You can get pretty decent initial results if you explicitly tell them to first make a detailed description with exact coordinates and then feed the description back into them to build the SVG.

I do wonder if the compression step makes sense at this layer instead of the filesystem layer.

Interesting take. I'm using btrfs (instead of ext4) with compression enabled (using zstd), so most of the files are compressed "transparently" - the files appear as normal files to the applications, but on disk it is compressed, and the application don't need to do the compress/decompress.

> The SOTA isn't capable of using a code diff as a jumping off point.

Not a jumping off point, but I'm having pretty great results on a complicated fork on a big project with a `git diff main..fork > main.diff`, then load in the specs I keep, and tell it to review the diff in chunks while updating a ./review.md

It's solving a problem I created myself by not reviewing some commits well enough, but it's surprisingly effective at picking up interactions spread out over multiple commits that might have slipped through regardless.

I'd never heard of detour. That's a pretty cool hack.

they were prominent in game hacking 2005ish windows

made hooking into game code much easier than before

Aren't all DLLs on the Windows platform compiled with an unusual instruction at the start of each function? This makes it possible to somehow hot patch the DLL after it is already in memory

I believe you're thinking of the x86 Hotpatching hook[1], which doesn't exist on x86-64[2] (in the same form, it uses a x86-64 safe one).

[1] https://devblogs.microsoft.com/oldnewthing/20110921-00/?p=95...

[2] https://devblogs.microsoft.com/oldnewthing/20221109-00/?p=10...

yes, that's it. Thanks for clarifying

It's as if they choose the word bankruptcy for a reason.

I'm almost certain their code is a dumpster fire.

As for your 200$/mo sub. Dont buy it. If you read the fine print, their 20x usage is _per 5h session_, not overall usage.

Take 2x 100$ if you're hitting the limit.

> Buried in the chaos are sketches of future agent orchestration patterns

I'm not sure if there are that many. We need to be vigilant of "it feels useful & powerful", because it's so easy to feel that way.

When I write complex plans, I can tell Claude to spawn agents for each task and I can successfully 1-shot a 30-60 minute implementation.

I've toyed with more complicated patterns, but unlike this speculative fiction, I did need my result both simple and working.

A couple of times now I've had to spend a lot of hours trying to unfuck a design i let slip through. The kind where 1 agent injects some duplicate code/architecture pattern into the system that's correct enough not to be flagged, but wrong enough to forever trip up every subsequent fresh agents that stumble on it.

I tell people my job now is to kick these things every 15 minutes. Its a kinda joke kinda not. But they definitely need kicking. Without, the decoherence of a non-trivial project is too high, and you still need time to know; where and how to kick.

I'm not sure what I'd need to be convinced a higher level of orchestration can do that. I do like to try new things. But my spider-sense is telling me this is a Collatz-conjecture-esque dead-end. People get the feeling of making giant leaps of progress, which anybody using these things should be familiar with by now, but something valuable is always just out of reach with the tools we currently have.

There are some big gains by guiding agents/users to use more sub agents with a clean context - perhaps with some more knobs - but I'd advise against acting under the assumption using grander orchestration tools will inevitably have a positive ROI.

Half my visits to HN are to check out a comment that explains the right uv inline dep syntax

   #!/usr/bin/env -S uv run --script
   # /// script
   # dependencies = [
   #   "requests<3",
   #   "rich",
   # ]
   # ///
   import requests, rich
   # ... script goes here`
   

so i can tell claude to write a self contained script it can later use.

Huh. I just tell Claude “write a self contained uv script” and it does that fine by itself.

I suspect the author was trying to put into words why their technically correct world view is better, but he spends his opening arguing semantics (ineffectually, as apparent) instead of meeting the 'wrong' people where they are and explaining why his semantics are an improvement.

Competency crisis is not limited to just the audience.

The number of Trump apologists lunatics who do not seem to understand what MAD was about is staggering.

Industrial scale warfare isn't some secret forgotten by accident.

The current American power-trip fantasy delusion is rightfully scaring the shit out of people, and the scary thing is the people who aren't scared.

It's reaching the point that I think the best thing is for Germany to detonate a nuke between the US and Greenland just to wake up the idiots who think it would be unreasonably difficult.

--

Edit: I see people are misunderstanding me as saying they should use the US bombs stationed there. I'm saying they should build their own - to have people remember that It's not really that hard if you have a functioning industrial sector.

Don’t let your hatred blind you to the ground we all stand on.

As pointed out you have built your worldview of drastically misunderstood table stakes.

I do agree Europe should become first mover but they are stuck in a world where they were a dependent and weakened non player for so long now they forgot how.

Germany is a non-nuclear-weapon state. Our bombs are there yes, but if you use one of our bombs without our approval there will be hell to pay. An invasion of Greenland will be all but guaranteed. Whether Germany will retain its military the next day is questionable.

It is ok for Germany to detonate nukes on someone who attacked NATO. The approval of the aggressor is not necessary.

Germany will be glass if they tried. Berlin will glow in the dark. They wouldn't even consider it in government. Their planes wouldn't make it off the ground.

I see you don't want to understand my point.

Why exactly do you think Germany is a non-nuclear weapon state?

Because we muzzled the wolf.