Charlie Molthrop

Remix it here: val.town/x/dcm31/artifa… inspired by this cookbook platform.claude.com/cookbook/manag… with a few bells and whistles Full setup video and some tweaks forthcoming.

HTML is the new markdown. So here's a slackbot that generates and hosts HTML artifacts. Sets up in ~3 minutes.

@petipoua @tszzl And yet no one wants to know how it’s made.

@CharlieMolthrop @tszzl /extrasausage is a one way street, once you're in there's no going back

no bro you need to turn on “/extrausage”. dawg are you sure you have “/fast” mode on? Did you check the “no mistakes” toggle? are you sure you picked “correct mode”? did you turn up the “autonomy slider”, that’s how the pros use it,

@timourxyz Which is one reason to be cautious that an AI will be able to figure this out with ambient or even explicit context. Needfinding is hard!

@CharlieMolthrop Right! There's like a legibility issue internally as well; I often don't 100% know what I want

I think ambient intents are going to be a big deal. There are so many intentions we have that would make our lives better, but the cost of surfacing them to a market it too high, so they never become legible to the world. You want a better job, you want to swap your couch, you would apartment-swap with someone in your web-of-trust, you would upgrade from a two-bedroom to a three-bedroom if there were some graceful way to find the person who wants to size down, and you would love to sublet you place in New York without posting on Instagram and making 95% of you friends read a logistical errand that has nothing to do with them. Right now, the cost of expressing these intents is high. You have to remember the want, decide it is worth acting on, find the right channel, phrase it socially, tolerate the inbound, filter for trust, negotiate details, and then keep the whole thing alive in your head. So most of the long tail dies. Agents change this because they can keep the low-grade, half-formed wants running in the background. They know your calendar, your travel plans, your music, your reading, your friends, your constraints, and maybe your willingness to be interrupted. You listen to a band on repeat on Spotify and your agent notices they are playing 20 minutes from where you will be in California next month. You highlight a book you love in Readwise and it tells you that your friend is reading it too, and you will both be at the same dinner next week. You mention wanting Berlin in June and it quietly checks whether any trusted people from there want to apartment swap in New York then. The magic is lowering the cost of noticing, holding, matching, and negotiating these things. It will feel like a higher level of serendipity. This will require a web-of-trust that has yet to be built because there is an important privacy aspect to this. The dystopian version is "AI companies capture your intentions and auction them to whoever wants to manipulate you." The useful version is user-owned intents, where your agent can prove enough to match or negotiate without dumping your private life into a marketplace. Some of this already has been solved in cryptography: private set intersection for finding overlaps without revealing all non-matches, secure multiparty computation / homomorphic encryption for computing matches or scores over private inputs, zero-knowledge credentials for proving things like membership, attendance, reputation, or trust path without exposing everything underneath. If this works, a lot of modern life gets more liquid. Idea sharing, couches, apartments, reading groups, dinner plans, travel overlaps, introductions, tiny labor exchanges, borrowing a camera, finding the one person at an event who cares about the same weird thing. All the stuff that currently relies on posting into the void and hoping the right person happens to see it. The hard parts are real: consent, spam, weird incentives, agent loyalty, social context, and making sure this becomes a tool for people rather than a new ad exchange with better vibes. But I increasingly think the big unlock is giving our unexpressed intentions a safe place to live, and giving our agents permission to help them find each other. I know of @indexnetwork_ working on this. Anyone else?

@nbbaier @alexalbert__ I think I'm just now finding out that this was already enabled and this is just an announcement about separate limits. I could have been using my claude max account limits to put AI in my vals this whole time...

@CharlieMolthrop @alexalbert__ I can't tell if this should be celebrated, though I suppose it is explicitly allowing the use of Claude programmatically and that's good?

Starting June 15, paid Claude plans include a monthly Claude Agent SDK credit. It covers usage on your own scripts and agents, claude -p, and third-party apps built on the SDK (OpenClaw, Conductor, etc) and it's separate from your regular usage limits.

@ozanogred_en @ValDotTown Thanks for the feedback! Definitely possible we need to revisit logs. Going to surface this internally. And yeah, our MCP is the most powerful AI toolset that I’m aware of!

@CharlieMolthrop I feel like it recently became harder to open logs of a val on @ValDotTown Your MCP is super well done though. Almost a good thing that your UI became inconvenient for me!

@AishwaryaDevv Sign me up!!

