rgbrgb

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

very cool! i'd been thinking about this idea and found vega-lite to be an interesting take as well [0].

i'll compare and look at folding this into setoku for app generation [1]. right now apps are just html blobs your claude authors + a mechanism for populating them with live data. definitely hard to audit but very flexible for operators to claude together internal apps. anyway, the charts look decent but really depend on the model that's making them and don't really follow any sort of style guide (example: https://demo.setoku.com/apps/a7a1240ae0bc202c5eefa1cc). Your lib could bring some consistency and make global styling possible.

[0]: https://vega.github.io/vega-lite/

[1]: https://setoku.com

interesting. the less "research lab" version i've seen of this is https://polsia.com

comparatively, I really appreciate the transparency here. clearly it's a little too early for this (quickly glanced at the P&L's, correct me if I"m wrong), but someone has to run the experiment and figure out when it's ready for prime time.

> semi-skilled workers

fwiw the h1-b workers I encountered in bigtech were totally on-par with their US citizen equivalents in both coding and english communication. many teams were about 50/50 in my office (SF, non-HQ).

my current talent/placement company works mostly with AI startups who are usually too early to support visa requirements [0]. being able to support the lead-time and planning for international applicants is a huge advantage later stage companies have in terms of being able to scoop up talent at reasonable prices. big loss for the local ecosystems if these jobs move across the border imo.

[0]: https://www.hedgy.works

why shadcn and not bootstrap? shadcn is like a cool weird approach to a ui kit but bootstrap got us a date picker iirc.

kind of rhymes with the reports of LLM's watching open source PRs and instantly exploiting defects. security by obscurity is so back

agree and underscores the idea that you should keep your setups portable between model providers by using external memory systems and connector gateways

tbh I use 1 custom skill (workflow for completing a github issue and opening dev server/PR) and have it checked-in to my main project repo.

For me, it's like a dev script basically and gets that level of care. I don't need an eval... I'm the only user and I use it like 5 times a day.

There’s kind of an interesting thread here about open source, which is usually thought of as more secure because of more eyes on the code, actually being less secure because an accidental merge can be exploited instantly with LLM’s monitoring. Is there a lot more security value in obscurity than before?

at Hedgy we built an MCP to give our agents read-only access to cross-system data + context about what it means [0]. daily it helps me debug customer flows and think through features and priority.

the advantage of MCP is that the tool description names what data it has so the agents know to just use it if they want that kind of data. as new data is added, everyone’s tool description updates. with a REST api or cli I suppose we could update a checked in AGENTS.md to ship it to engineers but idk how id get that to colleagues using the it from their claude.ai or co-work.

[0]: setoku.com

if you're using claude code, i find you can instruct it to watch the pr and iterate on ci failures. I put this in an /issue skill that completes GitHub issues in the way I like then PR's or boots dev with QA instructions if it needs a human touch/eye. to drive this, I have a higher level bash script that makes a fresh worktree off of origin/main named after the issue and spawns a claude session running /issue.

i'm not at the point where I'd go totally hands-off with code review / QA, so this setup is the right balance of automation for my current read on agent capability.

or maybe more like a restaurant than a kitchen... with software development (like all product development) you need to bake in the user feedback loop

like to torture the metaphors, i think we already have the factory (coding agents you can ask to manufacture software to a spec) but it's the whole process including QA, shipping, listening to users and iterating that has to happen over time (unless you have an accurate world simulation so you know exactly how your product will be received... and I know there are people working on that too but I'm skeptical)

this is sick and the video infra sounds interesting! as a fellow san diegan i really get a kick out of seeing everyone who hit the 14 stair behind my high school https://skatanica.com/spots/5eyevxzo35tcou1n6doxkw2lx?map=-9...

why no hometown hero tony hawk?

this is cool! incidentally we do a similar motion internally for members on https://www.hedgy.works

how did you think about evaluating quality when designing your ranker / fit scoring?