mikodin

Wow, these are beautiful! Are you open to others using these in applications? There is no license in the repo so I am unsure :)

This is also where TEE's with attestation come in - https://redpill.ai/ for example (god I hate their name, but I am a fan of the product)

What are the models? I am super curious in these as well

Yup - this! A big ol' experiment, we shall see how it goes. I'd be curious (if they exist) on some larger / older orgs with internet scale customer bases that are full in on AI development with limited human reading of it to see how they fare.

Phweww - 100% agree and am seeing that with my app as well! It's been one of the most joyful pieces of building it, is that I am really making something for myself and have been using it and continually adding the things that I want.

This is the process that nothing can do for us.

As I've been vibe coding a side project, I've been curious on just how much cruft and slop the agents are training on now. A part of me feels like I should actually have it be in a private repo.

Greetings friends! I have been joyfully working on a native iOS app called Sanctum. I really built this for myself and use it multiple times a day (https://apps.apple.com/us/app/sanctum-the-voice-journal/id67...)

Sanctum is a voice journal, think Obsidian but for voice notes. I am really honing in on data sovereignty, privacy, 1 click to record and self organization of notes / ideas.

While this isn't anything revolutionary, or technically difficult, I do think I've landed on a form factor and stack that is in my opinion not served by current products. So much so that I just simply had to build it myself. Sanctum was born out of an Obsidian plugin that I built and have been maintaining for about 2 years called Scribe and it's been a wonderful way to really hone in on a more full fledged agentic development process for a full stack experience.

The stack is simple

  - For transcription I am using AssemblyAI - they have solid terms, 24hr retention and no training

  - LLM inference is running inside a TEE using redpill.ai, it's slow af but as private as I could find.

  - For cloud backup I am using full E2E encryption with Backblaze for storage

  - Endpoints and the like are AWS lambdas, DynamoDB for billing storage, Supabase for auth

I (yes, fully me, not AI) have been doing a lot of writing on the process, we are flooded with these sorts of post on HN, but if anyone is interested in reading, check it out! https://www.builtinspace.xyz/blog/begin-with-ethos.

Anyway, something I am most definitely curious on is if people are recording their thoughts, what they are using (either a cobbled together solution or a product) and what value they feel they've been getting from it!

Same boat

Does anyone have a solution for iOS development?

I was all in on sandboxes and safehouse for my agents but the moment I got into iOS development it felt like my hand was forced to just run Claude / codex / pi directly on my machine because nothing else could do the dev loop.

It’s been a painful reality for me, I’m going against core pieces of how I feel I should be interacting with agent harnesses and yet, I need to get the work done so

I am super curious how much in your opinion the extra prompting is useful?

>often harnesses also mention in their system prompt locations of markdown files that the model can consult if the model thinks they might help >that hint alone as part of the system prompt can be strong enough to make the model read in more tokens than would have been necessary

I purposefully do this as I imagine it is useful. In my project I am seeing solid adherence to norms and a deep capacity to iterate on completed features. Essentially for each feature I have the model make a {featureName}.AGENTS.md at the root folder of the feature, where it maintains what is going on.

I am moving between Claude Code and Codex atm, but I began this pattern when pi + kimi 2.6 was my main driver.

I think particularly for iOS development. I was all in on sandboxed approaches...until I went to build an app, and now unfortunately convenience won

Thank you for this project - I am excited to check it out!

My current agentic workflow is having a github repo that is a workspace and essentially a single obsidian vault over it called agents. I modify with Claude code (or other harness), check diffs in...VSCode and read it in...Obsidian.

It's separate from my actual personal Obsidian vault (that I don't send to any AI providers), and is only for agents. It's been really nice on all sorts of varied projects and for performing web research. I also have a bun monorepo setup in the root with varied tools for search, fetching individual websites, setting up folder structures - etc.

But essentially, in my experience, the moment you tell the model that it's in an Obsidian Vault - magic happens.

I am so curious how this will play in with it all and am hoping this will improve my workflow!

Gah - this is unfortunate. This will have me quit as well - I wonder when they will begin to enforce this on the Claude Code front. I remember when OpenAI tried (maybe they still are?) putting this in for GPT 5 and this had me switch from them to Anthropic.

I'm curious what part of the charts would data centers fall under?

I'm assuming it would be under the Energy emissions category, but I didn't find anything particular around data centers or "technology" or "internet" or something like that.

Would it fall under "Electricity and heat"? Or just general "Buildings"? or "Commercial buildings"? Or am I way off base?

https://github.com/charmbracelet/crush (Haven't used it, but also hit the 404 and wanted to see it)

> For example if AI generates 2x of a utility function that does the same thing, yes that is not an ideal, but is also fairly minor in terms of tech debt. I think as long as all behaviors introduced by new code are comprehensively tested, it becomes less significant that there can be some level of code duplication.

