Of all the things LLMs do, one of the most fun is that they help you get over that hump of activation energy for an idea. We all have limited spare time, and going from "hey this might be cool" to a working prototype in minutes instead of days is intoxicating.
Much like my own heaving ~/prototypes folder, there is an avalanche of small projects other people are building in their own spare time (with LLMs), and there is a subsequent avalanche of "check out my cool project" posts. This is cool! However, unfortunately, almost universally, there is very little follow through. If you come back to those projects after a month, most are abandoned.
The creators of the ones that tend to last, at least in my brief experience so far, _do_ write useful blog posts by hand, or put a bit of human effort into sharing what they've built. I guess when I encounter someone sharing their work by way of blog post, it feels to me like they don't really care about actually sharing that work.
Also -- and this is much more a me thing -- I'm just fucking tired of reading Claude's writing. I have to work with Claude most days, and seeing it take over the whole internet is suffocating. Inflicting more of it on others just sucks.
I am bone tired of slop. This looks like a useful thing to build (the cameras in existing closed source robo vacuums creep me out), but when people don't even write their announcement blog post by hand it gives me zero confidence in the project getting anywhere meaningful.
Perhaps not the place to share this, but it's depressing. I hope this proves me wrong.
A lot of unit conversions are just built into Kagi (and Google!). "Searching" for "10nzd in usd" gives me a price, "10kg in lb" gives me a converted unit, etc.
The harness clamps what the agent can do. `bash` allows full code execution; a dedicated `mvn` tool might only allow `mvn compile` but not `mvn spring-boot:run`. You could probably implement this with an `allow` list attached to your `bash` tool, but by doing it this way, you can enhance the outputs or perform mandatory checks too.
For instance, Claude likes to run little Python scripts; reviewing them is tedious. Removing `bash` and adding a `python` tool would allow the harness to pre-review and grep for common harmful patterns, or run the `python` script in a `krunvm` or `muvm` to isolate it, etc. This review/isolation would be handled programatically as it's part of the harness; leaving the agent to choose what to do as a skill means the agent can conveniently forget to enforce its own checks.
Mine hasn't actually arrived yet! I'm still waiting for it in the mail. I don't think I'll tweak that much, all I really want to do is flash the published open source firmware, attach it to my tailnet and use it to control a little server I keep in the crawl space under the house (because crawling under there whenever it needs a reboot + entering disk encryption keys is distinctly unpleasant).
Possibly, I'm not really interested in learning Zig though (or learning to embed it in Rust). I'm sure that'd be a cool project for someone else to try :).
Unfamiliarity and I believe it requires a compile step. I’m at least familiar with Typescript and Deno so being able to embed them was an appealing idea :)
Yeah, it's been a bit of a dead end. I didn't want the heavy runtime but felt it was worth disproving after experimenting rather than ruling out off the bat. Even before getting it running, the dependency list alone was pretty discouraging, especially given the storm of supply chain attacks these days.
Rhai looks nice, I'll take a look, thanks! And good luck with Zerostack.
I've been trying to use `Deno` underneath `Rust` so that the tools can still be written in Typescript and thus self-mutated without the compilation step (but I can still try to do clever things with V8 Isolates or similar). It's been an ugly experiment so far; I'm vaguely thinking a simpler model would be to just define a binary "API" and run tools by exec-ing binaries.
Yes, that aggravates me too. I noted recently, Claude had a phase where it would write little one-off Python scripts to aid it in analysis -- which is super useful! But when it's written ten scripts in a row, each of which I've had to review and each of which I've had to approve by hand, it gets pretty annoying. If I could bless it with "if it only uses these Python libraries, pre-approve the script", that would've made life a lot simpler, but of course, that's not possible. Sigh.
Thanks, I've been tooling away in my spare time on my own version of this -- both to get a deeper understanding of agents (everyone suggests writing your own) and to help learn Rust. I'd like to retain `pi`'s configurability though, the ability to self-mutate and generate new tools is incredibly useful, particularly because I don't think any of these things should have access to arbitrary code execution through `bash` (of course, if they have access to, say, `edit` and `cargo run` they still have arbitrary code exec, but...) (so I tend to generate tools on the fly when I encounter something the no-bash agent needs to do).
I feel this a lot too these days. The only place the fun seems to remain for me is in Linux and in devices out of China, that you can hack and experiment with — like the Anbernic consoles, or the Xteink X4, or the little mp3 player DAP things, or the Sipeed NanoKVM devices, or the Supernote. The Steam Deck probably sits in this niche too, now I think about it.
Alongside the purpose they serve, all of them can be trivially broken into and re-tooled however you like — and for me at least, that’s where a lot of fun lies in computers. When it comes to mainline desktops now, everything is incredibly expensive and deflating.
The harnesses we have are almost stunningly incomplete IMHO. I've been trying `pi` recently, and quite like that it comes with a minimal set of tools by default -- and that I can easily override or replace the ones that it ships.
I've only just started working with it, but clamping `read/write/edit` to only allow editing files in the current directory, banning `bash` and mandating I write tools for the specific commands I want it to execute, has made me much happier. Running Claude inside a VM or similar to sandbox it is nuclear overkill; I've always been surprised that that's seemed like the state of the art.
With a better harness, the model can't choose to rename things with search and replace; if it wants to rename things, it _must_ call the LSP to do it. If it's going to write code, as you suggest, the harness _forces_ linting/formatting to run.
(Reading my own comment back, I am worried that the fucking AI writing style is infecting me :()
If you want an e-ink type screen, the Supernotes (or Remarkables, or Viwoods) are all very good at this. Personally I hate trying to read things on iPads.
> A good way to think of it is that jj new is an empty git staging area. There's still a `jj commit` command that allows you to desc then jj new.
This always made me feel uncomfy using `jj`. Something that I didn't realise for a while is that `jj` automatically cleans up/garbage collects empty commits. I don't write as much code as I used to, but I still have to interact with, debug and test our product a _lot_ in order to support other engineers, so my workflow was effectively:
git checkout master
git fetch
git rebase # can be just git pull but I've always preferred doing this independently
_work_/investigate
git checkout HEAD ./the-project # cleanup the things I changed while investigating
```
Running `jj new master@origin` felt odd because I was creating a commit, but... when I realised that those commits don't last, things felt better. When I then realised that if I made a change or two while investigating, that these were basically stashed for free, it actually improved my workflow. I don't often have to go back to them, but knowing that they're there has been nice!
> All of our expectations for control over our phones are completely out of whack compared to other computers.
I would, sadly, challenge this. If anything, our desktops and laptops are the exception now. Phones, TVs, game consoles, set top boxes, cars, Amazon echos, ebook readers, tablets, security cameras, autonomous devices like vacuum cleaners — when I think of the myriad devices we interact with that have a computer in them, they are all as stringently locked down as possible.
Much like my own heaving ~/prototypes folder, there is an avalanche of small projects other people are building in their own spare time (with LLMs), and there is a subsequent avalanche of "check out my cool project" posts. This is cool! However, unfortunately, almost universally, there is very little follow through. If you come back to those projects after a month, most are abandoned.
The creators of the ones that tend to last, at least in my brief experience so far, _do_ write useful blog posts by hand, or put a bit of human effort into sharing what they've built. I guess when I encounter someone sharing their work by way of blog post, it feels to me like they don't really care about actually sharing that work.
Also -- and this is much more a me thing -- I'm just fucking tired of reading Claude's writing. I have to work with Claude most days, and seeing it take over the whole internet is suffocating. Inflicting more of it on others just sucks.