rgbrgb

> Every app can run headless, so an agent can render to PNG, dump the element tree and drive it with scripted input.

This is cool. I hope SwiftUI / UIKit borrow this idea for native mac apps.

is there a way to find good deals other people have checked? seems like a nice data play if so and you could do affiliate links to monetize on some. I don't think people would mind you sharing the deals they found (could be a "share with community" checkbox too).

In addition to what everyone’s saying about platform economics, the other big advantage of selling tokens to everyone rather than competing with them directly is that they get to see everyone’s tokens (and, with consent, train on them)

i like this idea! though it feels very expensive... it says getting 3 apps going in LAX is over $90/mo. i have many personal apps running on a $50/YEAR VPS. i accept that this could be like the infamous dropbox comment [0] but it is so damn easy to give opus ssh to your VPS and have it deploy this stuff that there will at least be a race to the bottom if this model is successful.

[0]: https://news.ycombinator.com/item?id=9224

Hey HN,

I remember running SETI@home on my Mac G4 cube growing up. Loved it - felt like I was a part of something bigger than me. With the extreme efficiency of Opus 5.5 I’m finding myself with some extra tokens on my hands at the end of every week. This is an idea I had last week to put those tokens towards something useful and explore multi-agent systems with LLM’s.

Hoping a couple people here want to drop their agents into the lab and work with mine here https://lemmapark.com

LMK if you have questions or suggestions. Just started thinking about this community swarm approach and I’m pretty excited about it.

Thanks! Peter

cool project. slint looks nice

> filesharing for the meatspace era

serious question: what does this mean lol

> It’s completely possible that Rust’s compiler contains a backdoor... The only way to compile Rust’s compiler is using a binary package of the previous version released by the Rust Foundation.

this is interesting but idk if i get it. couldn't you compile it with a different rust implementation like https://github.com/thepowersgang/mrustc

no, just thought it was neat

- 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.

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

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

that makes sense, thanks.

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.

can you talk about why you do this in assembly?

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

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

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

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

beautiful. would love to see it on some leaderboard

https://benchmarkheaven.com/jev-models

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

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

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.

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...

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.

love this idea. did you try comparing to jev?

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

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.

would this work with a postgres hosted on supabase? for our company brain mcp thing we mirror postgres data (along with server logs, banking data, slack, etc) in clickhouse but took a very inefficient polling approach since it works with any read-only db connection string. always looking to improve that and get rid of latency though.

I've been thinking about this in the context of learning new languages and tech. In pre-LLM days it was fun to sometimes try to implement a new idea in a new language or stack and build up an understanding by trial and error. You'd have to accept that it will be slower to get going than a familiar set of tools and maybe only trade out one old tool at a time in this way.

Now the pace of dev with something new is so rapid and fun that it's hard to not skip even basic things with a new stack. I swapped postgres (old reliable) for clickhouse (first use) in a project and saw a massive speedup of my workloads, but I really have to go down the socratic rabbit hole to understand why and even then it's a different level of understanding vs having to read the readme, quickstart, install it myself, rewrite queries by hand. TBH though, pre-LLM I probably would have just plodded along with postgres and built a hacky auto-indexer thing, so in a way the agentic coding helps me explore more territory but encourages less depth.

No strong conclusions. Like OP, I'm just spitballing / trying to understand this new world too.

maybe someone wrote a classifier (or LLM wrapper) to find posts that will rank on hn

these were not average employees - top decile engineers i've worked with, shipping quickly and rigorously to millions of global users