rhgraysonii
rhgraysonii on Hacker News
Posted by
rhgraysonii on Saturday October 10, 2026 @11:32AM
from the show-hn dept.
https://bobbby.online/piet/tiles
Each tile is a Piet program that prints a word.Each generation, every tile runs.
After, its label shows what it printed.The original was a Piet program, compiled from Temper by a backend I wrote, playing Life on another Piet program:3 hours, 1.27 billion steps. Generation 0 printed "Piet!".
Posted by
rhgraysonii on Friday October 09, 2026 @07:50AM
from the show-hn dept.
https://bobbby.online/piet
I have been playing around with writing compiler backends for https://temperlang.dev and I made this last night after building one for Piet, and thought it was a nice little art project. The page is written in Blimp, a language I developed for fun. https://blimp.bobbby.online
Not how it goes in practice at all, would encourage you to actually try it out.
Curious how this compares to my own tool,
https://deciduous.devI will have to give it a run-through today.
I haven't used Jev yet so this should be interesting. I'd be interested to see if any Deciduous users have opinions, too.
Posted by
rhgraysonii on Thursday September 17, 2026 @10:24AM
from the show-hn dept.
https://marginalia.bobbby.online/cases
I made this as a means to browse through documents that are highly linked and referential in general, and thought it would be interesting to apply it to court cases. So this has the opinion, the arguments per person, the dissents, and concurrences all mapped out.It also is linked to an LLM you can chat about them with if you click a linkage and it has a DAG of the knowledge of all the content...
Posted by
rhgraysonii on Monday September 14, 2026 @08:22PM
from the bobbby.online dept.
If you could post an issue if you still have the error around that would be awesome.
Yes that is exactly what this does.
LLMFit tells you what can run on something. I built something quite similar to their search into Shoehorn now.
Posted by
rhgraysonii on Tuesday August 18, 2026 @10:29AM
from the show-hn dept.
https://notactuallytreyanastasio.github.io/shoehorn/
Working on Mac, Linux, and Windows now. I include a simple GUI to find new models and get things built and set up. It is working quite well across a few models for me. The GitHub README and DESIGN.md files go into detail of the how/why and it's working remarkably well so far. https://github.com/notactuallytreyanastasio/shoehorn
Posted by
rhgraysonii on Friday August 14, 2026 @10:43AM
from the show-hn dept.
https://github.com/notactuallytreyanastasio/shoehorn
I made this after seeing someone posit the idea online yesterday over lunch then spent some time refining it. So far it's pretty impressive IMO! Right now I am running Qwen3-30B-A3B on my 24gb unified memory m4 MacBook Pro at 50 tok/sec and this should definitely not be working for such a large model on my middling hardware.Things are detailed in the README to get up and running and DESIGN.md...
A really great place to reach for this is Elixir/Phoenix now that the set theoretic type system is in place with LiveView. I have been doing some pretty large/complex codebases gradually working towards fully integrating working this way for the past 5 years and it has been great.
Thanks! I was thinking of doing the 128gb to have some future proofing. I figure at this point, it's akin to a mechanic keeping great tools around, when it comes to having this sort of homelab and exposing it for your own uses. And great practice for building the next era of user facing computing that will be around as this proliferates.
I have been having pretty good success with Qwen 3.5 9B for "nontrivial but not challenging work all things considered" -- it runs great on my 24gb unified memory m4 pro MacBook Pro. What do the baseline specs look like Mac-wise for getting this model to run? Am I looking at a 96gb? 128? 256?
Posted by
rhgraysonii on Friday June 12, 2026 @10:55AM
from the show-hn dept.
https://soldat.bobbby.online/
I started off with a simple goal: port the game Soldat to Typescript. I ended up not only with the game, but with a full system to train AI bots to play my own game, building a neural net to train new bot AIs from tens of thousands of simulated matches with different strategies. It also runs live all the time on my website and has a news dashboard and you can replay any game exactly. It all was...
I use deciduous every day while working with LLMs to create more of my own tools/projects. It is a living memory for agents stored in a simple, portable manner.
https://deciduous.dev
It might be helpful to rotate the books on the frontpage so that that you can read them by binding without tilting your head.
I regularly have agents communicate with each other this way using my tools Deciduous (
https://deciduous.dev). It keeps all decisions in a DAG and the other agents, when configured, read from it constantly and use it to inform their new decisions. Extra entries in the same space from another agent come to light and they can begin to work together like this.
Valid, but you lose the lived history that comes with the audit log of it being actual review back and forth and CI runs vs lost to a developers machine and only a relic in the commit log. I can see both sides, though.
Posted by
rhgraysonii on Wednesday May 27, 2026 @10:14AM
from the show-hn dept.
https://bobbby.online/2048
I got bored of normal 2048 so I made this. It allows you to enter "blitz mode" with a set time per move and an ability to scale the board up if you want to play longer games.It allows 2 3 or 5 second turns, and can play up to 8, 10, or 12 size boards.It is nothing too complicated or complex but the code is here if you want to see. I made this while on vacation for a friend today with Claude's...
I wonder what he is up to. I have 2 _why inspired tattoos after he did so much to influence my entire philosophy and style of programming. What a unique character, who happened to pop up at a very formative time for me. Thanks for all the nice stuff and ideas, _why.
Jason’s work output is so prolific. Over the past 4-5 years he’s digitized the lifetime collection of magnetic media I acquired in a series of odd interesting events. So much slice of life nyc and weird cool music stuff that would have never been seen otherwise. Over 1300 tapes! All here
https://archive.org/details/markpinesHe is also just an absolutely delightful person to hang out with. Textfiles was one of the first websites I ever visited and getting to do this was a meet your heroes thing that actually went very nicely.
Finally, I can reasonably get something truly high contrast and not just close to it as the current offerings are. This is a little thing, but Zed continues to keep getting so many things right that it has gone from “interesting” to “my preferred editor” after 15 years in vim. The git “follow mode” has been especially great transitioning into heavy usage of LLMs in development. Happy to see the team continues to just get more little things right.
Temper is a programming language that compiles to many other programming languages. This interview with the creator and core team is pretty interesting, diving into how the language can compile to 6 other languages right now and is growing. Check it out:
https://temperlang.devDisclaimer: I am an advisor to the company around the language, Temper Systems
Posted by
rhgraysonii on Wednesday May 06, 2026 @01:16PM
from the youtube.com dept.
11 minutes elapsed between the comments. There is going to be some actual time before a report and the status page being live in a breaking system.
Posted by
rhgraysonii on Sunday March 15, 2026 @10:25AM
from the github.com dept.
I think the decisions it made along the way are worth tracking. And it’s got some useful side effects with regard to actually going through the programming and architecture process. I made a tool that really helps with this and finds a pretty portable middle ground that can be used by one person or a team too, it’s flexible.
https://deciduous.dev/
I have built this for my own use after extracting it from a project. It originally, for me, was about keeping logs of a bunch of complex math stuff I was doing in a project and cross referencing concepts and what I'd tried/not tried etc. Once I extracted it, the "archaeology" features became key after talking with users. Now the Q&A interface from the local app and the archaeology are the most popular pieces, but it works very well to make better decisions when documenting things as it goes with the git history combed through already. It can also attach documents or other metadata to the nodes to track things like PRDs, notion write-ups, etc. Really anything the LLM can have access to.