Hacker News: rgbrgb

New comment by rgbrgb in "Ask HN: What do you run on a $5 VPS that's worth keeping online 24/7?"

rgbrgb — Fri, 09 Oct 2026 14:04:42 +0000

- personal websites

- family ai knowledge / data store MCP https://setoku.com/

I love interserver.net which starts at $3/mo and has much better network and cpu than providers with twice the specs. I benchmarked a bunch for a hobby project. I also run some professional stuff there (worker servers for https://hedgy.works). Also LAX locations with great ping in California.

BTW I do think this is a golden age for the humble VPS. If you’re daring you can totally let Claude code be your sysadmin.

New comment by rgbrgb in "ts-rust: An experimental Rust port of the TypeScript 7 compiler (tsc)"

rgbrgb — Wed, 07 Oct 2026 22:58:13 +0000

say what you will about this project but "The Slop Line" from the readme is a great innovation

edit: the project seems pretty cool but i'm not seeing any reason to look up from bun

New comment by rgbrgb in "Worth Building"

rgbrgb — Tue, 06 Oct 2026 19:40:48 +0000

oh, i haven't tried claude design. i just meant claude code in the terminal

New comment by rgbrgb in "Show HN: Rhun, an open-source code editor written in assembly"

rgbrgb — Tue, 06 Oct 2026 19:39:29 +0000

that makes sense, thanks.

New comment by rgbrgb in "Worth Building"

rgbrgb — Tue, 06 Oct 2026 02:45:02 +0000

Give screenshots to Claude and ask for design review. Surprisingly effective. At this point opus 5.5 can do a lot with that exact type of feedback.

New comment by rgbrgb in "Show HN: Rhun, an open-source code editor written in assembly"

rgbrgb — Thu, 01 Oct 2026 22:45:09 +0000

can you talk about why you do this in assembly?

New comment by rgbrgb in "Jeeves. Reasoning improves Jev-like decision models"

rgbrgb — Tue, 29 Sep 2026 17:58:52 +0000

openai's new Decisions API looks to be targeting that https://openai.com/index/devday-2026-recap/

Drex: Open jev-like claims win on decision index

rgbrgb — Fri, 25 Sep 2026 18:54:01 +0000

Article URL: https://www.nace.ai/drex

Comments URL: https://news.ycombinator.com/item?id=49848470

Points: 4

# Comments: 0

New comment by rgbrgb in "Ollaya – Ollama for open-source, Jev-style decision models"

rgbrgb — Fri, 25 Sep 2026 18:51:48 +0000

there's this thing with a bunch of similar models https://huggingface.co/spaces/multimodalart/jev-decision-ind...

top open one is trained by perplexity cto for $3k, kinda cool https://x.com/denisyarats/status/2102252088067850507

New comment by rgbrgb in "Rails World 2026 Opening Keynote [video]"

rgbrgb — Thu, 24 Sep 2026 22:11:50 +0000

shopify agrees https://shopify.engineering/back-to-native

New comment by rgbrgb in "Creatine uptake enhances antitumor immunity"

rgbrgb — Thu, 24 Sep 2026 18:50:09 +0000

worth noting that there’s evidence both ways… tumor cells may like it too:

- Loo et al. 2015 found color cancer cells can use it as fuel and blocking the creatine cut metastasis in mice [0]

- zhang et al 20921 found it promoting mouse colon and breast cancer models [1]

not an expert in any way, but i’m guessing it depends on cancer type and there doesn’t seem to be human data either way. as a cautious person w a lot of familial cancer, i cycled off after i looked into it.

[0]: https://pubmed.ncbi.nlm.nih.gov/25601461/

[1]: https://doi.org/10.1016/j.cmet.2021.03.009

New comment by rgbrgb in "Contrastive Language Models"

rgbrgb — Thu, 24 Sep 2026 18:00:01 +0000

beautiful. would love to see it on some leaderboard

https://benchmarkheaven.com/jev-models

https://huggingface.co/spaces/multimodalart/jev-decision-ind...

New comment by rgbrgb in "Contrastive Language Models"

rgbrgb — Thu, 24 Sep 2026 16:40:59 +0000

what's wrong w "system one"? it feels like a good frame to think about use-cases that will fit jev etc.

New comment by rgbrgb in "Ask HN: Do you offload your coding to AI, or keep your skills sharp?"

rgbrgb — Wed, 23 Sep 2026 18:45:39 +0000

imo the valuable thing we bring as software engineers is and has always been solutions to problems with the contextually correct quality/speed/cost tradeoffs. with agentic coding, these factors all shift and we're all in the process of recalibrating. namely the speed dial can now be shifted way down.

to answer directly, i live in claude code now. and while it's a different shape of daily work, i'm still engineering, still evaluating those 3 factors and figuring out how to triage and solve user-problems much faster than i could 5 years ago.

New comment by rgbrgb in "Jev in 25 Lines of Python"

rgbrgb — Wed, 23 Sep 2026 17:52:20 +0000

i love that people are trying to make OS jevs but what is the point of doing all this work and not ask your coding agent to do a little benchmarking. selfishly want an open weight model to beat jev here

just found this one https://huggingface.co/spaces/multimodalart/jev-decision-ind...

Jev Decision Index Leaderboard

rgbrgb — Wed, 23 Sep 2026 17:39:40 +0000

Article URL: https://huggingface.co/spaces/multimodalart/jev-decision-index

Comments URL: https://news.ycombinator.com/item?id=49819739

Points: 3

# Comments: 0

New comment by rgbrgb in "MCP was always a bad idea?"

rgbrgb — Mon, 21 Sep 2026 18:15:21 +0000

most users i'm dealing with are not doc-reading developers. even getting them to tell claude to use tool X is pretty hit or miss whereas claude already knowing what tool to use is 100% hit with correct mcp tool descriptions.

New comment by rgbrgb in "Kev: Tiny Jev-like family of decision models built on top of Qwen3.5"

rgbrgb — Mon, 21 Sep 2026 16:55:13 +0000

love this idea. did you try comparing to jev?

New comment by rgbrgb in "MCP was always a bad idea?"

rgbrgb — Mon, 21 Sep 2026 03:18:57 +0000

it's mostly true but the mcp also installs the knowledge of that REST API in a standard way so that a user can ask "what's projected revenue this month?" and it'll know how to hit your company brain and answer

New comment by rgbrgb in "Laya the open source version of Jev"

rgbrgb — Sat, 19 Sep 2026 14:30:55 +0000

It can’t do images but it can do a pretty good job of triaging urgency or choosing when to escalate. So I’d guess yes but it depends how detailed your classification is.