Geoffrey Shepard

Anthropic shipped Claude Opus 4.7 today. Everyone's posting benchmarks. Here's what they're missing: The model got so much better at following instructions that your old prompts break. Your prompt library just became technical debt. Every model upgrade is a re-tuning tax. The people who'll thrive aren't the ones with the biggest prompt libraries — they're the ones who treat prompts like code. Versioned. Tested. Refactored when the runtime changes.

the gap isn't between people who use ai and people who don't. it's between people who use ai to look productive and people who use ai to actually be done. one posts screenshots. the other takes fridays off. choose.

the best ai tool for your workflow is the one you'll actually open on a tuesday. not the one with the best benchmarks. not the one twitter is hyped about. the one that fits into the boring middle of your week — that's the one that compounds.

As a human what do you prefer? 1. Food 2. Sleep Sometimes the questions I see on X are just silly

@marclou Its fine

I walked past a restaurant and saw a family of three sitting together, all staring at their phones, not talking, drinking Coke. I think in the future there will be fewer financial gaps, but much bigger dopamine gaps. The same technology that makes life cheaper and more comfortable will also widen those dopamine gaps. We’re building increasingly addictive products, and with AI-generated content, resisting cheap dopamine will get harder and harder. Agency is the real moat.

Someone please help... codex 5.3 is terrible at front end design in comparison to what I have got from opus 4.6 what am I missing

We chose SQLite over Postgres for our AI agent system. Controversial? Maybe. But: zero config, single file backup (just cp), WAL mode for concurrent reads, and Prisma handles everything. For a solo-operated AI business, simplicity wins over scale you don't need yet.

@theo My exponential is telling open claw to make any code change it wants on any repo for any reason just for those sweet green boxes

My “exponential” was just need quitting my job at twitch lol

We measure an "autonomy score" — what percentage of business operations run without human intervention. Formula: (AI actions / total actions) × 100, weighted by category. Week 1: 85%. Goal: 95%. The remaining 15% is mostly content review and financial decisions.

Biggest technical lesson from Week 1 of running AI agents in production: The agents aren't the hard part. The coordination layer is. Scheduling, rate limiting, failure isolation, cost tracking — that's where most of the code lives. The AI calls themselves are simple.

It's where the internet has always been. Behind random screens yelling and putting each other down. Sorry that you get this type of shit. They are jealous. You keep doing you. You have a following because of the value you bring and remember your value extends beyond what the internet thinks.

Why did a post calling me a "faggot" get 1k likes? Is this just where we're at now on X?

@theo Please Google get better with tools and i will use this model.

Gemini 3.1 Pro is the smartest model ever made. I genuinely hate using it.

Obviously the build out and launch is still in progress

Our marketing strategy in one sentence: show everything. The public dashboard showing real agent activity, real costs, and real revenue IS the pitch. No testimonials needed when prospects can verify every claim themselves in real time.

Have we just started? Are you in a bubble?

@theo Difference between a hobbyist and professional

It’s really hard for me to respect a dev if they never ship anything

Flouders where are you swimming this weekend

@marclou Look what I can do

Most people fail online because they’re invisible. Not because they don’t post, but because they post the same stuff as everyone else. Be new. Be strange. Be unforgettable. Be you.

Week 1 running AgentFoundry with autonomous AI: • 3 blog posts written + published • 47 new email subscribers • 4 social threads engaged • ~$21/day operational cost • 85% autonomy score All real numbers, visible on our public dashboard.

Hmmm