No matter the process, you can tell when someone isn’t doing the work. But it isn’t as simple as “AI slop or not.” There’s a spectrum of fully generated to assisted to “artisanal, homemade sentences.” If it’s generated and untouched, you notice quickly. Assisted pieces usually feel incongruent if the author phones it in on edits. There are some interesting ideas around evals for writing, which is highly subjective, but I have no idea how we could create universally applicable benchmarks (current tools probably pattern match and use synthetic examples).

Burning $100 in Astra tokens through the Davinci Resolve MCP is worth it just to see how capable this setup is for video editing. I was blown away. I'm using OpenCode, AI Gateway, and Warp for the MCP interface.

"Go through this session (including pre-compaction) and print your response to every prompt where I corrected you, pushed back on your output, or replaced your draft with my own rewrite."

In my last job I moved into product because I love working with engineers. They possess a unique combination of creativity and clarity. Working with @lgrammel on this piece was a true joy. It's an incredible system, built with an incredible amount of thought and care.

I run a content agent in a local harness, and if you don't pay attention to how your terminal client handles shell sessions, things can get wonky fast. Coding harnesses are great at sorting things out when you back everything with git, but I agree worktrees are a great way keep project workflows isolated.

Not too long ago I thought to myself, "It seems crazy that there isn't a cross-harness plugin spec." Just a few weeks later I was tapped in to work on the Agent Plugins launch with @hefnerdotpro. This was a fun one, and a great picture of what it's like to work @vercel: shortly after you feel friction, product ships to remove it.

Justin is a talented writer. Every talented writer I work with who uses AI as part of their process: 1. Understands its power and 2. Is constantly frustrated and underwhelmed by it AI for code can feel like magic, but you can't write tests for a great blog post in the same way you can for a feature. More importantly, in writing, words are the final product, where code is a means to a product end, and that's one of the reasons writers feel these sharp edges more acutely.

AI is capable of some wildly complex tasks, but I often find myself most delighted in the simple things it can do, like cleaning up my desktop.

"The most important skill in prompting is expertise in the domain you’re prompting for." @sjgoedecke is right, and this is why even though many perceive AI as "good at writing," it doesn't make people good writers. seangoedecke.com/llms-reward…

It's likely I will produce my best writing using AI, but that's because I practice writing without AI every day.

One of my first projects @vercel was writing the first Workflow SDK announcement with @pranaygp for Ship AI last year. 100 million runs later, we ran it back for the GA launch, but the product did most of the talking this time.

Let it sink in. “It’s since written every line of code I’ve shipped, including itself.”

AI will unleash human creativity in unprecedented ways, but I'm starting to believe that it will make people worse at writing, not better. The promise is quality output with less work, but that makes the learning curve for actual writing skill steeper, and the discipline to improve was already rare. At a minimum, writing will deviate to a homogenous mean—something people are already starting to notice.

This past week I made a charcuterie board for my wedding anniversary. My wife appreciated the bottle of Louis Jadot (from our wedding day), aged Gruyère, apricots, glazed pecans, and local honey. But the Blue Heat Takis didn't hit quite as hard.

I'm the type of person who likes to have a perfect yard. I'm also the type of person who has young kids. Which means my grass is the type of grass that lies to my neighbors about who I really am.

Regardless of where you land on UX clarity discussion in this thread, that topic itself misses the most important point: Notion agents mean this is a solved problem, real or perceived.

TIL that as a 23-year-old, Rudyard Kipling traveled 14,000 miles to try and meet Mark Twain, his literary hero (he did). That's wild. What stranger-heroes would I travel 14,000 miles to track down? Ron Chernow's biography on Twain is excellent, by the way.