colinsane

we've barely scratched the surface when it comes to the available design space of agent harnesses.

i also expect you'll see markedly different results if you constrain yourself to small models. there even trivial harness improvements like Codex's /goal feature, and more capable basic tooling (e.g. semantic code grep, js-capable `fetch` tooling) make or break the actual task success rate.

hopefully all of the above?

at some point the conversation has to go past this reflexive "USA uses tech abusively -> but look at how abusive China is with tech -> ..." back-and-forth to acknowledging that neither party is your savior -- and then (hopefully) acting upon and coordinating around that understanding.

i'm mildly annoyed by the project in general because i put in a sizable effort getting the whole sway stack to cross compile correctly in nixpkgs/NixOS, keeping that stable for a year so that people could build on it, and then suddenly hyprland forked every package in the stack with a fresh set of "works on my machine" nix expressions, and then much of the peripheral sway packages (e.g. status bars like nwg-panel, notification centers, etc) decided to become dual-stack and take a dependency on those fast-moving/beta packages. for a solid month any time i updated my machine there was a _new_ hypr-something dependency in my sway desktop that broke cross compilation. eventually i gave up and just set `hyprland = null; hyprutils = null;` in my personal config: mainline's been broken for a year now, sorry to anyone who was using that.

it gives "rewrite it in rust" vibes in the way they rush in to re-do everything without understanding why things were the way they were or if, in fact, anyone was using that obscure feature. maybe they'll sort it all out in time; maybe not. wish they could at least take less of a "we don't care if we break your shit" attitude in the meantime.

/rant

i hadn't considered that Seattle might be an outlier; the numbers vary by city more than i knew.

https://www.soundtransit.org/sites/default/files/documents/2...

page 11 has the $ figures. "link" is the commuter rail system: $408M operating expenses but only $51M revenue from fares, i.e. fares cover 12% of op ex.

the "average fare per boarding" is $1.34 (page 3; this is ticket price multiplied by the proportion of trips where the rider pays that ticket). throw that together: even with 100% payment compliance the average ticket price would be $11 per boarding for that to be a complete funding source. $11 would force more riders onto the subsidized fare programs, plus other knock-on effects from raising fares (e.g. reduced ridership in general) means the sticker price would have to be higher yet.

the commuter rail here was never designed for ridership fares to cover its operating costs. it just wasn't. the recent focus on fares in the face of all this is misinformed, that's the kindest way i can phrase that.

(apologies to hijack much of this with what turns out to be more of a Seattle-specific issue).

the turnstile thing is more complex than you perceive because almost every transit system relies on public funding. here (Seattle) those fares only fund about 10% of the _operating cost_ of the transit per Sound Transit's own reports. not to derail the point, but please do go read your transit system's quarterly reports instead of taking the conclusion of fare dodging for granted. just about every city has public budget reports for their transit system precisely because they are the product of public funding.

i just prompted Kimi & it replied with an uncensored version.

i posted the transcript as a reply to you, and HN automatically flagged it.

but go on.

The bigger problem with the post is that it talks out of both ends of the mouth: it’s clearly meant as a personal attack, but also insists that it isn’t.

my instinct is to step up and defend Andrew: to say that truly, he has strong opinions -- which is to say he _cares_ about doing things right -- but that he's more patient and accommodating than you're judging him to be from this 10,000ft view.

that's kinda weird: you might view this as a personal attack _from_ Andrew against Bun and i might view the reactions as personal attacks _against_ Andrew. viewing it through this lens without our preconceptions ought to make either both parties or neither party look bad, i think? i don't know the solution except to highlight the outsized impact that our individual preconceptions play when judging a situation from 10,000ft away.

the options available to small web hosts are:

1. do nothing: everyone gets page loads of 30s if not worse.

2. put the content behind anubis -> load drops by 80% and page loads are back to "a couple of seconds" (including the client-side challenge).

3. take the content offline -> load drops to 0.

which of these would you prefer?

just their smallest dataset looks to be 6 TB _compressed_. not a thing you can really ship as part of the agent. but if somebody made a fetch_url tool that sharded that across all users of it, i'd give it a try. could probably just layer that on top of bittorrent or IPFS or something.

ironically (?) i prefer to improve Pi by connecting MCP servers instead of native extensions in part due to this (process-level sandboxing is trivial; anything more granular -- as would be required for in-process plugins -- is far more intimidating).

any tips for calibrating or even just validating these handheld CO2 meters?

i've taken a few Amazon-listed CO2 meters from $dirt-cheap to $150, tossed them in a ziplock, and then discharged CO2 from a canister into the bag & sealed it. none of them read notably differently after an hour, nor show any sort of range error, etc.

i've also done this without the ziplock: put them in a large pot, fill that with CO2. CO2's heavier than the rest of the air so the concentration should remain elevated within the pot, but same deal.

i like the idea of monitoring CO2, but it's hard enough to get certainty about the _effects_ of CO2 level; without confidence in my meter i fear the conclusions i draw from it are more noise than signal.

i installed the playwright MCP to let my agent access walled sites (specifically ebay and WSJ). i noticed that 90% of the time it was bounced from a site, it just reached out to a different site that wasn't walled, and i think it's the right move: most information exists at multiple places on the web, it's cheaper and _faster_ to just skip over walled sources.

for the forum example: many forums have a policy to only allow access to attachments to logged-in users. i can't remember the last time i registered at a new forum just to view an attachment: the effect has always been to drive me elsewhere. no complaints -- these solutions work if your goal is to reduce load. i'm suspicious that they can drive monetization outside of a very few niches.

that's somewhere between saying "use Android, just switch to Graphene if/when they lock it down", and saying "just switch to postmarketOS/Ubuntu Touch/whatever flavor of Linux takes off".

i've watched friends try that route; i've been through this before. taking a downgrade is never fun: if it's a thing you're likely to care about in the future, then sometimes it's better to place yourself in the right ecosystem early.

