dvcrn

Zed already has a “agentic layout” for a while. It shifts the ai and threads to be more prominent and moves code + sidebar to the right

What’s this $10 deal?

I agree. I subscribe to SuperGrok but never used the grok models a lot for coding. Now with 4.5, I’m gonna hit my weekly limit tomorrow and even considering trying SuperGrok Heavy

I really like the feel of Grok 4.5

Built the same thing a while back: https://pi.dev/packages/pi-supergrok

Install with

pi install npm:pi-supergrok

Happened to me too but my card didn’t actually get charged, maybe check yours. Also the card in the invoice wasn’t even the card I’m using with Anthropic

> Despite thinking this is AI-generated, I agree but everything has a caveat.

Definitely not AI generated. I wrote this during a non-internet flight. :)

Hi, author here! I fully agree with your comment here and that’s exactly my point in the post: Different tools that work great for different tasks. If anything, the post is a take against treating Skills + CLI as a zero-sum replacement for MCP, and calling MCP dead/outdated

Especially portability is just not possible with Skills+CLI (yet). I can use the same MCP servers through remote MCP on my phone, web, iPad, in ChatGPT, Perplexity, Claude, Mistral and so on, which I can’t do with Skills.

> MCP has severe context bloat just by starting a thread

Hi, author here. The “MCP has severe context bloat” problem has already been solved with tool discovery. Modern harnesses don’t load every single tool + their descriptions into the context on load, but use tool search to discover the tools lazily when they’re needed. You can further limit this by telling the LLM exactly which tool to load, the rest will stay unloaded / invisible

> But a worse problem is that the output of MCP goes straight into the context of the agent, rather than being piped somewhere else

This is semi-solved as agents and harnesses get smarter. Claude Code for example does discovery in subagents. So it spawns a sub-agent with a cheaper model that explores your codebase / environment (also through MCP) and provides a summary to the parent process. So the parent won’t get hit with the raw output log

I just released Configmesh this week. It's a macOS app (with CLI companion) for e2e encrypted syncing and backing up of dotfiles and application configurations. You can sync for example stuff from ~/.config/, Application Support, *.plists, and so on, and add config sync to apps that don't support it natively

Fresh off the press

https://configmesh.app/

Demo: https://www.youtube.com/watch?v=EeA4TTpM2wk

My personal blog: https://david.coffee

And a few projects I’m working on:

- https://configmesh.app utility for syncing dotfiles + application configs

- https://fixmyjapanese.com AI powered grammar correction teacher for Japanese

- https://microfn.dev Toolbox and cloud runner for tiny composable JavaScript functions

microfn.dev - https://microfn.dev

It started out as a cloud runner for small (mostly pure) composable javascript functions that we run for you in the cloud. So whenever you have some small code snippet that you want to run, you can hit up microfn.dev, paste your code and then plug it into wherever you want (pipe into the terminal, use from MCP, add a cron to it, add to Siri shortcuts, use for home automation, ping it with webhooks, etc)

Now we added agents support, so you can have autonomous AI agents take your functions and decide when to use them. Even better, you can hook microfn into a MCP and have anything that supports MCP use those functions as well!

Suppose you need a new thing that your agent should do, you could ask the agent (whether that's claude or cursor) to compose a new function, add it to microfn, then use it itself going forward!

microfn.dev wants to be a toolbox for composable small tools. Imagine a toolbox at home with a bunch of hammers and screw drivers that you collect, share, and use for different purposes.

Some actual examples:

- Pull data off services (twitter, etc)

- Store data from sensors somewhere

- Give agents tools to talk to your specific systems without needing to write an entire MCP

- Wrap complex logic (eg slack auth + sending a message to slack) into a function and add it to a Siri shortcut, so you can quickly send messages to a specific channel with a ping or curl

Still very early alpha (beta-ish), but very excited about this

A buddy and me have been working on https://microfn.dev for a while: A platform for creating, managing and composing tiny (micro) javascript functions and using them from different places like webhooks, cron, MCP or AI agents.

It's still very heavy in development but the gist is: Say you have a cool idea for something small you want to automate or run - instead of thinking about hosting, workers, lambdas and what not, you just open microfn, open the editor (or the function generator), write your function, hit save - done! All the complexity is tucked away on microfn, and your place of use just has to authenticate with microfn and nothing else. We run it for you and keep you productive.

Now you can use that function from anywhere: From the terminal, periodically with a cron, add it to an AI agent as skill, use it through an MCP (not released yet), through Siri shortcuts, share it with your friends and so on.

Say you want to have an agent or function that gets the weather and sends it through Telegram: You can either quickly generate 2 functions through the AI function generator that get the weather ("I want a function that gets the weather for Tokyo") and another one for sending a message on telegram, or you can use what's already available (such as https://microfn.dev/david/getweathertokyo). Equipping them to an agent works like in a video game - each function is a new "skill" or "tool" the agent can use, and if someone else already has some cool skills, you can fork them without needint to re-implement everything from scratch.