We still run into the same issues that this brings about in the first place, AI or no AI. When requirements change will it update both functions? If it is rewriting them because it didn't see it existed in the first place, probably not. And there will likely be slight variations in function / components names, so it wouldn't be a clean grep to make the changes.

It may not impact velocity or stability in the exact moment, but in 6 months or a year - it likely will, the classic trope of tech debt.

I have no solution for this, it's definitely a tricky balance and one that we've been struggling with human written code since the dawn.

Unclear but I will say upon opening the site I was sparked with joy and excitement to use them

I was under this impression as well - I'd love to hear from someone who's deeper in the know about this!

I also expected it to be more art forward because of "canvas". Visual workspace draws a clear picture for me.

I am doing something very similar to this. I think the workspace _being_ the memory is the way. It's also enabled the workspace to be completely model and harness agnostic.

On top of that, I actually have it as an Obsidian vault, and I have the llm themselves use Obsidian markdown for the frontmatter and knowledge graph linking. It makes it very easy for me to navigate the data and interact in a way that is deeply enjoyable, and it also helps the model navigate the files.

Piggybacking on this - I think it well equips us for a future when local models are stronger. I for one am grateful for efforts like these

I've been using PI for this - just switch to "oh my pi" and am liking it!

Honestly, it's been a dream, I have it running in a docker-sandbox with access to a single git repo (not hosted) that I am using for varied things with my business.

Try it out, it's super easy to setup. If you use docker sandbox, you can just follow what is necessary for claude, spin up the sandbox, exit out, exec into it with bash and switch to Pi.

I was on a plane two weeks ago, and this girl - likely 12 was trying to get the screen in the seat to work by tapping it. Her Mom (likely in her 30s) started doing the same thing, both confused.

I gave it a beat and then reached over and pushed the button to pop out the remote control for them. It was a cute head smack moment for the Mom and the daughter didn’t know what to do with the remote for a solid few seconds.

This happens to me as well when I’m in a public bathroom without a sensor, and I wave my hands underneath obliviously for a few moments.

Life is funny

I would say yes.

The reality is that the money being thrown = the time of humans. I guess compute as well, but in terms of people doing innovation - openly published things are the same thing, minus the money.

What always came to mind for me is an “engine wiring harness”. It’s responsible for getting power and data to all the right places without having to manually route cables around the engine / car.

If you google an image of it, maybe it’ll make sense

I've found immense value in this, am already doing it with Pi(https://github.com/badlogic/pi-mono) and it's very easy to replicate

Seconding this—I had to wait a little bit to download it and play around and have some fun with it. I didn't mind.

What I appreciate the most about this string of comments (from OP) is that digging into "doing it for fun", hosting on your own machine, wanting simplicity for you as the maintainer and builder. This has been a big focus for me over a number of years, and it leads to things being not efficient, or scalable or even usable by others—but they bring me joy and that is more than enough for most things.

The reality is that there are of course ways to make this more efficient AND it simply doesn't need to be.

Good job on making something that people are clearly interested in, it brought me some joy clicking around and learning some things.

If you want it to be more than just this, of course you'll have to make it faster or have it be a different interface—installable offline typa thing so we can expect a bundle download and be fine with waiting. For example I can see this as a native app being kinda nice.

If you don't want it to be more than this, that's okay too.

Regardless, well done

I know you did this in a weekend, but it would be super nice to get some screenshots, or a video into what makes this different.

I also don't know what the "river/awesome philosophy" is, so therefore I don't know what this WM does that makes it different than something like Rectangle for example.

And truth be told, I'm not going to look it up. I am only adding this comment because I'm sure there will be a ton of other people that fall into the same category as me.

Good luck though, super cool to see that you built this in a weekend!

I essentially do a 1 click deployment for my personal site with Cloudflare.

I don't want to deal with the cloud infra for my personal site.

I could, I've done it in corporate, I've done it for my startup 2 years ago. But I'm rusty, I don't know what the latest people are using for configuration, etc.

Because there is 1 click with CF or Vercel and I don't have to think about it—I don't. If they increase their price it likely wouldn't be enough friction for me dust off the rust.

I think this is the relation. I'm not locked in, it's just HTML pages, but I am through my own habit energy, tech changing, and what I want to put effort into, which is not infra and serving my site.

Yeah I see the benefit right off the bat, this is a direct head to Vercel and NextJS.

With that said, I have no idea on the market share or profitability of any of that or Cloudflare vs Vercel.

Also perhaps the rails that will be put in place for seamless 1 click Astro deploy will continue to push them forward with other technologies as well, so it's not just about Astro.

I do feel that fear as well, is this an unnecessary distraction for CloudFlare? Time will tell.