Bishonen88

> Frontend design defaults

> Asked for frontend work without design direction, Claude Opus 5.5 falls back on a few default styles, and a general instruction such as "avoid a generic AI look" mostly swaps one default for another. It responds well to instructions that name specific patterns to avoid, as in the following example. Work iteratively: check which styles the first result used instead, and extend the list if needed.

I hardly ever read tips for prompting etc. because things change too quickly, the writeups are kindof big. Glad I read this one, because I often did exactly what they assume users would do. I write "don't make it look like generic ai slop" and that seemed to work nicely. Now I know why there was still a chance of seeing similar styles across apps. I reckon doing some manual work in terms of scouting dribbble/behance for nice layouts will yield better results.

A 5min 'best running shoes' session would mention both Hokas, ON's etc.

That's an anecdote, not a bubble in my opinion. I have a counterexample where I have not worn any Hoka's but have seen/known of them. Have multiple pairs of On shoes.

Gave it a quick go as I'm looking to adopt some sort of fitness app. There's too much text/complexity for my taste.

The website could use some images/simplification to get going and then have more details and whatnot later on. It seems that you let the LLM generate the content itself (em dashes, emojis) - Personally I'd be skeptical of a fitness app that has most of its content LLM'izied.

On step 3 of the tutorial, it's not clear that you can scroll down and there's more there on a mac 16''. I was confused what to do. It didn't allow me to change to metric system either (which I later found in the user-settings). You can't 'esc' from the tutorial popup either.

But this is not AI coordination saving traffic. It's 'sharing economy'. And its already here and it sux. All the bicycles which can be borrowed for a few cents per minute didn't replace personal bikes, anywhere, I think. At least in Germany they created many problems for what seems a tourist convenience. Even worse with scooters...

Same with car-sharing. In theory good but in practice I'd rather own my car 100x than finding a car, making photos to record any damage, handling rubbish from others etc.

For pro gaming perhaps the difference would make the slightest difference. For casuals, let alone office workers, the difference is 0 (writing this with a mx master 4 next to me).

Saying this as someone who has tried dozens of mice in my life. Last corded-one, bought for my son yesterday (razer cobra minecraft edition). I don't think I'd be able to tell the difference between wired and wireless in a blind test.

what? especially the bags part seems crazy. Easy to imagine what happens when we stop screening bags...

Counterpoint: use intellij on full stack apps with cdk, react, sqls and whatnot, multiple open at a time, without any problem.

> ...That is the realistic "install Postgres and go" baseline. RDS ran on its default parameter group, which AWS tunes for the instance size. Hostim runs its own managed tuning. In other words, the two managed options are tuned out of the box and the self-hosted default is not, and that difference is part of what you are comparing.

So... useless comparison vs Hetzner? Akin to comparing two laptops on a compile job, but leaving one in battery saver mode and then concluding that its 2x slower.

yes, I'm getting paid handsomely for delivering software faster than every before, using llm's. If you mistake that for marketing, then so be it.

This is as unhelpful as it gets. The genie is out of the bottle - people can create unimaginable things with claude within hours. What would take months/years can be done in a day or a week.

Being banned on those platforms is a real setback for many users. One might argue that openai etc. are valid alternatives, but when they dropped fable (and perhaps reinstate?), not being able to use it simply means others can do more/better.

yup, same thoughts here. I think someone is trolling the irc members. It's so over the top, like an episode of 'the office'. I'd be amazed if this were an honest message.

13x 'not ' found in that article. That's what AI's love to write.

This article on the other hand has 1: https://routerjockey.com/introducing-graphiant-the-future-of...

I don't mind either way, but reading through the Tim Cook one without opening the comments on HN, I was 99.9% sure I'm reading AI.

you might be biased due to your employment :)

Probably you're right, but given the browser usage-distribution, I reckon most hackers wouldn't care about firefox at this point and solely concentrate on chrome. I reckon firefox users are on average, more tech savvy and given a hack, would be able to help themselves/find out about the hack quicker than the average chrome user.

While the text seems to be at least AI-supported, I think the research is still interesting. Whether that was done mostly by the author or an AI still, does not change much to me at least.

I'd appreciate some sort of disclaimer at the start of each article whether it's AI written/assisted or not. But I guess authors understand that it will diminish the perceived value of their work/part.

FAQ: Is it available worldwide? A: Yes. (...) outside the EU.

So, yes but no. Not that I care, but the answer to the above question is a no, and should start with No.

