects so amazing.

Open Source: It's Not Just About the Code, It's About the People

WE INVITE ALL TALENTED AUTHORS TO JOIN OUR COMMUNITY🤗 ADD YOUR PUBLICATION AND TAKE THE FIRST STEP TO A WORLDWIDE AUDIENCE!