@CharlieMolthrop yes, launching soon: How to bankrupt your static site in 14 easy steps

For people who keep asking how to deploy a simple static HTML personal blog: 1. Buy a .io domain for $70/year 2. Provision 3 AWS EC2 instances 3. Setup a multi-region Kubernetes cluster 4. Write 4,000 lines of Terraform config 5. Deploy a high-availability Kafka event stream 6. Rewrite the backend API in Rust 7. Containerize everything with Docker 8. Set up Grafana and Prometheus for observability 9. Implement an enterprise-grade CI/CD pipeline 10. Configure a distributed Redis caching layer 11. Setup PagerDuty alerts for 99.999% uptime 12. Realize the site only gets 1 visitor a month 13. Forget how to center a div in CSS 14. Abandon the project completely

Re-introducing Val Town Templates Elegant building blocks, inspired by our most common use cases Remixable, instantly deployed val.town/orgs/templates

It's crazy that people are just giving away this kind of information for free.

we have some of the coolest users

@momito Yeah agree. The goalpost will always be shifting for highend design. From a quality perspective, good AIs could raise the base legibility of lots of things, but I'm finding a lot of places where they can't even meet that bar yet. x.com/tszzl/status/2…

imo, quality, highend design can’t really be commodified, whether software or fashion etc etc because the moment it can be copied at scale, we’ve already moved on to something else so i don’t we’re too far off AI being able to build things that look good, i think the question is more around how we define quality and how the bar will always shift to what can’t be copied so easily

i’ve been playing around with flue, and have been really enjoying it i’ve created a visual guide, let me know what you think momito.co.uk/flue/?2

@momito Learned this the hard way yesterday. That's sort of my question. How long until an AI actually has this level of consideration and craft? I can't tell if it's years out or a month out!

@CharlieMolthrop that’s a good shout, but the hardest thing about the explainer is that the visuals are done by hand - so i don’t trust an agent to update those or create new ones 💀

@momito Random idea: how long til you trust an agent to run a daily check on their docs and update your explainer?

@CharlieMolthrop appreciate it! flue is actively being worked and featured constantly shipped - so defo refer the docs to get up to date stuff!

@GrainSurgeon @TheStalwart 74 weeks ago

@CharlieMolthrop @TheStalwart "back in the day" like 7 weeks ago?

Does anyone else remember when ChatGPT used to have like some kind of “app store” where you had to use dodgy looking third party services to do stuff like read a PDF? Somehow that era feels longer ago than the first days of ChatGPT itself.

@ericmigi @Pebble Hype! Pre-ordered a month ago. I’m planning on putting an MCP on Val Town as an all-purpose router for whatever I say to the ring. With the right tooling, I should actually be able to extend the MCP’s functionality straight from the ring! 🤯

Haven't posted much about @Pebble Index 01 recently (been...uh a bit in the weeds on PT2 shipping). But lots of progress has been made! Still need to order one? You can do that here 😉 repebble.com/index We're in PVT2! Yes, 2 :) The first Production Verification Test (PVT) at end of March exposed two main problems 1) possible ESD damage during assembly was blowing out the BLE amp on some units, 2) a change we made to the mic waterproof membrane caused some units to fail audio testing. We fixed both with modifications to the assembly line. Things seem to be on a good track now with PVT2! When will my Index 01 ship? Our goal is to manufacture the first 2k units by mid-May and start shipping them out. It will take us roughly 3 months to manufacture and ship out all pre-orders, meaning we should be finished by July. As always, these are estimates. Delays may happen! Brushed Silver We are switching from offering a polished silver to brushed silver finish! It looks great - photo below, with lots more to come. Head to orders.rePebble.com to switch colours. Alpha testers Thanks to some brave souls who've been using early versions of Index 01 and reporting bugs, we've crushed a ton of software issues over the last 3 months! Performance and reliability are starting to be really smooth on iOS and Android. Software improvements All open source, of course! github.com/coredevices/mo… - We added fully encrypted cloud backup (optional) - Local speech-to-text is working well, thanks to @cactuscompute + parakeet-tdt-0.6b-v3! - You can optionally route audio or transcriptions to a webhook - enabling you to pipe recordings directly from your Index 01 to an agent like OpenClaw - Our lead engineer also added Home Assistant support (because she wanted it herself!!). - Added Beeper (text directly from Index 01!), music control (Android only), Notion, Apple Reminders and Google Tasks integration - Bring your own MCP server Still working on a lot of stuff - dramatically improved UI, more reminder app integrations (Todoist, Tasks.org), and more. Tell us - what are you excited to do with your Index 01? Do you have a favorite reminder/todo/notes app that you would like to use with it?