Hacker News: capocasa

New comment by capocasa in "Nim Version 2.4.0 Released"

capocasa — Wed, 28 Oct 2026 18:03:30 +0000

Oh my goodness! Excitement!!!

Announce: Mpx, a cross platform multi-attach syncing terminal multiplexer

capocasa — Fri, 02 Oct 2026 15:28:19 +0000

Article URL: https://forum.nim-lang.org/t/14202#86214

Comments URL: https://news.ycombinator.com/item?id=49934607

Points: 2

# Comments: 0

New comment by capocasa in "Show HN: Open-source model routing for coding agents at Astra-level performance"

capocasa — Fri, 02 Oct 2026 09:06:11 +0000

That sounds really quite interesting- one question pops up, this sounds like it could produce a lot of non-cache input tokens. How much impact does this have, and are you mitigating it?

Interested in adding support to my own 3code- https://3code.capocasa.dev- which aims to reduce cost by using more compact system prompts and a clever compaction variant.

New comment by capocasa in "Pi 1.0"

capocasa — Fri, 02 Oct 2026 08:51:24 +0000

Thank you!!! And thank you for your interest!

Yes- I plan to make a a full web app, as well as a web-and-terminal orchestrator app. Still planning the details.

New comment by capocasa in "Pi 1.0"

capocasa — Fri, 02 Oct 2026 07:31:06 +0000

I'm here for the long haul!

https://3code.capocasa.dev

I believe software can be done- with incremental improvement and keeping the foundation, like vim. That's the 3code trajectory.

New fun ideas go into seperate tools, possibly ones 3code (or other minimal agents) can call, but the core stays lean.

New comment by capocasa in "Pi 1.0"

capocasa — Fri, 02 Oct 2026 07:29:47 +0000

I agree! MCP should be a command line tool wrapper than can be used from any minimal agent without bloating context if you don't need it.

New comment by capocasa in "Pi 1.0"

capocasa — Fri, 02 Oct 2026 07:29:01 +0000

I did some token tests and both pi and my own 3code used 4x fewer tokens than Claude Code, while opencode used 2x fewer tokens than Claude Code. You can tell Anthropic just doesn't care about using tokens and the tradeoff is maximal performance. That's understandable, but it might not be the tradeoff you need, hence, alternative clients.

New comment by capocasa in "Pi 1.0"

capocasa — Fri, 02 Oct 2026 07:27:46 +0000

I went for a middle ground in https://3code.capocasa.dev.

Each family gets their own system prompt, based on the original harness one, but compacted and includes instructions for more brevity.

New comment by capocasa in "Pi 1.0"

capocasa — Fri, 02 Oct 2026 07:26:39 +0000

I made just that!

https://3code.capocasa.dev

Written in Nim. Unixy scrollback but cross plaform. Tested for token efficiency.

New comment by capocasa in "Pi 1.0"

capocasa — Fri, 02 Oct 2026 07:24:49 +0000

Or for something not quite as bare bones- batteries included and tested for token consumption- https://3code.capocasa.dev

This Year I Vibecoded My Taxes

capocasa — Mon, 14 Sep 2026 08:16:42 +0000

Article URL: https://capocasa.dev/this-year-i-vibecoded-my-taxes

Comments URL: https://news.ycombinator.com/item?id=49693556

Points: 1

# Comments: 0

New comment by capocasa in "Mistral raises €3B"

capocasa — Tue, 08 Sep 2026 11:54:24 +0000

Last time I tried Mistral large it was pretty bad at programming but I hear they're fairly good at European language legal.

10-task GLM 5.3 harness bench: Claude, OpenCode, pi, zcode, Hermes and 3code

capocasa — Mon, 07 Sep 2026 10:31:57 +0000

Article URL: https://capocasa.dev/10-task-glm-5-3-harness-bench-claude-opencode-pi-zcode-hermes-and-3code

Comments URL: https://news.ycombinator.com/item?id=49596553

Points: 9

# Comments: 0

New comment by capocasa in "Private German rocket makes history, reaches orbit from European soil"

capocasa — Sat, 05 Sep 2026 21:23:05 +0000

This is such a breath of fresh air

New comment by capocasa in "Show HN: FrontierHarness Eval – 9 harness, same model, cost per pass varies 17x"

capocasa — Thu, 03 Sep 2026 13:15:16 +0000

I saw that very much developing 3code. Even slight system prompt variations can have huge differences in results, so I have one system prompt per model family.

3code benches 75 lower token use vs. OpenCode on 10-task SWE-Bench subset

capocasa — Wed, 22 Jul 2026 06:11:53 +0000

Article URL: https://capocasa.dev/3code-benches-75-lower-token-use-vs-opencode-on-10-task-swe-bench-subset

Comments URL: https://news.ycombinator.com/item?id=49002476

Points: 6

# Comments: 0

New comment by capocasa in "Are we offloading too much of our thinking to AI?"

capocasa — Tue, 14 Jul 2026 21:15:06 +0000

Definitely, but since my experience is that without the AI the thinking simply wouldn't happen at all in most cases it's a net improvement.