threecheese

Dig into LinkML; I've been eye-deep in defining an ontology for my life (which I struggle to grasp), and just getting into the tools forced me to learn ... outward. There's so much cool stuff, and now I have a mental model as well as a machine-based thing I can talk to (obv an LLM) having a "shared understanding ".

Cheers. Same. (well, not with mrs frenck- that'd be scandalous!)

This makes the most sense. Meta can guarantee at least that cohort of sites will permit their agents to operate, and all they needed to do was publish a tos update. Some Meta PM is smiling today, in between bites of infant flesh.

I am so confused. You need to pay a tax to ... watch content of any kind? Like a book tax?

Or, is this "people watching broadcast content on devices", or "you'll get YouTube TV for free"?

Pets are OK sometimes! They do need care and feeding, though; some of us don't see that as chores, instead delightful hobbies. I can definitely see the perspective of "there are better things to do", especially if you don't like those things.

Once you really know your keyboard, it's like an extension of your hands. You can fly through those six terminals, and moving your hand to grab a mouse means stopping whatever you were doing. That wall of text is all familiar to me - I see an UI full of empty space and wonder what I could have used it for.

Of course there are great reasons for using pointers also. I'd say this is mostly a preference, I'm sure you are extremely effective using your own methods. I have maybe two dozen terminals open atm, and I can tell you what each of them is for - but put a phone bill or a bank statement in front of me and it might as well be Greek.

Not a reply to TT, but I just saw your nick and thought I'd respond. We both commented on a thread recently, and your response was really insightful and just a pleasure to read; I didn't take the opportunity to respond there (locked). You should, like, write a blog, man. I infrequently wish HN had a "follow" feature, but this one of those times. Peace.

ref: https://news.ycombinator.com/item?id=49768575

1. Entrenched in-company interests create friction by just existing - Ops/Risk/Support/Arch/ProcessEng. Staffing is on the knifes edge, no buffer. And so going fast $here makes you slow $there. 2. Customers expect defect-free software, and compromising quality == churn == revenue loss. 3. Token costs are already astronomical, and everyone who could already cut headcount. 4. Mythos scared the shit out of everyone, and every last cent is allocated to Enterprise Risk (another entrenched friction).

It’s a lose/lose proposition for every software company with more than three management layers. We're frozen in place.

I think there's a type of company for whom this works; a small team really can deliver a massive volume, but it cannot be constrained by your typical software bigco superstructure. Ops/Readiness/Process Engineering/Enterprise Arch/Risk etc, entrenched concerns with soft power through pure delivery friction.

You need to be an an org who is able to deliver directly to your consumer, who needs to be defect-tolerant with the expectation of quick iteration. That customer will have access to advanced tools that its competition is unwilling to adopt. Many will fail.

There are many verticals for which this does not work at all - but this is unlikely to be the permanent state. The new model will work its way through the market, and companies will fall as fast-moving competitors find a willing customer segment they can target, make that segment out-compete the others using their access to tools with superior abilities but higher defect rates. The customer base will eventually adopt, having become accustomed to this, and so slowly expectations will change, and so will our field.

I for one welcome our slop overlords.

If we released software with the number of defects in the popular coding tools, we'd be out of business before the end of the year. But they persist- for some verticals speed matters over quality.

I can't believe OP here. Where are these software teams, are they in the room with him? My teams are more stressed than ever: leadership doesn't understand why they aren't 5x more productive - even if they were 1.1x more productive, the ops teams aren't scaling, the defect management isn't scaling, the guy yelling about their Jira ticket status updates is just getting louder, and they are being pressured to reduce token spend while pressured to release more software.

Some motherfucker today suggested we should use Haiku for all coding tasks, and this guy is a Sr Director of real humans.

Same. I've spent 20 years trying tool after tool and finding some part of it unfit, some stupid edge case for my broken brain. I have so much of my own crap now that I'm building new crap to manage the crap. If my professionally-sourced anxiety wasn't eating my stomach lining I'd be having a great time!

It's all being built to try and capture the value of creating the new, good software. Aka a cambrian explosion of developer tools - primarily used to create developer tools and twitter attention - so people use your developer tool to create developer tools. And wikis - thanks to Karpathy, we now measure Obsidian clones by the gross.

In my professional life however, we are NOT producing more software ($bigco). We are on the edge of it maybe. My experience is we've been on the razors edge - just enough staff to meet the business needs - and so every AI iteration sped up some process, which exposed some limit in a dependent process, which we tried to free up with a reorg, which cut capacity somewhere else, and the snake eats its tail. We've had enough iterations to get to a place where an increase in developer output probably won't cause the whole thing to fall over. I hope.

But anyway, I spend a lot of time exploring new dev tools, it's sort of a hobby of mine; I like to understand the state of "what's out there" and this has helped me professionally. This has recently become impossible do the sheer mass of llm productivity, while at the same time more fun than ever; the amount of crazy interesting and seemingly mature brand-new things (in the dev space) has astounded me. I found Swamp Club recently, like wtf where did this come from? It's like five dudes with LLMs.

