Hacker News: ucirello

New comment by ucirello in "Local Git Remotes"

ucirello — Fri, 29 May 2026 14:12:51 +0000

That's what I used to do with git (just recently moved off of SVN) in a shared computer predating github. It works very well!

New comment by ucirello in "Show HN: Sgai – Goal-driven multi-agent software dev (GOAL.md → working code)"

ucirello — Thu, 26 Feb 2026 16:43:57 +0000

author here! Good suggestion, we should probably come up with some GOAL.md examples. With that said, one-shotting a pretty large app is a somewhat doable task, and that's one of the reasons we have introduced the interview step: exactly to let the model pull from you (instead you pushing into the model a spec document) what it needs to know to be able to work autonomously.

New comment by ucirello in "Show HN: Sgai – Goal-driven multi-agent software dev (GOAL.md → working code)"

ucirello — Thu, 26 Feb 2026 16:43:28 +0000

author here! It supports multi-repository. You would need to create a directory with both git repositories cloned in, and save the GOAL.md at the parent. This UX could use some polish, for sure. It works, but it needs this extra step.

New comment by ucirello in "Show HN: Sgai – Goal-driven multi-agent software dev (GOAL.md → working code)"

ucirello — Wed, 25 Feb 2026 20:20:56 +0000

author here! I am not sure if I would phrase it as sane Gas Town. The design constraints are very different. For example, I tried to optimized for output density (the number of tokens that I didn't have to rewrite because the output quality was bad), instead of treating it as a distributed system and coordination problem. SGAI, for example, runs one agent at a time - maybe one day it will run more agents in parallel, but only as much that I can obtain better outputs (not more outputs).

Also, I am not a cryptocurrency enthusiast - and therefore, I wouldn't accept creating a memecoin out of it.

New comment by ucirello in "Show HN: Sgai – Goal-driven multi-agent software dev (GOAL.md → working code)"

ucirello — Wed, 25 Feb 2026 18:01:23 +0000

author here! it is my daily driver for quite some time; with that said, its current shape is a bit of a more recent development. Initially, I would manually handle jj workspaces and fire out screen/tmux sessions; but over time, I figure it would be nice to have an UI that I could browse from anywhere through a VPN.

It does take some investment -- by adding customizations through the overlay folder (`sgai/` directory at the root of the repository) -- but eventually it should be able to code in a way that you would approve in a PR.

New comment by ucirello in "Show HN: Sgai – Goal-driven multi-agent software dev (GOAL.md → working code)"

ucirello — Wed, 25 Feb 2026 17:03:55 +0000

author here! the decision was mine; if anything, the senior leadership was fine with an unencumbered open-source license. What I didn't want was someone using it to make a business out of this tool without me in the mix.

In a sense, a futile effort; because if you reverse engineer a nlspec and rebuild it, then you can have it with any license you may want.

New comment by ucirello in "Show HN: Sgai – Goal-driven multi-agent software dev (GOAL.md → working code)"

ucirello — Wed, 25 Feb 2026 17:00:38 +0000

author here!

I have been working on this for my own use until recently, when I shared with the rest of the team, and we thought it would be nice to let the world see it.

I have been interested in autonomous code development for quite some time (at least since March/April 2025) - and summer '25 is when I felt the models were good enough to be pushed to autonomy.

I wrote a bit about it[0], and sgai is the incarnation of my take on AI autonomous coding.

sgai is not even v0 yet, a lot of work to be done to improve its implementation - but I think it should be usable enough for those willing to give it a try.

0: https://cirello.org/aifactory.html

New comment by ucirello in "Software factories and the agentic moment"

ucirello — Sat, 07 Feb 2026 19:41:55 +0000

Justin never invites me in when he brings the cool folks in! Dang it...

Automating Agentic Development

ucirello — Wed, 26 Nov 2025 20:31:12 +0000

Article URL: https://blog.fsck.com/2025/11/21/automating-agentic-development/

Comments URL: https://news.ycombinator.com/item?id=46061982

Points: 1

# Comments: 0

New comment by ucirello in "Perkeep – Personal storage system for life"

ucirello — Wed, 12 Nov 2025 05:17:44 +0000

I wish bradfitz had more time to work on it.

Designing MCP servers for wide schemas and large result sets

ucirello — Wed, 08 Oct 2025 14:30:55 +0000

Article URL: https://axiom.co/blog/designing-mcp-servers-for-wide-events

Comments URL: https://news.ycombinator.com/item?id=45516616

Points: 12

# Comments: 0

Bouba / Kiki Effect

ucirello — Sun, 21 Sep 2025 05:38:31 +0000

Article URL: https://en.wikipedia.org/wiki/Bouba/kiki_effect

Comments URL: https://news.ycombinator.com/item?id=45320327

Points: 15

# Comments: 2

The Sunday Morning Post: 'Science Is the Belief in the Ignorance of Experts'

ucirello — Thu, 31 Jul 2025 03:54:32 +0000

Article URL: https://www.derekthompson.org/p/the-sunday-morning-post-science-is

Comments URL: https://news.ycombinator.com/item?id=44742175

Points: 4

# Comments: 2

Apple Interview in 1995 (2022)

ucirello — Mon, 07 Jul 2025 03:27:59 +0000

Article URL: https://engineersneedart.com/blog/interview/interview.html

Comments URL: https://news.ycombinator.com/item?id=44486480

Points: 4

# Comments: 0

New comment by ucirello in "Show HN: I built a word game. My mom thinks it's great. What do you think?"

ucirello — Sun, 06 Apr 2025 03:10:48 +0000

les circuits de consécration sociale, sera d'autant plus efficace plus la distance sociale de l'objet consacrée - Bourdieu

New comment by ucirello in "Rust Can Replace Protobuf"

ucirello — Tue, 18 Feb 2025 00:54:28 +0000

Why not do it in Zig?

New comment by ucirello in "We replaced our React front end with Go and WebAssembly"

ucirello — Tue, 11 Feb 2025 05:28:52 +0000

Why not Zig?

New comment by ucirello in "Is XYplorer really written in VB6?"

ucirello — Sun, 12 Jan 2025 19:28:03 +0000

I will disagree with this list, in part. And I am thinking specifically of PHP. I am an emigrate from PHP ecosystem, I departed from PHP 11 years ago and never looked back. The number one reason that I left PHP is that #1 in your list was plainly false. There were _not_ high paying jobs in PHP, no matter how good you were or not. The whole point of using PHP is to pay as little as possible; and make developers as fungible as possible. And if a certain demographic yielded good quality developers for an even lower price point, I would certainly see whole teams being replaced to fit it. I was actually recruited, more than once, exactly for this reason.

Languages don't die, they ride into the sunset. There is enough inertia in PHP-ecosystem that you can still find jobs, but they are very often just legacy work jobs (at least in my area). No serious technical leader would pick PHP to execute on new work, except of course, if their main driver is to pay as little as possible and the language choice doesn't bubble up to investors' keyword-driven investment thesis.

VB6 and PHP are nice. I am skeptical of the affirmation that there is a lot of money in these ecosystems. The pie may be currently large, but I do not see it growing.

New comment by ucirello in "Interactive Visual Sorting"

ucirello — Sun, 24 Nov 2024 17:02:05 +0000

In the box of QuickBasic 4.25 Professional it has a BAS file that was exactly like this. Really neat. It even played sounds!

Tab Window Manager: The OG Window Manager of Unix

ucirello — Thu, 29 Aug 2024 02:21:57 +0000

Article URL: https://en.wikipedia.org/wiki/Twm

Comments URL: https://news.ycombinator.com/item?id=41386628

Points: 4

# Comments: 1