News for hackers. Stuff that matters.
Re:When AI Builds Itself: Our progress toward recursive self... by chilipepperhott on Thursday June 04, 2026 @03:48PM (#48403708)
I find any and all claims like this ridiculous from a company who can't build a terminal application that uses less than a gigabyte of RAM.
Re:When AI Builds Itself: Our progress toward recursive self... by cpursley on Thursday June 04, 2026 @03:49PM (#48403723)
A came here just to write: Pretty please let it churn for a few nights and redo Claude Code in Rust. Because the harness is very very good as are their models, but that node thing is a hog for no good reason at all.
Re:When AI Builds Itself: Our progress toward recursive self... by jcarver on Thursday June 04, 2026 @04:14PM (#48404003)
I had similar thoughts and ended up writing my own open-source harness in Rust: https://aether-agent.io/ . It's rough around the edges, but I use it as my daily driver and I'm pretty happy with it.
Re:When AI Builds Itself: Our progress toward recursive self... by rytill on Thursday June 04, 2026 @04:35PM (#48404266)
I checked out your agent and it looks pretty well designed. Congrats on starting to share it with others!

One thing I noticed: "Your Tools: Aether agents get tools exclusively via MCP servers." "...Aether ships with 1st-party MCPs for file system operations..."

Can you share your thoughts on why you decided to use MCP as the core tool abstraction? I have heard many decry MCP as being context-wasteful. Is this not the case with your agent?

Re:When AI Builds Itself: Our progress toward recursive self... by jcarver on Thursday June 04, 2026 @04:53PM (#48404479)
Great question.

The MCP protocol has gotten a bad rap for wasting context due to most MCP clients dumping tool definitions directly into context, which is wasteful.

Aether doesn’t do that. It uses an opt-in "proxy" that puts MCP tool schemas on the filesystem so the agent can browse, search and load the tool schemas it needs progressively. As for motivation there's several advantages to taking a MCP 1st approach, including:

1. It allows Aether to be a truly blank slate agent as 0 tools are hardcoded into the core runtime.

2. It allows users to extend Aether using any language they want

3. MCP gives a standard way to deal with local+remote tools, progress notifications, permission prompts (e.g. ask the user to allow/deny a tool call), OAuth flows etc.

4. There's a big ecosystem of existing MCP servers users can connect to

But that's all optional, you can just as easily give Aether a single Bash tool and only use CLIs too.

Re:When AI Builds Itself: Our progress toward recursive self... by ale on Thursday June 04, 2026 @03:54PM (#48403784)
Incoming rust rewrite branch ready to merge: +1,009,257 -4,024
Re:When AI Builds Itself: Our progress toward recursive self... by canadiantim on Thursday June 04, 2026 @04:03PM (#48403888)
People already rebuilt Claude Code in Rust after the Claude Code leak, it's on github as claw code (and other variants)
Re:When AI Builds Itself: Our progress toward recursive self... by Lplololopo on Thursday June 04, 2026 @04:47PM (#48404409)
Really? Let me explain how bigger companies work:

They have different teams for different departments with different type of people.

So the team or teams responsible for writing the terminal application are different people than the researchers doing the learning.

This can lead to dimentral quality aspects.

Re:When AI Builds Itself: Our progress toward recursive self... by asdfman123 on Thursday June 04, 2026 @04:55PM (#48404511)
Developers can develop leaner applications, but they're usually not incentivized to.

Frankly, I love efficiency too, but I've hard to learn the hard way that what the market wants is features. Or at the very least, the executive team wants that.

Re:When AI Builds Itself: Our progress toward recursive self... by j2kun on Thursday June 04, 2026 @04:58PM (#48404538)
Their whole argument is that AI's added efficiency means they don't need to set aside valuable human time anymore. Why can't they just point Claude at Claude Code and ask it to reduce memory usage by 90%?
Re:When AI Builds Itself: Our progress toward recursive self... by asdfman123 on Thursday June 04, 2026 @05:29PM (#48404887)
You can do that. But I'm telling you, in tech (and enterprise shops I've worked at too) they don't care.

I'm using the internal Google tools and it's helping me write code much faster too, but it still takes time. I could make the CLI tool I work on faster, but no one cares except the end users, and their minor concerns have no impact on our internal politics.

At the end of the day you have to do what you're paid to do, unfortunately.

