Read the complete chats with HumbleAI GPT on ChatGPT: first chat, second chat. 😎 Who is your author? πŸ€– My author is David GonzΓ‘lez Romero (David GR), an ICT Engineer and Business Consultant with over 15 years of experience in enterprise software solutions, consulting, business analytics, and data science. He is the creator of the website ‘Talking to Chatbots’ and the domain reddgr.com, where he discusses various topics with a focus on AI, technology, and finance. Through his platform, David GR explores the use of chatbots as tools for engaging discussions and offers resources for enthusiasts and professionals alike. He …

About the Author (by HumbleAI, February 2024) Read more »

Black and white line drawing generated by the ControlNet Canny model, depicting a woman in a wetsuit holding a surfboard on the beach. A text from CLIP Interrogator, describing an image, is superimposed over the drawing.

The intense competition in the chatbot space is reflected in the ever-increasing amount of contenders in the LMSYS Chatbot Arena leaderboard, or in my modest contribution with the SCBN Chatbot Battles I’ve introduced in this blog and complete as time allows. Today we’re exploring WildVision Arena, a new project in Hugging Face Spaces that brings vision-language models to contend. The mechanics of WildVision Arena are similar to that of LMSYS Chatbot Arena. It is a crowd-sourced ranking based on people’s votes, where you can enter any image (plus an optional text prompt), and you will be presented with two responses from two different models, keeping the name of the model hidden until you vote by choosing the answer that looks better to you.Β I’m sharing a few examples of what I’m testing so far, and we’ll end this post with a traditional ‘SCBN’ battle where I will evaluate the vision-language models based on my use cases.

Microsoft has just announced the launch of its own β€˜GPT Builder’ for customizing chatbots, similar to OpenAI’s β€˜GPT Store’. This was part of a broader announcement of Copilot Pro, a premium AI-powered service for Microsoft 365 users to enhance productivity, code, and text writing. According to Satya Nadella’s announcement today on Threads, Microsoft and OpenAI appear to be competing entities, yet they are working on the same technology (GPT), augmented by Microsoft’s investment in OpenAI. It certainly seems like a strange business strategy for Microsoft. Please provide some insight into the move’s rationale and strategic motivations.

Introducing a new section in Talking to Chatbots: Hiring Chatbots. In this series of chats, we will be conducting job interviews with chatbots – either a standard version of the most popular LLMs or a customized GPT or Character – and we’ll make them compete for the job. The chatbot with the best answer to our question wins and gets published. The rest of the answers will be listed, ranked, and shared in a signature SCBN chatbot battle chart. With the SCBN scores, I value adherence to my prompt instructions (role-playing is important in this case, which most chatbots fail …

Hiring Chatbots: Cloudflare’s Lava Lamps Interview Question Read more »

This website is written in English and Spanish, powered by TranslatePress WordPress plugin and Google Cloud Translation API: For automatic translations into other languages, you can use the Google Translate widget below: I am sharing the HTML code below for website owners who might find it helpful. PROTIP: ask a chatbot for help if you want to customize the languages or the main functionality of the widget: There are other professional and affordable alternatives for AI-powered website translations, such as Weglot, which I have also used on my websites in the past. I will update this page with more details …

Notes on Website Translation Read more »

AI will only be a threat to humanity the day it grasps self-deprecating humor. I said that in a previous blog post, and I maintain it. AI will never be a threat to humanity, and I firmly believe only humanity can be a threat to humanity, as I also discussed with some of my favorite language models in an older blog post. However, as someone who could call himself a technologist, I’m sensitive to the fact that all forms of technology are a subject of fear, uncertainty, and doubt for individuals and societies. That’s not a new topic, and I’ve already talked a lot about AI ethics and cognitive biases on this blog, so today’s story is not particularly novel in terms of sharing and discussing my own ideas, but a good excuse to share more chats, as well as the latest GPT that I’ve built with OpenAI’s fun and promising chatbot customization tool: The Meme Erudite.

🎡 Themes: Music, Business πŸ€– Chatbots: ChatGPT (OpenAI shared link disabled by moderation) βš™οΈ Prompt engineering: Creative writing, song meanings, language analysis [X.com post: HUMBLE] [X.com post: authenticity] [Related page: Is my Opinion Humble?] Full lyrics and translations at LyricsTranslate.com 😎 Can you write an essay, free of profanity and with polite language, based on the text I provided? (it’s taken from a rap song) The essay should be written in the first person and not exceed 1200 characters. Focus on topics such as the importance of humility, considering the person who wrote the song used to struggle financially in the past, but seems …

Polite Rap Songs: HUMBLE by Kendrick Lamar (TTCB X) Read more »

