fred rivett 🇬🇧📈

best people to work with are: - extremely proactive - low ego / eager for feedback - high ownership / agency - say "we" instead of "me" - also fun

If you missed it, I updated my (very popular) Pangram post with a test of GPTZero. Overall, it outperformed Pangram a bit! I also did some neat work on how AI plagiarism can beat detectors. Props to @edward_the6 for giving me some credits to do this. jackonomics.substack.com/p/p…

Friday was my last day at Anthropic. Two years ago, when Claude Code was a small internal tool, I asked it to build an RL env. I steered it for tens of hours but never manually wrote a line of code. It worked, I was hooked, and I joined the team. When we first launched, most people approved every permission prompt by hand and mostly used Claude to answer questions and write tests.  Today, the default is trusting Claude's judgment to auto-approve. Claude does large migrations and builds new products.  Helping build Claude Code into an industry-defining product has been the journey of a lifetime.  Thank you to the incredible team behind Claude Code, Cowork, and Tag. These products are the sum of thousands of great ideas from you. I'll miss working with you all. Thank you to our users for embracing a new way of working. Your constant feedback shaped so much of what we shipped and your stories made the work so meaningful. Excited to see what you all make next!

Weekend hack: HackerTube. I was annoyed with YouTube's recommendations so I had Claude filter down 43M comments over 20 years of HN to 6,454 videos that keep being recommended. *Significantly* better viewing experience, ~2 hours with Opus 5.5: hackertube.org/ - Excellent recs without any logins (state is kept in local browser session) - Thumbnail is a representative frame from middle of the video instead of the super duper A/B test hyper-optimized user uploads - Underlying data from the comment analysis as one zip file, point your Claude at it and ask for your own version - HackerTube Longs ✊ A bit more on the process: I use Claude Code (desktop app for Mac), Opus 5.5 on Medium effort as my default. I only talk to Claude and have it do everything, the only "manual work" I helped with in tandem was in the browser (reminiscent of MenuGen): 1) I had to create some kind of API key from Google Cloud UI to query YouTube for video metadata, 2) I booted up a VPS box for serving and 3) I bought the domain name. Once the box was up I gave Claude the IP and told it update, secure, harden, deploy and optimize the code, and it did the whole thing. Many awesome projects that would have normally taken weeks/months even can now be few-shotted for breakfast. What else are we not thinking of.

I've read maybe ~10,000 YC applications. 8000 for YC admissions/PG quite a few years ago and anther 2000 informally as an alum. There's a new and growing mistake and I want to share why it's more important than you think. By the way - I try not to ever say YC admissions works this way or that way. That's YC's job and they're always changing things and making up their own minds. But I will share my impression and you can see what you think - YC partners, please chime in as well if you like. The YC application is fundamentally an evaluation of a founder's potential. And much less an evaluation of a specific business. (Airbedbreakfast transitioning into Airbnb because Brian, Nate, Joe never give up and never stop listening to their customers) So, in your writing of the application, YOU need to shine through. This batch, I read ~200 applications. I'm guessing over half were significantly written, edited, or polished with AI. That half was easily in the bottom half of my informal rankings, almost every time. To be clear, most were NOT AI slop. I often couldn't tell at first they had used AI. Founders were pouring their heart and soul into their app - so I what I received was high quality. But I think the AI really hurt them. Here's why: Once polished by AI, I as reader lost insight into the personality of the writer. I love the YC application because the questions are the same questions I would ask in office hours or casually to a friend that wanted help with their startup. It pushes the founder out of their pitchdeck/VC talk style into simple worded questions that can be answered simply as well. And great founders shine through when they just write like they talk. The LLM writing made answers feel more like a corporate cover letter, with the personality drained out. The AI-assisted drafts also gave me a sense of mid work. The writing itself seemed like zero standard deviations from the mean. The LLMs had lopped off the outlier portions of sentences, paragraphs, and thoughts. Given the YC App is an outlier detector, a writing tool that lops off outlier writing is the opposite of what you want. And the AI writing was needlessly verbose. Which hurts when a reliable predictor of great founders is that they're deep thinkers and deep thinking shines through in the density of their writing. So... I did an experiment. I asked a bunch of these seemingly AI-assisted app writers to talk with me live. I just asked them the same YC app questions and recorded their answers. I then gave them back the transcripts. Unedited and unpolished. And... OMG! A good number turned from easy no to actual good applications. Magic! Remove AI >> Improve application. This happened BOTH with native English speakers and founders abroad. So this is my recommendation to all of you. Don't let AI touch your application, even for a second. And maybe try the dictation approach with a friend. My apologies to the YC admissions team if you already knew AI-written applications were crap and you were using this insight to help you easily move applications to the No pile. YC's Winter Batch Application deadline is Nov 2nd.

all I do for work now is re-authenticate MCPs

Who’s the most famous person you’ve ever spoken to? Not “seen from far away” — actually talked to, even for a minute. A quick hello, a handshake, a normal conversation… and you still remember it. Who was it?

this is the first software business I've ever got to "work", let alone get 75 people to put their card down I got two service biz past $50k mrr, but saas was a hard wall. I don't have a good UX taste (I know when what I see is good, but I can't make "good" myself) But all those years I spent in service + sales gave me the backend knowledge that I think claude code can't replicate

i think Amish-maxxing will unironically become a massive status symbol in the AI era the more AI runs our lives, the more people will crave a slower / more physical one and the Amish have been living that life for 300 years: > the men walk about 18,000 steps a day (3x the average American) > only 4% of them are obese, even on a diet heavy on meat / potatoes / pie > they keep the phone in a shed at the end of the road, so nobody checks it at dinner > they go to bed when it gets dark and get up with the sun (circadian-maxxing) > they eat almost every meal together as a family > they have big families, usually 5 or more kids > they grow their own food and build their own houses & furniture with their hands > when a neighbor needs a barn, the whole community shows up and builds it in a day the Amish do actually still use some tech but before anything new comes in, the community asks one question: will this technology bring us closer together or pull us apart? which is probably the healthiest AI policy anyone has come up with lol

every product i use should just be a headless mcp, that feeds into an agent, where i never have to think about anything underneath. except for our product, of course. in our product, customers love the ui and love us very much. we're special that way.

The benefits of abundant intelligence will accrue far outside of San Fransisco. Spent the last year writing about capital, sovereignty, and the coming reordering of economic power. THE COMMANDING HEIGHTS Commanding-Heights.com

New record for Stack Overflow: <1000 questions posted last month

plot twist: after three days with the iphone duo, it's my favorite phone in years. the UI part is still a horrible mess, but this is the first truly new mobile device apple has made in decades. (more thoughts to come after at least a week with it, stay tuned)