Re:When AI Builds Itself: Our progress toward recursive self... by fg137 on Thursday June 04, 2026 @05:59PM (#48405181)
In other words, performance is almost always an afterthought.
Re:When AI Builds Itself: Our progress toward recursive self... by asdfman123 on Thursday June 04, 2026 @06:11PM (#48405318)
Sure
Re:When AI Builds Itself: Our progress toward recursive self... by Garlef on Thursday June 04, 2026 @10:24PM (#48407217)
Make it work, make it nice, make it fast.
Re:When AI Builds Itself: Our progress toward recursive self... by jachee on Thursday June 04, 2026 @11:53PM (#48407726)
Good, Fast, Cheap.

Pick any two.

Re:When AI Builds Itself: Our progress toward recursive self... by bpodgursky on Thursday June 04, 2026 @04:57PM (#48404537)
They obviously don't care, aren't making any attempt whatsoever to do this, and 99% of users don't care either.

If you want to pollute your own priors with weird artificial litmus tests, it's a free country, but the artificial world-model you build in your head does not affect the real world around you.

Re:When AI Builds Itself: Our progress toward recursive self... by andriy_koval on Thursday June 04, 2026 @05:13PM (#48404714)
Maybe that gigabyte is occupied by useful information: traces/memory?
Re:When AI Builds Itself: Our progress toward recursive self... by overgard on Thursday June 04, 2026 @06:01PM (#48405215)
A gigabyte is a lot of memory. Even the largest context windows are a small fraction of that with any sane engineering discipline.
Re:When AI Builds Itself: Our progress toward recursive self... by andriy_koval on Thursday June 04, 2026 @06:06PM (#48405268)
For each LLM interaction they likely have bunch of thoughts traces, tool calls, etc, which don't go to context, but still can be retrieved.

But I obviously don't know for sure.

Re:When AI Builds Itself: Our progress toward recursive self... by javcasas on Thursday June 04, 2026 @05:16PM (#48404747)
Nope. Used to render on the terminal like a game engine.

https://x.com/trq212/status/2014051501786931427

Re:When AI Builds Itself: Our progress toward recursive self... by oersted on Thursday June 04, 2026 @05:22PM (#48404812)
This kind of immediate-mode rendering is quite standard for TUIs. Although immediate-mode rendering tends to be significantly simpler and use less memory than retained-mode rendering, at the cost of some redundant computation. So I am not sure if this is the reason for the bloat.

It’s possible that it doesn’t play well with JS garbage collection, since it recreates the whole UI structure for every frame (which tends to not to be an issue in the languages immediate-mode is usually employed).

But yes it’s a bit more akin to game renderings than web rendering. Which can be totally fine if done well.

Re:When AI Builds Itself: Our progress toward recursive self... by overgard on Thursday June 04, 2026 @06:05PM (#48405249)
I haven't tried to make a TUI admittedly, but double buffering is the oldest technique on the planet. A TUI doesn't even need to pay the cost of a lot of pixels since its effective resolution is much lower
Re:When AI Builds Itself: Our progress toward recursive self... by javcasas on Friday June 05, 2026 @08:17AM (#48411390)
Long long time ago, I used to do some graphics stuff in 320x240, which uses a whopping 64KB per buffer, and still has more resolution than a terminal.

In 1GB I could probably fit all the buffers to double-buffer all the TUIs in a whole country. Well, maybe not. But it's likely not that far off.

Re:When AI Builds Itself: Our progress toward recursive self... by ux266478 on Thursday June 04, 2026 @05:47PM (#48405060)
How on earth are you spending more than 50us on a UI like this from start to finish? What the actual hell? 11ms to construct a scenegraph of this complexity? I don't even know what to say to that.
Re:When AI Builds Itself: Our progress toward recursive self... by nicce on Friday June 05, 2026 @05:00AM (#48409879)
In comparison, I have around 3ms total latency when streaming 4k 144hz from headless machine in my basement to upstars :-D

At least that is what Moonlight client claims.