AgentWorld is _fantastic_. i just migrated "down" from the 122B A10B qwen model to agentworld (35B A3B) because it feels as capable, easier to steer, and it's 3x faster.

also i like that if i drop more sophisticated tools into my harness (e.g. any of the NLP/RAG-based search tools in place of grep/rg), the agent will actually reach for them and make progress faster; previous models have been reluctant to embrace new tools.

i like that people are taking the privacy argument seriously, after however many decades. i think there are other arguments to be made for running these locally which are less settled, but IMO the Fable debacle drives it home: the surest way to embrace this technology without worry that it will be taken away from you down the road is to physically own the compute.

the _one_ downside i've seen is on an airplane serviced by Starlink: UDP was extremely lossy to the point that whatever recursive resolver i was using at the time would mark half of all nameservers it saw as "unhealthy" and start returning NXDOMAINs to the clients before even trying to hit the authoritative NS.

Buy Bitcoin.

look, i'm sorry, but this is a thoroughly solved problem by now.

the companies which have the power to alleviate these shortages are the same companies who are profiting most from the shortage. scarcity is an asset, it's not irrational that a concentrated marked will produce more of that asset.

can those macs boot linux? i've heard about Asahi but have no idea how far along they are. i've got my fleet configured with nix and sure, nix can target darwin, but there's a _lot_ of sharp edges there: i don't really want to pull that thread unless i have to...

i asked gemini and it replied with "Error: 400 Your prompt was blocked by safety filters. Please revise and try again."

curl used to have rust in it, dropped it 1.5 yrs ago. AI doesn't help with the hard parts here i don't think. https://daniel.haxx.se/blog/2024/12/21/dropping-hyper/

a huge aspect of open source is the user -> contributor -> maintainer pipeline. maybe they mean well, but in fact they're constructing a wall between those last two groups.

especially in larger projects where maintainership duties are heavily delegated, the last thing i want is some tool that can only be used by me, because suddenly i can no longer share the workload that tool targets with people who aren't "technically" maintainers.

good for bitcoin

sure.

git clone https://github.com/nixos/nixpkgs

ANTHROPIC_BASE_URL=https://openrouter.ai/api ANTHROPIC_AUTH_TOKEN=<make_an_account_on_openrouter_and_get_this_from_the_settings_panel> claude --model qwen/qwen3.6-plus:free

This repository has two ways of packaging Nix packages: defining them via pkgs/top-level/all-packages.nix (the old way); or defining them via the pkgs/by-name directory (the new way). Let's port my_example_package over to the new way.

i'm not actually working in the nixpkgs repo -- i'm trying these in a private repo that has very similar structure. i'm also a n00b with these tools, so probably a bad prompt. but Qwen 3.6 actually conflates "the old way" with "the new way", attempts to do the porting in reverse, and just gets stuck. gemma-4 E4B does better. even gpt-oss-120b, an open weight model from a _year_ ago, does the full port unattended.

so either it's shit at coding, or i'm using it wrong. curious to hear other anecdotes.

Windows and other OSes have application launchers that open whatever app you want, and those apps may have issues that cause it to download and run arbitrary code. if that's the logic here, then every application launcher is vulnerable to similar RCE.

if there's really nothing more to this 8.8 RCE CVE than that, this will finally be the thing that's makes me blackhole cve.org.

for public torrents, skip the trackers and just run a DHT crawler like bitmagnet. it'll take a month to "catch up", but after that you'll have more indexed content than any individual tracker & it'll be way snappier.

Why hasn’t there been a fork of nixos? And the folks who want to do things in a certain politically leaning way gravitate towards that and those that don’t stay.

v.s.

Why hasn’t there been a fork of nixos? And the folks who want to do things in a certain politically leaning way stay and those that don’t gravitate towards that.

now let's spend the next few years arguing which of these is the correct proposition.

sure, it's more complicated: there's questions about _what_ to fork (Nix is an _ecosystem_, not necessarily a single repository), there are certain things which can't trivially _be_ forked (e.g. a multi-hundred-TB S3 cache that's actually critical infrastructure; project websites, wikis, uncountable automation services). how do you coordinate all the details of forking, if forking isn't actually as trivial as pushing the "fork" button? that requires highly capable leaders, and if the ecosystem were good at finding and promoting that type of leader, then it wouldn't be in this place to begin with.

more optimistically, various parts of this ecosystem _have_ been forked, or reshaped, by various entities. things happen; sometimes that happening is just a lengthy process.

I should be able to get a cheap / run my own 600B param model.

if the margins on hosted inference are 80%, then you need > 20% utilization of whatever you build for yourself for this to be less costly to you (on margin).

i self-host open weight models (please: deepseek et al aren't open _source_) on whatever $300 GPU i bought a few years ago, but if it outputs 2 tokens/sec then i'm waiting 10 minutes for most results. if i want results in 10s instead of 10m, i'll be paying $30000 instead. if i'm prompting it 100 times during the day, then it's idle 99% of the time.

coordinating a group buy for that $30000 GPU and sharing that across 100 people probably makes more sense than either arrangement in the previous paragraph. for now, that's a big component of what model providers, uh, provide.

So, there'll be a one-time, 'Oh man, we spent a lot of money and we didn't get anything for it.'

[RSS] is a standard that websites and podcasts can use to offer a feed of content to their users, one easily understood by lots of different computer programs. Today, though RSS continues to power many applications on the web, it has become, for most people, an obscure technology.

arguing that RSS is dead because the average person doesn't understand it is like saying HTTP's dead for the same reason. neither are dead: we've just abstracted them to the point that they're no longer the front-facing part of any interaction.