Huppie

Thanks for the great work!

Even though I delegate more and more to coding agents I've stayed with Svelte(kit) for any project where I can choose. It's always been a breeze to work with coming from an Angular background and (imho) the average quality of the resulting code (quality of training samples I guess) is just better than with most other frameworks I've seen.

I totally agree with you bundle size and performance matter and I look forward to working with remote functions.

All this to say: Congrats on the release!

Just kicking off a subagent does this automatically...?

My main conversation is usually with an orchestrator that hands off work to various (usually cheaper) subagents to plan / review / etc. It has instructions to find the correct model for each task and not to do too much itself so a multi-phase plan automatically gets a fresh subagent for each phase.

Not OP but will definitely have a look.

I have some older projects that use beads (I still run an old version without dolt that's imho pretty good overall) but lately with Fable also have a few newer projects where I just have the agent write docs and keep a worklog with the what/why/decisions etc. (I think I read it here on HN somewhere and figured I'd give that a try.)

The latter seems to work pretty well for now (slightly better than beads) but I'm always looking for ways to improve it. This could be an interesting replacement.

I have a Claude Code hook that calls codex for a code review on commit time (Codex is set to Astra Medium) and it's been pretty good in general. It sometimes hits the 5hr limit but most of the time it provides really good feedback and because it's a completely different model it's mostly complementary to what Fable/Opus do themselves. IMHO it's been $20 well spent.

...but the few times I've tried to use codex for a moderately difficult task it burned through its limit extremely quickly.

Not OP but the way I read it...

Electrician: "Okay, so my services start at $100/hr"

<nobody bats an eye>

Electrician: "... for when my assistant can handle things."

Replace Electrician by whatever skilled professional you prefer.

Just taking one of your prompts and adding

> N.B. Make sure all the important information pops out (is visible at first glance) like an expert designer would, the information is more important than the design.

Already have me a much better result with the 'Arts & Crafts style', but N=1 so YMMV

I do recognize your use case and think it is a better solution than a WhatsApp status update. However (at least in my friend group) the friction of getting people to install yet another app is also very high.

Having said that, once there's an Android version too I'm definitely going to try if I can get a bunch of friends to try it.

Not the person who wrote that reply but their reply immediately clicked for me.

Here in Europe basically everyone uses WhatsApp. So you might as well just place a WhatsApp status update writing something like "We're doing X this afternoon? Wanna join? We'll leave from [location] at [time.]" and basically everybody in your contacts can see that update.

It's not perfect (different privacy model, a lot more people can see the update unless you have a very curated contacts list) but no friction of getting people to install another app.

Edit: Also no notification for status update, so slightly different model that could solve the same need.

If you don't care much for display quality (or are willing to pay significantly more than what you'd be paying for a TV) that's doable.

I've tried finding a monitor big enough and with a decent panel for anywhere near the price of a TV... it's nearly impossible.

Then I tried finding 'dumb TVs' with at least somewhat decent panels... also almost impossible.

In the end I just bought a decent Philips TV with a good panel and 'Android TV' and chose to never connect it to WiFi and activate that (run it in dumb mode.)

It had enough HDMI ports to hook up everything I want and was the best option available. Would I have preferred a 'dumb screen' with a bunch of HDMI ports and no TV tuner at all? Yes.

I feel so incredibly lucky I chose to overdo it a bit on RAM when I upgraded last year... though I remember deliberating to go for 192GB (it's 96GB now) but motherboard support was somewhat more complicated and it felt like a waste of 300 euros...

Not a diagram but the section on page 9 regarding who's considered the manufacturer is relevant here. For generic packaging that's the manufacturer of the packaging.

Under definitions (page 9) there's a big section > 6) Who is the ‘manufacturer’ of branded packaging? NEW! And it starts off this blurb: > According to the PPWR (Article 3(1), point (12)), if a packaging does not bear a name or trademark, the manufacturer will be the natural or legal person who manufactures packaging or packaged products. Seems pretty obvious to me the generic bubble envelope example from the blogpost doesn't make sense because that is generic packaging where the manufacturer has to handle this.