Re:When AI Builds Itself: Our progress toward recursive self... by fg137 on Thursday June 04, 2026 @06:00PM (#48405197)
Do game engines constantly have buffer issues?
Re:When AI Builds Itself: Our progress toward recursive self... by overgard on Thursday June 04, 2026 @06:02PM (#48405222)
Depends on if they're written with Claude
Re:When AI Builds Itself: Our progress toward recursive self... by lstodd on Thursday June 04, 2026 @05:27PM (#48404863)
I sorta remember Quake console running on an 486dx2 ..
Re:When AI Builds Itself: Our progress toward recursive self... by airstrike on Thursday June 04, 2026 @09:39PM (#48406966)
LOL right? This is all that needs to be said about the engineering behind Claude Code
Re:When AI Builds Itself: Our progress toward recursive self... by krapp on Thursday June 04, 2026 @05:24PM (#48404838)
Frankly that's an insult to gamedev. Literally every game engine I can think of could do better. Probably even Unreal Engine could do better.
Re:When AI Builds Itself: Our progress toward recursive self... by ux266478 on Thursday June 04, 2026 @05:53PM (#48405118)
If I saw our UI show up in the profiler eating 5ms of CPU time every frame, I'd send whoever was responsible to QA hell until they find some way to redeem themselves. Not even fancy animated 3D UIs, like what you get in Death Stranding, eat up these kinds of resources. Not even remotely close.
Re:When AI Builds Itself: Our progress toward recursive self... by est on Friday June 05, 2026 @01:02AM (#48408188)
> render on the terminal like a game engine

All those CPU to render this effect

https://x.com/cyrilXBT/status/2060617507615207904

Re:When AI Builds Itself: Our progress toward recursive self... by javcasas on Friday June 05, 2026 @05:19AM (#48410035)
ULTRACODE! NOW WITH MORE BLINKENLIGHTS!

(to be read with the Unreal Tournament announcer voices, see https://www.youtube.com/watch?v=MwxjYFqP35A )

Re:When AI Builds Itself: Our progress toward recursive self... by flexagoon on Thursday June 04, 2026 @09:30PM (#48406912)
Traces and memory are text. A gigabyte of text is an insane amount. That is an equivalent of tens of millions of lines of code, or hundreds of millions of AI tokens.
Re:When AI Builds Itself: Our progress toward recursive self... by toephu2 on Thursday June 04, 2026 @05:45PM (#48405048)
I have iterm2 open right now with Claude in a long session and it's only using 500MB of memory.
Re:When AI Builds Itself: Our progress toward recursive self... by pizlonator on Thursday June 04, 2026 @06:03PM (#48405232)
Only 500MB!

you are confirming their point even as you contradict the specifics

Re:When AI Builds Itself: Our progress toward recursive self... by z3c0 on Thursday June 04, 2026 @06:42PM (#48405658)
And highlighting a disconnect in the developer community. Some of us are okay with unnecessary overhead for quick results. I always felt gross dealing with Electron apps, but they're popular for a reason.
Re:When AI Builds Itself: Our progress toward recursive self... by deathanatos on Thursday June 04, 2026 @07:01PM (#48405840)
But each day now that overhead becomes more costly as AI drives up the very cost per byte of RAM.
Re:When AI Builds Itself: Our progress toward recursive self... by verdverm on Thursday June 04, 2026 @07:07PM (#48405887)
they make one of those electron apps too
Re:When AI Builds Itself: Our progress toward recursive self... by ChrisLTD on Thursday June 04, 2026 @08:47PM (#48406662)
Yeah. Bonkers considering the brain of the application isn’t even on your device.
Re:When AI Builds Itself: Our progress toward recursive self... by toephu2 on Friday June 05, 2026 @01:40PM (#48415796)
Followup: I closed out Claude completely, iterm2 completely. Reopened iterm2, and it appears iterm2 is using about 500MB of memory. So this has nothing to do with Claude Code CLI.
Re:When AI Builds Itself: Our progress toward recursive self... by thesmtsolver2 on Thursday June 04, 2026 @06:02PM (#48405220)
For some reason, idling Claude Code needs 100% of my CPU.
Re:When AI Builds Itself: Our progress toward recursive self... by nicce on Thursday June 04, 2026 @07:07PM (#48405891)
Like Google’s AI studio tab in browser. Incredible degrade in software quality?
Re:When AI Builds Itself: Our progress toward recursive self... by Jtarii on Thursday June 04, 2026 @06:15PM (#48405365)
Well, they could very easily if they wanted. There is just no economic value in it.
Re:When AI Builds Itself: Our progress toward recursive self... by davidatbu on Thursday June 04, 2026 @08:17PM (#48406447)
So would you take these claims seriously if they came from OpenAI (since Codex is a pretty lean CLI app)?

If so, I think it would be in the spirit of HN to discuss the subject matter of the blogpost (increasingly autonomous coding towards the end goal of RSI) as if the blog post was indeed from OpenAI. OpenAI is, by all accounts, going through a very similar process anyways.

Re:When AI Builds Itself: Our progress toward recursive self... by dang on Friday June 05, 2026 @12:00AM (#48407762)
"Please don't post shallow dismissals, especially of other people's work. A good critical comment teaches us something."

https://news.ycombinator.com/newsguidelines.html