Hacker News: ithkuil

New comment by ithkuil in "Stringman, an $800 open-source room scale gripper robot"

ithkuil — Wed, 04 Nov 2026 22:09:56 +0000

you can also program it to turn itself off

New comment by ithkuil in "Stringman, an $800 open-source room scale gripper robot"

ithkuil — Wed, 04 Nov 2026 00:13:52 +0000

can it just carry around a normal vacuum? no need for wheels when you can fly

New comment by ithkuil in "Postgres 19 is late because so many more bugs are being found now"

ithkuil — Tue, 03 Nov 2026 15:56:27 +0000

what do you do for a living?

New comment by ithkuil in "Postgres 19 is late because so many more bugs are being found now"

ithkuil — Mon, 02 Nov 2026 16:56:08 +0000

I personally preferred to code without AI; but it's objectively possible to do more things now so you're more competitive compared to other people who are not using AI. The tragedy is that since everybody is using AI, we cannot bank those advantages and we're just all going to suffer (a variation on the tragedy of the commons theme)

New comment by ithkuil in "Postgres 19 is late because so many more bugs are being found now"

ithkuil — Mon, 02 Nov 2026 07:44:19 +0000

I don't in general, but if enough people stop using AI and I still have access to GPUs then I have a pretty good advantage.

So unless it gets outlawed, I don't see people opting out of it

New comment by ithkuil in "Prospero: A new coding harness for a more civilized age"

ithkuil — Sat, 31 Oct 2026 15:51:05 +0000

I already found myself being limited by Memory used by Claude code, about 300MB per session. With 40 sessions that eats up quite a good chunk of my laptop's memory

Not a big deal since most of my sessions were parked so I just found a way to have them exit without losing the screen content (I took a screen dump from herdr) and a simple wrapper script that waits until hit enter to resume the session.

I don't _ have _ to switch to a lighter weight harness, but I'm not oblivious to memory usage

New comment by ithkuil in "Herdr has released native app"

ithkuil — Fri, 30 Oct 2026 09:51:48 +0000

I was initially excited because I thought I could just try out a new frontend while keeping my 10 existing spaces each with 10 worktrees each with 2 or more tabs untouched.

New comment by ithkuil in "Here be monsters: What do you still need to know when agents do the work?"

ithkuil — Thu, 29 Oct 2026 06:51:53 +0000

Or when you desperately search for the undo button on the mop

New comment by ithkuil in "Here be monsters: What do you still need to know when agents do the work?"

ithkuil — Thu, 29 Oct 2026 06:45:55 +0000

Models have plenty of skin in the game during training, but zero during inference

New comment by ithkuil in "The Mythical Man-Month in the Age of AI"

ithkuil — Tue, 27 Oct 2026 10:03:05 +0000

Things are moving at a pretty much breakneck pace, I'm not surprised there are so many opportunities for improvement yet to be grabbed

New comment by ithkuil in "Behind the scenes at the NeXT Computer office"

ithkuil — Mon, 26 Oct 2026 06:50:32 +0000

I have a toy recreating the visuals: https://github.com/mkmik/nextstop

(It's vobecoded in the original sense of the word)

New comment by ithkuil in "Cerebras Deploys Trillion-Parameter AI Models"

ithkuil — Sun, 25 Oct 2026 07:02:09 +0000

Do you need diagonal wires for a topological hexagonal tiling?

Wouldn't a rectangular brick layout be topologically a hexagonal tiling

New comment by ithkuil in "The recently proposed o(n log n) integer multiplication algorithm [pdf]"

ithkuil — Thu, 22 Oct 2026 08:38:49 +0000

Wait and see when _they_ are 20 years old!

New comment by ithkuil in "The compiler was supposed to end programming too"

ithkuil — Wed, 21 Oct 2026 19:31:12 +0000

Yes it does but yes you can also steer it clear of those mistakes in a similar way as you would have to steer tour human team.

It still requires a lot of work and care to leverage correctly and it's a moving target.

But it's quite impressive

New comment by ithkuil in "Advanced coding in low-resource programming languages"

ithkuil — Wed, 21 Oct 2026 09:29:08 +0000

> time is a circle

Or it is a self-similar fractal with significant and interesting variations

New comment by ithkuil in "Rabbits were a medieval royal luxury in England until the Black Death"

ithkuil — Mon, 19 Oct 2026 07:52:55 +0000

And the word rabbit comes there from french rabotte which however comes in turn from a Germanic language (dutch) so it doesn't feel quite french.

New comment by ithkuil in "Butlerian Jihad"

ithkuil — Sat, 17 Oct 2026 05:55:35 +0000

My experience:

Pick a random number between 1 and 10. I don't mean the most common random number

*4*

Pick a random number between 1 and 10. To feel truly random it should surprise me

*4*

I ran it again and it said 1.

I guess it just tries it best to do what you ask for.

Before jumping to conclusions we have to make sure it's clear what we're actually asking it to do.

And that's not at all different than what happens with humans.

This is especially visible in human dynamics that happen in those weird places that we call corporations.

New comment by ithkuil in "How the Claude Code team does code review"

ithkuil — Sat, 17 Oct 2026 05:37:08 +0000

I'm trying to learn how to write software with agents where I keep control over the design while yielding control over the implementation.

This is not very different from what already happens to architects that delegate implementation to teams.

The challenge Is to find a way to encode the architecture in a way that both you and the agents can understand and agree on.

I'm still learning how to do this effectively, but my initial experience is quite positive. Not because agents are great but because humans are bad; the degree of coherence I've seen agents following is bigger than many human teams I've led in my career.

My benchmark is a quite big project for which the architecture is already well known, namely the reimplementation of the OpenVMS OS (kernel and user-land). There are many traps and many opportunities for the agents to just go ahead and diverge from the goals, so I found it a good playground toearn how reign them in but let them be effective at "drawing the rest of the owl"

New comment by ithkuil in "Muse Spark Open"

ithkuil — Thu, 15 Oct 2026 18:41:32 +0000

Even if your revenue exceeds 20MM you can still use this model from inside a commercial product but you can't expose it directly as a "model as a service"

New comment by ithkuil in "Yandex outage: data shows that instead of going dark, malicious bots moved"

ithkuil — Thu, 15 Oct 2026 06:19:50 +0000

Russia is big though