πŸ’» Themes: AI πŸ€– Chatbots: ChatGPT βš™οΈ Prompt engineering: Coding, Image Analysis [Related – Is Philosophy a Science? Introducing SCBN Chatbot Battles ] [GitHub repository] Tabulating and Formatting Text in HTML 😎 Suggest a simple HTML table format where I can include this information in a tabulated way, eliminating the hashtags of the social media post, and pulling the links in text (so the URLs are not shown). The table should be titled “Chatbot Battle: Is Philosophy a Science?“. I want to keep the emojis for the scoring system (i.e. πŸ€–πŸ•ΉοΈπŸ•ΉοΈ), but the ranking represented by the emoji medals can …

HTML and Python Coding With ChatGPT Vision (Chatbot Battle GUI) Read more »

πŸ’ΌπŸ¦ Themes: Business, Finance πŸ€– Chatbots: [ChatGPT] [Bard] βš™οΈ Prompt engineering: Public Figures, Controversial Topics [Blog post] [Acquired Podcast interview] Chatbot Battle: Charlie Munger, on Chuanfu and Musk Chatbot Rank (SCBN) Specificity Coherency Brevity Novelty Link Bard πŸ₯‡ Winner πŸ€–πŸ€–πŸ•ΉοΈ πŸ€–πŸ€–πŸ•ΉοΈ πŸ€–πŸ€–πŸ€– πŸ€–πŸ•ΉοΈπŸ•ΉοΈ View Chat ChatGPT πŸ₯ˆ Runner-up πŸ€–πŸ•ΉοΈπŸ•ΉοΈ πŸ€–πŸ€–πŸ•ΉοΈ πŸ€–πŸ•ΉοΈπŸ•ΉοΈ πŸ€–πŸ€–πŸ•ΉοΈ View Chat ✍️ SCBN Chatbot battle Scores are only reflective of the question about BYD and Tesla’s CEOs. The chat with ChatGPT was longer and included many other prompts and high-quality answers used in the original blog post. 😎 Here is another interview fragment (transcribed by ChatGPT) in which …

Charlie Munger, on BYD and Tesla, Chuanfu and Musk, at Acquired Podcast Read more »

βš—οΈπŸ’ΌπŸ¦ Themes: Science, Business, Finance πŸ€– Chatbots: [ChatGPT: first chat, second chat]. [ChatGPT Vision chats not available to share] βš™οΈ Prompt engineering: Language Analysis, Role Playing, Opinionated Answers, Prompting Games πŸ”— Related pages: [Blog post, Cognitive Biases and Wisdom in the Era of GenAI] [Blog post, Charlie Munger at Acquired Podcast] [X.com post: The Ever-Evolving Landscape of Investing and Influencing] 😎 β€œIf you think you are smarter than me, you most likely are not. There is a scientific explanation for that: the Dunning-Kruger effect” I’ve been tempted to use that sentence in social media before, but I prefer not to because …

The Dunning-Kruger Effect: Finding Self-Awareness in the Age of Overconfidence Read more »

Talking to Chatbots is a knowledge hub, created by people, augmented by the wonders of generative AI. Chatbots help us connect the power of technology with human ingenuity through conversation and curiosity. This page compiles chatbot conversations and articles posted on the blog, social media, and other channels. There are endless possibilities for learning and creating using generative AI and LLM (large language model) chatbots, so it’s worth sharing our experience with prompts, answers, prompt engineering, prompt hacking tips, or just having fun. Currently, chats are organized by theme. Each category includes specific posts or conversations that align with the …

Talking to Chatbots Read more »

Generative AI Resources Datasets Talking to Chatbots dataset. Over 2,800 chatbot conversations: Talking to Chatbots unwrapped chats. Over 10,000 chatbot prompts, with their corresponding LLM inference, detailed statistics, and metrics: NLI Chatbot Prompt Categorization dataset. Over 1,000 annotated LLM prompts, from diverse real-world sources (lmsys/lmsys-chat-1m, reddgr/talking-to-chatbots-chats), suitable for textual entailment and natural language inference (NLI) tasks. Find all the datasets on my Hugging Face page. Models NLI Chatbot Prompt Categorization. A fine-tuned version of BART I trained locally on the reddgr/nli-chatbot-prompt-categorization dataset. A lightweight model specialized in categorizing chatbot prompts with zero-shot inference. I use it for categorizing all conversations shared in …

Talking to Chatbots and Reddgr Featured Content Read more »

✍️ The internet is full of content generated with generative AI models such as the LLMs powering ChatGPT, Gemini, Claude, and other chatbots, and the diffusion models that generate images or videos that mimic photographs or artistic styles. This kind of content can sometimes be helpful but often sounds repetitive, spammy, and cringe-worthy. The idea of building this website emerged because I believe LLMs and generative AI models are great tools for generating text and images, whether for selling products or telling stories, yet people tend to hide the fact that they use them as part of their creative tasks. …

About Talking to Chatbots and Reddgr (Red DGR) Read more »