Under definitions (page 9) there's a big section

> 6) Who is the ‘manufacturer’ of branded packaging? NEW!

And it starts off this blurb:

> According to the PPWR (Article 3(1), point (12)), if a packaging does not bear a name or trademark, the manufacturer will be the natural or legal person who manufactures packaging or packaged products.

Seems pretty obvious to me the generic bubble envelope example from the blogpost doesn't make sense because that is generic packaging where the manufacturer has to handle this.

Edit: The farmer example is a bit bad imho because produce is not like the products in the blogpost and 'under its own trademark' applies to the product packaging (e.g. custom Apple carton frames etc.), best to focus on the more applicable sections imho.

Yeah, I remember seeing both kind of machines. IIRC For the competitive scene string setters were (are?) a no-go but we installed plenty string-setters on holiday parks because they're just more economical.

I remember some classmates interned working on new / different firmware for the machines you're talking about though. Fun project for an internship!

Back when I was in school I interned at a company installing bowling lanes / machines. Even back then it was fairly simple technology, no cameras or speed measurement yet, just some inputs from the machine as to what pin-cords had been pulled out (i.e. what pins fell down) translated to some simple animations. I remember the screens being just a simple VIA motherboard running DOS + their software from a compact flash card.

Sounds like a great project to work on given how cheap both hard- and software is becoming. Wishing you all the best!

N.b. The forces in the machines can easily break hardware so be sure to move it away from the machine if possible, and otherwise protect it appropriately.

Not OP but in my case I've been using this setup for quite a while (well before Claude remote control was a thing), this works with any other tool / ssh session.

I'm not entirely sure there's a big advantage to Claude remote control to be honest. Maybe it's just me being afraid of lock in (I do switch between Claude and Codex somewhat often) and/or the inertia of changing things up that keeps me from trying it.

Subagents indeed. This [0] was the post I was referencing, and here's the original suggested prompt:

> For all coding tasks use your judgement to decide an appropriate lower power model and run that in a subagent

As said, I tweaked it a little bit to my preference (mostly because it started delegating a bit too much) and had it placed in my global claude.md but that's the gist.

[0] https://simonwillison.net/2026/Jul/3/judgement/

Simon Willison recently had a useful tip instructing Claude to use its judgement to pick an appropriate model for tasks.

After a short discussion about the idea with Claude mostly on how it fits in my workflow and what models / effort I would like for certain tasks it placed a paragraph in my global Claude.md and it has worked wonders. Ultra became a lot better (faster, cheaper for the same output) and the amount of time Fable gets stuck overthinking things are reduced to the places where I think that model makes sense, for the rest it started fanning out a lot to Opus, Sonnet and even Haiku.

Maybe you missed the 'or sent to private cloud' part of the announcement, it's not just local-llm only.

Don't get me wrong, just like you I personally would also prefer LLM-integrations with a privacy-focused provider and I think Apple is a good party to get that from (assuming they're using good models and keep their privacy guarantees here...)

But in the end you're still often 'sending data to an LLM provider', and the EU enforcing them to also let that be competing LLM providers still doesn't sound like a bad thing to me.

If Mistral would give the same privacy guarantees: great! If a company wants to use their enterprise OpenAI subscription: great! Etc. etc.

Let's allow for some competition here and not force a specific LLM-provider onto users just because they like the Apple hardware and software ecosystem.

We may have a different view of what 'giving access' means in this context.

The way I see it: If a user willingly (1) installs another AI app like deepseek and (2) willingly gives it access to 'full phone and app data' with a warning screen or setting of whatever that seems... like a good thing?

I may not agree with those users that it's worthwhile providing their full private data to [some AI startup X] or [Some Chinese or US AI company that will hover up as much for their own use] but if the EU forces Apple to provide this as an option, that sounds good to me.