So like a toolbox full of small composable hammers and tools that can be used across different scenarios and places, to be plugged into existing workflows, automation or to even be used in autonomous agents and through MCP.

Again, super heavy in development and not really a 1.0 yet, more like an early alpha, but wanted to share here anyway. Feedback greatly appreciated!

Thanks :)

Lots of small stuff like bots and scripts to automatically rename files that I use locally every single day

Then things like:

“Fix My Japanese” - uses LLM to correct Japanese grammar (built with Elixir LiveView): https://fixmyjapanese.com

It has different “Senseis” that are effectively different LLMs, each with slightly different style. One is Claude, one is ChatGPT.

Or a slack bot that summarizes long threads:

https://github.com/dvcrn/slack-thread-summarizer

Here’s mine :) https://david.coffee/

I blog about random bits and blobs in tech. Sometimes a review, sometimes trying out something new. Wanted to try and keep it interesting and not too fixated on one category.

Last post is a mini review on a travel router, and if you need one - https://david.coffee/the-case-for-a-travel-router/

Or going through the process of getting custom molded earplugs done - https://david.coffee/my-custom-molded-attenuating-earplugs/

Or using Elixir to build a distributed ChatGPT CLI - https://david.coffee/mini-chatgpt-in-elixir-and-genserver/

Not as active as I wished

Heh, I wrote one too (in Elixir + LiveView) - https://github.com/dvcrn/chatgpt-ui

Background was that we wanted to explore providing access to ChatGPT to employees at $company, but restrict access with Google OAuth using company email, and use the company OpenAI API key on the back. So I hacked together something quick that matches our requirements and we can self-host.

funny timing, just yesterday I finished a little app I was hacking on and needed a somewhat decent looking logo that was blocking the release. Instead of trying my luck in sketch and doodling around, I went to DALL E, and with my first prompt was able to generate better logos than I could have drawn. I was immediately unblocked and super happy with the results

It’s just amazing that non design people like me can just conjure up decent looking, and usable stuff with AI. I will definitely use DALL E much more going forward for creative work

The logos are a bit noisy and need redrawing in a proper vector tool but its a great starting point to try out different ideas immediately

(The results: https://twitter.com/dvcrn/status/1578710631838289922)

Shameless plug for my CLI for creating MaskedEmails that is using these APIs (since beta actually) - https://github.com/dvcrn/maskedemail-cli

If you're into domain/service-specific email addresses, give it a go!

I keep IPFS companion turned on constantly but when I hit a site that's getting loaded through IPFS it often takes so long that I end up turning IPFS off so it just fetches it from the central server

Small composable packages aren’t a bad thing IMO. It’s nice to pull things together how you want without having to reimplement the same logic multiple times. Just encapsulate smaller bits of useful code into their own mini packages

Like if there’s some string manipulation thing I need, instead of copy pasting some snippet, I can pull in the micro package that already does this

Even getting around Activation Lock on a stolen iPhone is probably a lot of hassle unless you know a guy who knows a guy who can unlock it for you

IPNS is so slow that using it for anything just makes for a very unpleasant experience

I went down a similar hole with a UniFi Dream Machine.

udm-utilities [0] basically allows you to run all kinds of stuff on it through podman.

Went from trying to teach it to mimic my ISPs router to get internet working, to banging my head against IPv6 prefix delegation, to now running adguard, homebridge and a bunch of other things across different VLANs on it.

All in all, I am happy with the result, and happier that I got dragged out of my progrmaming bubble to learn proper networking with IPv6.

[0]: https://github.com/boostchicken/udm-utilities

If that doesn’t show how well they’ve hidden the IP7 self-hosted version behind dark patterns! A loyal user had no idea it existed and stayed on 1P6 because of it.

You have to upgrade from within the IP7 app but only if you downloaded from their site, not appstore.

I fully agree. Been a standalone user for years and a coworker asked me recently how I got the standalone license because he didn’t think it existed anymore.

Even with me knowing it exists, I wasn’t able to find it on their site to send him. (Hint: you have to upgrade within the app, but only if you downloaded from their website, and only if no 1p account or trial is present)

Add other dark patterns like the extension being 1PX only by default and doesn't work with standalone. You have to cram through their website to find the legacy extension and even that isn’t straight forward. They tried very hard to hide all info of a standalone existing.

(Personal annoyance: locking new features like the redesigned autofill overlay to the subscription-only version even though the Safari extension fully supports it for standalone, but not the others.)

Also name clash with Triton, a binary analysis framework - https://github.com/JonathanSalwan/Triton

Luckily modern tech companies don't need those resumes anymore nowadays

Is there any way to make this the default in Safari?

Luckily day one is fully e2ee encrypted, otherwise I wouldn’t trust their self baked sync service a bit