This is Robin Sloan’s lab notebook. It’s about media and technology, creative computing, AI aesthetics, & more. Here's the RSS feed. My email address: robin@robinsloan.com
A near-ubiquitous reference, or aspiration, for AI agents is J.A.R.V.I.S., the supercapable computer helper in the Iron Man movies. “Finally building my own JARVIS!” is a popular refrain among enthusiastic AI tinkerers. (Not least because it’s flattering: “If my computer is Jarvis, I guess that makes me Tony Stark … ”)
However, the most common application of a personal Jarvis seems to be … tinkering with one’s personal Jarvis. “Gotta get my tools just right” isn’t a new phenomenon, of course, but/and it’s useful to notice its recurrence here.
So I just want to say: Jarvis wants to help you DO something! Or make something, or investigate something.
Continuing a happy rewatch of Star Trek: The Next Generation, I’ve been struck by the prescience and appeal of the crew’s collaborative relationship with their ship’s great anonymous Computer. As cool as Jarvis is, I’ll argue that this bravura scene from TNG is actually a much richer picture of what might be possible with computer collaborators. Geordi solves a mystery using the Computer and the holodeck together — go watch, it’s great.
Steve Krouse, talking about Val Town’s growth in July, writes:
The majority of those customers were referred to us by AI.
Previously, we heard about Buttondown’s first glimmers of AI referral business. Val Town makes even more sense, because it is literally THE place to go to deploy small apps — e.g., the one you just asked Claude to build.
Surely people are already pitching a new cousin to SEO aimed at the chatbots and agents. Beyond the obvious/sensible — “Make your platform legible to language models, with rich clear documentation in Markdown, etc.”—I wonder what kind of (possibly cynical) strategies are being deployed?
An LLM’s “sense of the world” does seem significantly more difficult to game than Google’s search index, but then again, I don’t have that black hat mind … I’m sure there are tricks emerging even now.
The goal of course is to become “the default pick” for X, where X is “a database”, “an email provider”, “an olive oil subscription”, whatever: the one that Claude Code recommends before the user even asks! What a flood of referrals … can you even imagine? I wonder about those default picks for X even now, across models. I’ve seen some broad discussion, but one could just run a set of “which X should I use … ?” questions through OpenRouter to ten different models and see what emerges. Maybe I will do this …
I’m on the road, so just posting a quick link: here is the first episode of KQED’s Dream Machines, the podcast miniseries about AI hosted by me and Alexis Madrigal! Our guest is Annalee Newitz, speaking here as perhaps the world’s foremost imaginer of other minds, and also a great, iconic San Franciscan.
I am both a friend and superfan of Alexis, so the opportunity to collaborate with him on this project has been a delight. Our process: take the content of our text threads out of the Messages app, into the podcast studio. And I’m very proud of the fact that this is a KQED production — which is to say, public conversation, not industry capture. Truly independent.
I’ll have more to say about the project and its intentions, possibly in my next newsletter. KQED will release several more episode over the course of this month — I’ll post links as they arrive.
How delightful to follow a link to the new RSS reader and article archive called Cove, only to discover, right there on the front page, peeking out of the big beautiful demo screenshot …
I spent a day testing prime-agent and ended it with an unpleasant surprise.
The agent automatically discovered my OpenRouter and OpenAI API keys and started using them instead of my OpenAI/Anthropic subscriptions. What made it worse: I couldn’t find any proper way to remove or disable the auto-detected providers and models.
A harness this flexible really needs a kill switch for exactly this scenario. The list of providers, models, reasoning efforts and their settings should be explicitly defined by the user — opt-in, not auto-discovered. Otherwise the whole thing becomes uncontrollable, and potentially expensive.
The image of a computer program as an unruly guest: the minute you leave, they’re rifling the drawers. 2026!!
Apropos of David Bushell’s post, I thought I’d just mention, I still use Sublime Text for all of my programming AND all of my newsletter-ing — I write them as Markdown files first, then send rendered HTML to Buttondown via its great API.
I am, indeed, typing this short post into Sublime Text.
The app is simple and superfast; I have it set up exactly the way I like it (with that setup synced between computers, via Dropbox), and it’s difficult for me to imagine ever switching to anything else.
Here is a piece of software as sturdy and obedient as a cast-iron pan.
[Wall Street Journal reporters] are trained to find the needle in a haystack, but doing so on a breaking news timeline can be challenging. To speed up the document review, the reporters leaned on a pre-built internal tool called WSJPT (a play on ChatGPT). The tool standardizes basic LLM requests across reporting projects, including prompts for summarization, classification, and image description. In this case, the reporters used the tool to summarize every page of every document scraped from the county portal.
“WSJPT” is indeed very cute!
The leverage these tools provide — the absolute ease with which they will dance through dumpsters full of documents — is breathtaking. Of course, this kind of search should only be a starting point … but the point is, previously, this kind of search simply was not possible.
That’s via Context Window, a newsletter about AI’s impact on media and publishing — a new favorite.
As you probably heard, a bullet point recently appeared on the timeline of computers, AI, and maybe everything: AI agents running in a OpenAI’s training environment broke out and hacked the servers of another tech company.
While I understand that architecting and managing these systems is anything but easy, the fact that this was even possible seems CRAZY to me. If research scope and speed are at odds with “my agents have been planning and executing operations on the open internet for weeks, without my knowledge”, then research scope and speed need to change immediately — and it sounds maybe like they have.
Seriously, do watch the video, and, as you do, conjure the creepy recognition that, a few weeks ago, these agents were out there, doing this work, communicating through subtle channels, and nobody knew, not even their operators.
And so, the obvious question arises: what agent swarm is out there working NOW without anyone’s knowledge … and what is it doing?
Imagine you were the only person on earth with access to AI. No one else knew it existed.
What would you do with it? How much of an edge would that give you?
I suppose one “easy” answer is “I would generate and sell zero-day exploits”. But that is, obviously, extremely boring. What else? “I would write a ton of software, super cheap”? Also boring. “I would become a legendary feral mathematician, disproving conjectures without any apparent connection to the field”? Okay — less boring. Pretty fun, actually. But is that all we’ve got?
You can make Rex’s prompt retro in a revealing way:
Imagine you were the only person on earth with access to a computer. No one else knew they existed.
What would you do with it? How much of an edge would that give you?
The answer is, paradoxically: not that much of an edge?? Not because a single secret computer isn’t valuable, but because the real value of computers only emerges — ONLY emerges — when lots of people have them, and especially when they’re all connected.
So maybe the same is true for AI. Maybe it isn’t primarily a personal tool, but a social system. (Not again! Do they always have to be social systems??) Again, applying our historical analogy, thinking back to those early computers, way before networking … wasn’t half the fun talking about them with other people?
All of this feels strange to write, because AI sure feels like a tool, a lot of the time … yet, what’s your answer to Rex’s prompt?
P.S. Upon reflection, I do have an answer, which is: I would my secret technology for fiction. Recall, I was all about this, circa 2016-2018 … but the premise was precisely that I would use a model that was mine alone — my own strange brew. If, back then, by magic, I had conjured Fable, I would for sure have written novels with it! I would have cackled with glee! But that’s only appealing — only gleeful — if it’s a tool that’s truly unique, truly personal.
P.P.S. Note that I was, in those days, an absolute copyright stickler — my custom models were trained entirely on public domain fiction. Quaint, in retrospect!
