There’s a lot of excitement about what AI (specifically the latest wave of LLM-anchored AI) can do, and how AI-first companies are different from the prior generations of companies. There are a lot of important and real opportunities at hand, but I find that many of these conversations occur at such an abstract altitude that they border on meaningless. Sort of like saying that your company could be much better if you merely adopted _more software_. That’s certainly true, but it’s not a particularly helpful claim.
This post is an attempt to concisely summarize how AI agents work, apply that summary to a handful of real-world use cases for AI, and to generally make the case that agents are a multiplier on the quality of your software and system design.
Of the many explainers I've seen and read, this is probably one of the best.
Something about this concept—two sets of synonyms (PUB and BAR, QUIZ and EXAM), which when paired together, form phrases that themselves are not synonyms (PUB QUIZ and BAR EXAM)—captured the minds of Crosscord.
If you’re a creative person, square theory is a useful framework to keep in mind. If you’re coming up with a title for a paper or a brand name, try to see if you can think of one that completes the square. If you’re writing puns for a popsicle stick or a Laffy Taffy wrapper, you can use squares to model your setups and punchlines. If you’re constructing a crossword, consider whether your theme or your question mark clues can form squares.
Proud of my colleagues in MSTIC and the amazing work they do every day.
On Thursday, researchers at Carnegie Mellon University unveiled LegoGPT, an AI model that creates physically stable Lego structures from text prompts. The new system not only designs Lego models that match text descriptions (prompts) but also ensures they can be built brick by brick in the real world, either by hand or with robotic assistance.
Oh, so that’s what AI is for…
A young computer scientist and two colleagues show that searches within data structures called hash tables can be much faster than previously deemed possible.
For more than a decade, O’Brien kept a meticulous log of mixed metaphors and malaprops uttered in Ford meetings, from companywide gatherings to side conversations. It documents 2,229 linguistic breaches, including the exact quote, context, name of the perpetrator and color commentary.
Straightforward design suggestion that works around the complexities of syncing and portability of passkeys that’s just a mess today. Use magic links on new endpoints, passkeys on existing ones.
The Nulls of the world, it turns out, endure a lifetime of website bouncebacks, processing errors and declarations by customer-service representatives that their accounts don't exist.