I had this discussion many times in my community: Claude, ChatGPT, and all the AIs are never able to properly determine days of the week and proper dates. I have the solution now, and it's the same one as for calculations. It needs to use code, so here goes the sentence to put in your global instruction for any AI that you're using or into your prompt if you need an AI to use a calendar or help you plan something. Here goes the sentence: "Always run code to compute or verify any date, day of the week, or time interval. Never answer date questions from memory." And the root cause is the same as for calculations. If the AI does not use code, it will just make a guess. That is why most of the time it gets it wrong.

The energy here is hard to describe. Every session is packed with 1,000 people or more. It has been decades since I’ve seen this many people buzzing at a conference. The excitement is palpable. But it is not just excitement. It is curiosity, concern, opportunity, and maybe a little anxiety all mixed together. You walk in and immediately see the spectacle: Elon’s presence, the Tesla Bot, and the Cybertruck sitting prominently in the center. But once you move past the flash, the deeper conversation begins. European AI laws. Copyright. Privacy. Regulation. Governance. Control. There are real questions being asked about what happens when your AI agent wakes up in the morning and starts “helping” you… while accidentally violating five different rules before breakfast. And then there is the bigger realization: AI is everywhere. Engineering. Medical. Business. Sales. Operations. Every industry. Every country. Every language. Different rooms. Different accents. Same conversation. And then the pivot… The quote of the day for me was: “We all heard that time is money. It is not. Time is life.” That line stuck with me. Because one of the quiet themes hanging in the background is this: AI has the potential to free up human time. And yet, our first instinct seems to be to use it to do more. Work more. Produce more. Respond faster. Move harder. So maybe the real question is not just, “What can AI do?” Maybe the better question is: What should AI give back to us? AI may become the most powerful productivity tool of our lifetime. But if we only use it to fill every freed-up minute with more work, we may miss the bigger opportunity. The real promise of AI is not just doing more. It may be helping us decide what is worth doing in the first place. 🌱 Food for thought. That’s my first impression from AI Week Milan. AI is moving fast, but the bigger question is whether we are moving with more purpose.

Today, we would like to recognize @Matthew Sutherland for his contributions inside the AI Bits & Pieces community. Matthew has been a great sounding board, and has also spent time reviewing Claude Code–related content and providing specific, actionable suggestions. His feedback has focused on structure, clarity, and how ideas translate into practical use. His comments are thoughtful and grounded in hands-on experience. They tend to clarify intent, tighten explanations, and make the material easier to apply for others working through the same topics. Outside the community, Matthew is the founder of Byteflow AI, where he builds and runs AI systems that automate real operational work. His focus is on workflows, agents, and integrations that run in production and support day-to-day business execution. His work follows a clear framework — Scope. Shoot. Solve. — emphasizing problem definition, working deliverables, documentation, and clean handoff. Engagements range from operational assessments and system builds to incident response and targeted briefings. With more than 25 years of experience across technology, operations, and business development, Matthew brings a practical, execution-first perspective to applied AI and automation. We appreciate the time and care Matthew puts into strengthening shared work and contributing to the quality of the conversation. Thank you, Matthew, for the role you play in helping this community learn and improve together. Follow Matt on LinkedIn: https://www.linkedin.com/in/matthewsutherland/ For a highlight of Matt's Post: https://www.skool.com/ai-bits-and-pieces/classroom/5bebee2e?md=13b025f0574742bca30bc136b78d0d7e

After learning how to prompt clearly and iterate effectively, a natural question emerges: Does it matter which LLM I use if I’m iterating well? In the short run, the honest answer is no. If you’re clear in your intent and willing to refine direction, most modern LLMs will get you where you need to go. Prompting and iteration do a lot of the heavy lifting early on. That’s why many people experience an initial breakthrough and think, “Okay, I’ve got this.” And they do. At first. 💎 Why Iteration Levels the Field Early When you’re iterating well, you’re doing a few important things: - Clarifying what you actually want - Responding to output instead of restarting - Adjusting direction in small, intentional steps Those behaviors transfer. They work across LLMs because the interaction pattern is the same: input → response → refinement. In that phase, differences between LLMs fade into the background. You’re building skill, not dependency. 💎 When Fit Begins to Show Up As AI becomes something you use regularly—not occasionally—another shift starts to happen. You’re no longer experimenting. You’re working. And that’s when fit begins to show up. Not in dramatic ways In small ones that compound over time. You notice how an LLM responds to follow-ups. How much structure it assumes. How easily you can steer it without over-explaining. Tone and writing style are often where this becomes most obvious. Some people gravitate toward Claude because it feels more measured, structured, and editorial. Others prefer ChatGPT because it feels more conversational, adaptive, and easy to steer through quick iteration. Neither is better. They simply feel different to work with. And once AI becomes part of your daily rhythm, those differences start to matter. To be clear, this isn’t about specialty capabilities like coding, image creation, or domain-specific features. It’s about how naturally an LLM mirrors: - Your tone - Your writing style - The way you think through ideas

Hi Everyone, I would like to invite you to a free webinar I am hosting today. It's a comparison of the 4 models: ChatGPT, Claude, Gemini and Copilot. Today, January 15th, 19:00 CET / 1:00 PM EST https://www.linkedin.com/events/4mainaichatbotscompared7414659699100344321/ It would be great to see some of you there. There will be gifts :-)