In this analogy, a programmer who cannot understand their workload is like a rug QA tester with eyes but not feet; or a safety inspector who doesn't know that the red dye is corrosive to skin, or that corrosiveness is possible, or even that it exists as a concept. Or that the "red" is a dye, and what a dye does.

Currently, learning programming is the lever to unlock architecture understanding. We will need a few new layers of abstraction before this changes.

As a non-js developer, Bun compiles my ts code to local executables nicely. Allows me to experiment with the new diversity of ts frameworks and distribute the binaries (hobby scope).

All sorts of good and interesting arguments ITT, but at the end of the day it's all academic; companies are going to compensate by offshoring. I doubt this nets us more citizen-jobs, pressures salaries to increase, or provides any benefit other than the messaging to the base.

This tracks with what I've observed, as a fan-and-sometimes-user. They look to be funding a skunk works - which started with their version of Cursor (Jules or something), which wasn't great.

They are working on a cli agent; I tried it, but it silently injected hooks into all my other cli agents to re-target JB inference APIs, which caused me to burn through my JB tokens in like two minutes and b0rked all my running agent sessions.

They are working on a spec-driven thing, which I attempted to try but getting burned by the cli thing I abandoned it. It looks really interesting - it's a meta-harness, built and shipped with one of the Spec-Something frameworks, where you define your own specs for your projects, kinda like snake-eating-it-own-tail-of-specs. If spec-driven is The Future, they are at least trying.

There have been a few other things I can't recall, but my observation is that they are taking generative AI seriously as an existential threat, and probably (as another poster here put it) "heating the office burning tokens".

Counterpoint, if you give the agent access to your files - which happens to include the Notepad diary you've been writing since your teens - and it makes a similar conclusion about something you privately wrote, would have the same opinion?

The value proposition for software - and the reason why it's highly paid and has eaten the real world - is its "write once run forever (ish)" property. Unlike every other consumable, it doesn't expire.

In this proposed world where this static software is replaced with dynamic software ("AI will build it JIT"), doesn't that destroy the value proposition?

And in the world where normal software becomes AI-integrated ("software has intelligence "), isn't this tantamount to very very high hosting costs - where each execution now costs centi-dollars instead of nano-dollars?

Seems like the only use case where the cost model is equal or better is "AI writes the software".

Looks really cool! I'm not sure which architecture choices ruled out agent subscription plans, but you should reconsider (unless enterprise is your target).

There have been a few very good harnesses - like Amp, which is excellent - which made this same choice and just haven't had the adoption they deserve.

Is there a middle ground , like where the "main" agent uses an API, but delegates using provider mechanisms (claude -p et al)? I don't mind paying for intelligence, but coding agents are expensive and at this time I am nearly exclusively using subscriptions for them, until the math (inevitably) changes.

I agree. I am a little envious of people who are willing to use Meta products; muse is pretty cool.

I had the same opinion, until technology met its match: my wife.

Her and the Apple Lady talk quite a lot. It's really useful, and we barely use the phone anymore (light switch is even rarer).

As a paid Synergy user, there are tradeoffs (as you probably know). I'm willing to accept these for a side-by-side Mac workflow (or Mac + something else), where each host has a dedicated display.

For a workflow where you are also display switching (kvm etc), Synergy doesn't work well. You can technically use it when hosts are coming on/off display, but it's not designed for it. If you use a kvm-like workflow and have a Magic Touchpad, there's no easy solution without re-pairing, and I hope OPs tool works for this.

Your iPhone was definitely transmitting identifiers which can be passively retrieved, via BT for example. These aren't directly tied to your identity, but announce that id-0001 was in Germany.

It's not beyond reason to guess that you stumbled into some niche ad targeting group, like "US grape juice drinkers who've visited Germany", and your old email identity was transitively linked somehow. Maybe ten years ago that email was about grape juice?

Is there any conceivable active or passive property defense here, given they may capture inside private spaces (open doors, windows etc)? Assume "expectation of privacy" was defined in a different world.

Something like IR emitters, infinite-crawl QR Codes, IR-only nsfw content, lidar to damage sensors but not eyes, something fun.

It's table stakes for using Anthropic APIs cost-consciously. They aren't building a minimal harness for nerd points; they are building it to be usable, and dogfooding it with Real Money to learn what that means realistically.

This might've made a better argument ca. 2005 wrt a 20-something Austrian's minimalist wsgi framework. Heck, I'll bet you could even find said argument somewhere in the Archive :)

How do you trigger this? I've been messing with OMP lately for funsies.

Can you elaborate? I've been getting great usage out of my $200/mo plan, and thought I'd try a reset (first time) which was expiring just for giggles. Am I going to get only 20% of it effectively?

I overused Astra in order to drain my weekly, figuring I'd have the reset. (not wastefully, I did get more work done)

Is anyone leveraging IRC/XMPP/etc for agents or A2A communication? It seems like a natural fit; all the "human agents communicating" abstractions and underlying technology pieces are in place and mature, as are methods for dealing with unruly actors.

I've wondered why I haven't seen this everywhere.

Does this need to be shipped with a renderer? A better question is, are the node layout instructions ultimately being translated into absolute positions?

If so, you could target any number of render backends, keeping the same simple interface for your agent, avoiding the bazillion problems rendering engines face to work well across the ecosystem.