FacelessJim
FacelessJim on Hacker News
I can’t seem to understand if this is something that could also be used without agents. I see the appeal of having first support for agents but I’d also like something I can use myself like I use tmux, without agents.
If agents didn’t exist, would herdr provide a nice UX as a terminal multiplexer?
My work laptop has a touchscreen.
I use it so rarely that I keep forgetting it has one and every time I clean the screen with my fingers I get confused for a couple of seconds and then I remember.
If you spend some time working on cross platform code you will quickly realize that that choice is actually the right one. The NT API is actually very close in abstraction to Unix and allows for much less ad hoc code to handle windows specifics than using Win32 API (which is an abomination).
The zig windows NT implementations are very well done and I actually use them as reference when dealing with windows IO.
And the thing that maddens me the most is that it has a critical mass where it’s basically the default starting language and most people never really move from there. And so we’re stuck with this grotesque abomination that somehow keeps on rolling. The amount of money that was poured into python to make it barely bearable is probably the GDP of a small nation.
Stated in the article with the title that clearly seems to suggest that it’s thanks to the drug itself.
Weight-loss drugs just seem to be the panacea for everything. But that’s because they treat the same underlaying issue. Being fat. But they’re sold as if all these issues were not related to each other.
I’ve jumped between mimo and ds quite a bit lately. Mimo seems to be slightly better in terms of what it can achieve in terms of end results. But it gets there very slowly, and in a super convoluted way. Sometimes it’s almost frustrating to read its reasoning. Also I’ve noticed that it tends to not use tools in the harness as much as other models.
I usually default to ds, and if it gets stuck try mimo but usually just for fire and forget tasks. After a bit I come back and see what it did.
>The same program translated to normalized Malbolge for *clarity*
The audacity
Oh yeah absolutely. One of my favourite ways to interact with agents is to spin up an interactive common session where both me and it can run commands in a shared environment. You can ask the agent to setup a MWE for you to play with and further explore in the REPL for example.
Depends a bit. More traditional tools like static analysis/Debuggers/full fledged IDEs are somewhat lacking compared to your standard static programming language. Although there’s very good progress being made with JETLS on the static analysis part, and the VSCode extension is very mature.
But, on the other hand, you rarely need those kind of tools with Julia.
The REPL+Revise in Julia is most often all you need.
If you really want to jump into running code debugger style you have Infiltrator.jl
And in the year of our lord 2026, I’ll say that agents are very effective in debugging Julia, especially paired with persistent sessions/daemons like DaemonicCabal.jl or JuliaDaemon.jl.
As I like to say, AIs are very good at “drawing the rest of the owl”
Been using it daily for years now, even at work.
Nowadays you can just compile as a library that you can share with other languages.
As a language it’s very pluggable (both directions). I think it’s one the best languages in terms of
interop out there at the moment.
Love pi. I tried to run some local models and pi was the only one that actually worked decently because it didn’t have a gargantuan system prompt that would take minutes to prefill on my scrawny ass laptop.
Been running it almost barebones vanilla for a couple of months. Just a bunch of basic extensions and some skills.
Now, if only they could fix the very annoying bug of the history jumping back at the beginning if I am not a the end while the model is reasoning that would great.
Julia has a very good threading story. Task based, M:N, a lot of schedulers, structured concurrency, distributed. Sanest atomics I’ve seen. All in the stdlib.
> Their primary product, the Zed editor, is unusable for me and others due to it mismanaging file syncs on disk - when external edits happen, the editor retains stale state unless you close and re-open the specific file (Not even an editor reopen syncs it). There is a significant risk of your changes being silently overwritten or conflicted.
But isn’t Zed written in Rust?
Have they heard of our lord and saviour “mapreduce”?
x = mapreduce(f, r, arr, init)
equivalent to
x=init
for e in arr
r(x, f(e))
end
Of course, if r is ever something different than a simple operator, slap yourself. But otherwise it’s an absurdly powerful construct.
That’s it. I’m rewriting my whole stack with this.
I’ve read it the same way. Definitely a double edged slogan.
I wonder how these kinds of papers get funding at all…
Terrific presentation. But I have a comment:
His dismissal of the argument Knuth makes regarding the hot loops could have been explored a bit better. I found it weird he didn’t mention the difference of types of programs of then vs now. Even today, in scientific code it is still absolutely the case a lot of the time that a huge chunk of the runtime comes from a single very very hot loop. It might be hidden in a library, but it’s there.
Instead he focuses only on “program size”.
Knuth samples where very small FORTRAN programs (compared to today’s standards). Today’s program are bigger but the fundamental number crunching primitive of “let’s compute stuff in a loop” remains. It’s just buried under a pile of extra cruft (data loading, parallelism, dispatching etc).
Now we just deal with a lot more programs that are of a whole different class compared to what they where doing with computers in the 70s. We have much more I/O involved. And hot loops don’t like being I/O bound.
We were encountering a panic in the lib and could not really figure out why it was firing. The project kind of stalled due to lack of time and funding anyway unfortunately.
I am running Ornith 1.5 Q4 on my work issued laptop which surprisingly has 40gb of RAM and 20GB of “unified” VRAM.
I am getting 50t/s of prefill and 5-6t/s of inference.
You can’t get crazy with it, but it’s pretty nice to just let it work away at simpler prompts overnight or during lunch break or while I am working on other things.
Being able to literally a 30gb blob and then being able to talk with it while running on your machine it’s a different kind of magic compared to a far away magic in the cloud.
Very nice!
I’d be curious to see if there are words that didn’t show a spike in utilization.
So basically all those words that were used before and are still being used today by LLMs and humans alike!
Small OT:
> Maybe I should document what I did!
Please do!
Me and a bunch of friends worked on a project that used diamond-types as the backing CRDT engine. It does indeed go brrrr. But damn, it took way too long to reconstruct what it was doing (we needed some more fine grained knobs, so we were playing with the frontier directly). We eventually moved out to something a bit better documented, which was a real pity. I really liked the general architecture and simplicity (of the text-only based version at least).
Been using it for a year or so on my main box. Never had any kind of issue. Snapshots saved my ass a couple of times. All in all it’s been pretty boring (in a good way)
I really like the approach Julia is taking. The std libs are their own packages with their own versions. You can then build your own “standard library” by compiling a sysimage that freezes the versions (you can add third party packages as well).
Practically speaking the standard library is just meant as “what’s included in the default sysimage”.
This allows to have different standard libs for different use cases. Think of Linux distributions in a sense. There are already a couple of alternative “stdlibs” out there for different focuses.
The Applications folder itself is the equivalent. You can select an app and just press delete.
Been using the great and free AppCleaner[1] since I have memory. It's so good I just forget it's there.
It autodetects when you delete an app from the Applications folder runs a quick scan and suggests which other files you might want to delete (So you might save savedata or settings if needed)
[1]https://freemacsoft.net/appcleaner/
Here’s an even wilder take: to support the effort of someone that gave us an incredible font that is now being copied. Crazy right?