←Ben’s Bites Waybackbensbites.com/p/thoughts-from-san-francisco6 Oct 2026sent to 170,771opened 29.8%clicks 6,325unsubs 163← 1 Oct · 8 Oct → · random

Hi folks,

Some random thoughts, notes and reflections from my week in SF.

There are roughly 4 groups of people using AI. First, the everyday folks (my mum, my wife) who use it as a better Google and may never want more. Second, the curious ones: they work on computers, they’ve tried Lovable or Replit (about 70% of Lovable signups say they’re non-technical50), and then they hit a database bug, type “fix it” five times and quit. Third, people like me who aren’t engineers but know what localhost is and can steer a coding agent. And then developers.

Back in the Makerpad days, I thought my job was to convert people into builders. But it was really helping those already curious learn how to build.

People don’t know what they could do with agents. I think curiosity comes from seeing other people’s examples. That’s why I build silly things, and why I renamed my talk to “how I build and play with AI”. Someone told me afterwards they loved how often I said “play”. This stuff should feel fun. Copy, remix, learn.

On personal agents: I think they’ll be the interface of the future. They aren’t yet. They’re sold to everyday people as “we’ll do your computer work for you” (rebook your flight!), while the rest of us see them as a way to do way more with our computers. My pet peeves:

  • One thread for everything. I want ephemeral side threads, Slack-style, and little widgets built on the fly. Wabi248 is the only one I’ve tried that does a version of this. If a personal agent built you a mini app for something, you’d be much more inclined to ask to tweak it.

  • Invisible memory. I’ve spent months tending my “context garden”, and personal agents don’t show me what they ‘remember’ about me. I make mine sync every memory to a Google Doc so I can check it.

  • Loops that never close. Agents nag me about a document I haven’t signed or something open that I did do. But maybe the tasks closed loop was in Gmail instead of Slack, or my calendar, or somewhere else.

I’m tempted to build my own (I know, it’ll be a slog). But I’d build it on primitives like Pi, not from scratch. We’re not loyal to one lab, so I’d want to pick my own pieces, and that’s why I keep investing on the building blocks. As Alex from OpenRouter61 put it, everything looks the same because these are the new primitives, just like every SaaS app was a login page plus a dashboard.

Fast feels smart: I’m not speccing work for agents to run overnight, I’m steering them all day, so I’d rather have speed. Speed often feels smarter, I’m constantly in the loop.

People want more devices. Microducks489 sold out in hours, Ghost (see in afters) sold out in hours. I’ve got a Mac Mini I barely touch and I still want more things to tinker with.

More compute, more surfaces, more play.


Headlines

You can now mod Claude Code134, like you’d mod a video game. A mod is a small add-on that changes how Claude Code behaves or looks: block risky commands, blur secrets from its output, or add your own buttons and panels. Claude can even build a mod for you. These install as plugins in Claude Code. Anthropic’s first official mod150 flags things in Claude’s replies you might miss.

Karpathy’s thoughts, tips & tricks485 on understanding LLM outputs:

  1. HTML not text

  2. diagrams

  3. plain english

  4. explainer videos

Funnily enough, these were things I mentioned in my talk last week as I often ask for these outputs.

Google Docs now opens Markdown files135 without converting them. So you can edit and comment on your Agents.md and other files with your team in Google Docs. Rolling out over the next two weeks.

Instinct157 can now join your group chats to plan trips, split tickets, and run your fantasy league. Your friends don’t need to be on Instinct.

“I was travelling over the weekend with a group of strangers. Sadly our guide was too confused to decide which spots to visit in what order. I asked both ChatGPT (not codex though) and Instinct to help with an annotated + interactive map. Instinct was much better. Maybe Codex/Claude Code would’ve done a better job but it was hard to reach for them while travelling without a laptop.” — Keshav


My feed


Afters

This is why GPUs cost $6,000

@mom_agency_55

I've been working on a skill that makes better HTML plans in Claude Code. It uses simple language, shows code snippets, surfaces questions & makes mockups. Linting reduces the normal failure cases that Claude runs into. Would love your feedback before shipping more broadly!

@trq21283

convergence to the mean when everyone looks at everyone else to decide what to make, we eventually stop making anything of our own. we copy what works. borrow the language, the aesthetic, the features. we call it learning from the market, following best practices, staying…

@ryolu_39

People keep reaching for "factory" metaphors for AI, but factories run one process to make identical parts. Knowledge work is more like an R&D lab or a Michelin kitchen: you might spin up a little assembly line to make 20 of something, then tear it down — not run it for years.

@kylemathews38

Welcome to our Monday Meditations! 🌞 Today @badlogicgames and @mitsuhiko are talking why we built Pi Durable, a harness build around a small task-based workflow engine so long-running, multiplayer agents can suspend and resume anywhere. Also: why not Temporal or Effect.ts.

@pidotdev32

Decided to make a “HomeOS” for managing our family in one place and omg I wish I had done this years ago

@ow131

Introducing Core, The Personal Al Computer The most powerful technology humanity has built should belong to you Order today: ghost.ai

@zainmfj113


* sponsors who make this newsletter possible :)
Wanna partner with us for the next quarter?
Email us at shanice@bensbites.com7 or k@bensbites.com