The whole point of the regulation is that the data on the device is _the user's_ data and if Apple can have its AI services work with the user's data, competitors should be able to do the same.

From my (admittedly European) perspective it looks like Apple is just throwing a tantrum here.

I remember a recent episode of the Rational Reminder podcast about this, it's not as bad as it may look...

https://youtu.be/QaQHdF2DeRY

The Swedish one was linked on the Belgian map: https://swedish-mail-dependency.netlify.app/

Not the person you responded to, but for a current monitor you could look at e.g. Shelly devices.

I have a Shelly Pro 3EM three phase current meter device on my home battery connection just to get more accurate data into Home Assistant because the battery provider doesn't provide it. (In hindsight I should've bought a different battery install but that's not something I can change after the fact...)

With the back and forth refining I find it very useful to tell Claude to 'ask questions when uncertain' and/or to 'suggest a few options on how to solve this and let me choose / discuss'

This has made my planning / research phase so much better.

More recently I've been doing the implement phase without resetting the whole context when context is still < 60% full and must say I find it to be a better workflow in many cases (depends a bit on the size of the plan I suppose.)

It's faster because it has already read most relevant files, still has the caveats / discussion from the research phase in its context window, etc.

With the context clear the plan may be good / thorough but I've had one too many times that key choices from the research phase didn't persist because halfway through implementation Opus runs into an issue and says "You know what? I know a simpler solution." and continues down a path I explicitly voted down.

imho they're mostly better at a subset of different tasks. I find codex to be better at reasoning through bugs and reviewing code when compared to Opus, but for writing code I find Claude a lot better.

Maybe that's just CLAUDE.md and memory causing the difference of course.

As a matter of preference however I like the way Claude Code works just a lot better, instructing it to work with parallel subagents in work trees etc. just matches the way I think these things should work I guess.

Man, the iPhone 15 Pro is the absolute worst iPhone experience I had thus far, really makes me reconsider if I shouldn't just get a cheap android next time. Most definitely not worth the premium.

To be honest I'm mostly fine with the price increase (it hasn't been adjusted for inflation in ages), the thing I do take issue with is that for over a year now (with the 'upgrade' to a new web interface) you can't easily create a password etc. anymore straight from the browser extension.

You click the button in the browser, choose what to create 'I want to create a password (or a note, or whatever)' and then get redirected to their web-app and be presented with a pop-up asking what you want to create (I just told you, didn't I?)

I get it, when you move to a new web-app some things can break. But after using stored passwords creating new ones is pretty much the only other thing you do in the app, it seems to be core functionality that's been broken for over a year now, it's kinda madness tbh.

Edit: To be fair they offered a 'solution' when I reported it: "Don't use the web-app, install our desktop app instead."

Funnily enough I've been using Codex 5.3 on maximum thinking for bug hunting and code reviews and it's been really good at it (it's just seem to have a completely different focus than Opus.)

I generally don't like the way codex approaches coding itself so I just feed its review comments back in to Claude Code and off we go.

Yeah, totally agree. Maybe it can inspire your app too, wish you the very best and a lot of sales.

Some of the hidden features:

- If you add a task to a routine and end it with a question mark it becomes a conditional where you can add specific tasks or subroutines on the yes or no condition.

- Make it 'weekday?' and it becomes a switch case for the week.

- 'is it 7:30 yet?' becomes a conditional that automatically detects if it's before that time. I use it for e.g. 'before breakfast' (at 7:30) -> go play (with a timer until 7:30)

N.b. 'fun' fact, my daughter wanted an avatar with clothes that you can earn. The idea was pretty easy to implement but getting nano banana (using a great Claude nano banana skill) to generate the correct images took... some practice. I think I spent more time on the images for the avatars than all the other features combined. It took way too long to realize simple stuff like "nano banana won't generate transparency, only a fake white/grey checker pattern"

Also learned the last iPod touch (great device by the way) has a really low screen resolution which can be quite challenging at times.