If you're small, you're in a position where it's to your advantage to be weird—you can have a point of view that the big tech companies never could. In the world of chairs—you're not going to build a cheaper chair than Ikea. Why not build something they couldn't—like a more interesting one
LLMs Get Lost in Multi-turn Conversation
The cat is out of the bag.
Pay attention, devs.
This is one of the most common issues when building with LLMs today.
Glad there is now paper to share insights.
Here... See more
People think analytical tools and data products (like dashboards) are inherently strategic
They aren’t
Why? Because companies enlist analysts to build these solutions to solve ad hoc problems and 𝗱𝗼𝗻’𝘁 𝘁𝗵𝗶𝗻𝗸 𝗮𝗯𝗼𝘂𝘁 𝘁𝗵𝗲𝗶𝗿 𝗹𝗼𝗻𝗴-𝘁𝗲𝗿𝗺 𝘀𝘁𝗿𝗮𝘁𝗲𝗴𝗶𝗰 𝗯𝗲𝗻𝗲𝗳𝗶𝘁𝘀 (or what they could evolve... See more
once the architecture has been agreed upon, it becomes very costly—for managerial and business reasons—to significantly modify it. This is one argument (among many) for analyzing the software architecture for a large system before settling on a specific choice.
If your system requires high performance, then you need to pay attention to managing the time-based behavior of elements, their use of shared resources, and the frequency and volume of their interelement communication.
If modifiability is important, then you need to pay attention to assigning responsibilities to elements and limiting the
The Most Beginner-Friendly AI Agent Resources I’ve Seen This Year:
Here’s the breakdown:
👉 Rule #1: Define the Agent Before You Build One
Most confuse agents with chatbots that call tools
Chip Huyen’s explains the... See more