-
Someone built this with Replit, and it’s super useful / not loaded with banners and referral links.
-
Pro tip: If you are a professional politician who writes professional legislation and has a professional understanding of how it should be customized, automatically generating a housing plan with ChatGPT is probably not the way to show you care about the issue.
-
I’ve heard from no-coders who have built projects using LLMs, and their experience is similar. They start off strong, but eventually reach a point where they just can’t progress anymore, no matter how much they coax the AI. The code is a bewildering mess of non sequiturs, and beyond a certain point, no amount of duct tape can keep it together. It collapses under its own weight.
I couldn’t agree more. Alexa and I were discussing a WordPress theme I was playing with in Cursor, and I was telling her that the only reason I’m able to spin up some cool internal projects (despite being a strategist and not a developer) is that I understand the logic of front-end languages and what they can and can’t do.
Even if I were to insert all the CSS properties in a training doc and it could read my mind and there were no problems with the code – three highly laughable assumptions – you need to understand easings and z-index and the effects these have on other objects to avoid tearing your hair out. Part of this is some pretty dishonest marketing on how “far we’ve come” in generative AI, the other part is accepting the reality that we’ve overestimated the cost savings of FTEs as a result of AI.
Anyway, good post by Josh. Check it out.
-
I really loved this article by Jon Turow on both the excitement and work to be done on MCP. Particularly from a marketing perspective, the best use cases of AI are being drowned out by generative slop. There’s a lot more to be done.
Digging into the data reveals a two-sided story: on one side, developer tools like Cursor are driving early MCP demand; on the other, the explosive growth in MCP server supply has created opportunities for founders to build experiences that weren’t previously possible
-
Rausch eventually found his way into the sports world after connecting with Dan Quinn, then the Seattle Seahawks’ defensive coordinator, in 2014. One of Rausch’s teachings that Quinn immediately took to was the importance of specificity: providing players with exact instructions and information, instead of speaking in generalities.
Rather than telling athletes to “play tough,” for example, how could they play tough? Rausch learned from studying UCLA legend John Wooden, who still holds the NCAA record with 10 national championships. Psychologists who studied Wooden found that offering specific instructions, even ones as simple as grabbing rebounds with both hands, led to performance increases.
There’s a larger lesson here that we need to dust off in personal and professional relationships in 2025.
-
Trying something new:A 馃У on a topic I find many students struggle with: "why do their 馃搳 look more professional than my 馃搳?" It's *lots* of tiny decisions that aren't the defaults in many libraries, so let's break down 1 simple graph by @jburnmurdoch.bsky.social 馃敆 www.ft.com/content/73a1…
via Evan Peck
-
This is a good piece from CNN (I can’t believe it either) on my largest critique about AI: Both the developers and the users don’t know how to use it. Because that’s the case, we’re blaming the people rolling it out vs. the actual use cases not being known.
-
This is a test.