Having developed multiple react web apps from scratch over the last 5+ years at work, I always start with a fresh repo and add what I need myself. Nowadays, booting up a project with vite, eslint, prettier, redux (and rtk-query), tailwind etc. takes no time at all. Don't care about SSR. Am I missing something by not using tanstack? LLMs tell me many things, all of which seem irrelevant (e.g. not using react router, SSR, request-deduplication etc. which are covered by the basic few deps I added)

what percentage of people is using local models for anything serious? I reckon single digits if even that. And for a corporate work environment, probably close to 0.

Amazon.de for example already has it(for preorder). Oreilly books online has the first edition available right now. I reckon they might add the second revision when it comes out.

It's right there on the page. Age 10 and above

Didn't realize who's blog I'm reading. I was intrigued by the title, being a fan of 'self help' books. I mostly read about productivity (i.e. Feel-Good Productivity is a good one IMO), health, living a balanced life etc. and was expecting to find some a-ha moments in this post. I didn't. It confused me more than anything often talking about 'relationships' as if this is the only self-help kind of book there is.

And I have learnt a ton of lessons from self help books like the one I mentioned above, Arete, "how to make friends and influence people", Atomic Habits and others, without looking to fix any unhappiness, flaws of myself or whatnot. Was just curious what other, more experience people have learned about life that I can learn without having to wait 20-30+ years.

I get your point. But if sharing with others is a vital part of this, then ... they'd be better off sticking to web apps instead :) "Create with glaze, hit publish and we'll give you an url".

Even though they portray some of the benefits of this app as unique to desktop apps, they're not (e.g. storing data on device, offline mode etc.).

Am not a hater. Love Raycast. Saw the post and opened the link intrigued what they came up with and was somewhat disappointed tbh. Good luck to them anyway!

So, another wrapper around claude 4.6 for +xx% higher price? Using just claude code, one can do what glazeapp seems to aim for, no? "Beautiful by default" seems to be a system prompt akin to:

  Design Philosophy Create apps that feel premium, polished, and worthy of being featured on Dribbble's most popular shots. Every pixel matters. White space is your friend. Less is more, but what remains must be perfect.

  Visual Design Principles

  Color & Theming

  • Use sophisticated, limited color palettes (2-3 primary colors maximum) ...

You're right of course. For me the difference maker is in seeing on a projection chart that if I just cancel 2x zwift, disney and netflix, I can save up to:

Savings from Cuts

€11,048

€60/mo @ 8%

within 10 years. That's HUGE! While the 60 Euro a month seems kind of irrelevant on its own.

Dunno about that. Having used the $20 claude plan, I ran out of tokens within 30 minutes if running 3-4 agents at the same time. Often times, all 3-4 will run a build command at the end to confirm that the changes are successful. Thus the loss of tokens quickly gets out of hand.

Edit: Just remembered that sometimes, I see claude running the build step in two terminals, side-by-side at nearly the same time :D

great idea. thought about the waste of tokens dozens of times when I saw claude code increase the token count in the CLI after a build. I was wondering if there's a way to stop that, but not enough to actually look into it. I'd love for popular build tools to implement something along those lines!

hindsight is 20/20. If I'd known that Nvda, Aapl, Amzn etc. would go up, it's easy to now to regret how much money we'd have. Same thing with "RSU's" we get at FAANG. I often hear from coworkers that if they wouldn't have sold them when they got them, they'd be rich right now. Yes, they would be - but in an alternate universe, they'd have little/nothing and wouldn't have bought the car/camera/vacation they got out of the money when they sold the RSUs.

I added something related to this idea to my life-planning app: what if for projections. I track all my expenses/incomes/investments in my app. I then can with 1 click run a scenario where I move certain expenses to investments. I.e. cancelling netflix for 10 years, or xbox gamepass etc. and seeing what it would actually do to my 10 year projection (which already accounts for ETFs/Stock with variable return rates etc.). i.e.:

Exclude Recurring Expenses Simulate cutting these expenses and investing the savings Redirecting €19.99/month to investments

Then I see black on white what would happen if I get rid of all the 'small' subscriptions, on a visual chart. It's eye opening when one selects items that add up to a ~100 Euro ++ a month.

I get your point, but just out of curiosity, what is 'reasonably productive' in that case? E.g. compared to speed/efficiency/ease of coding/developing/researching on PC, would you say you're 20% of that on your phone? I reckon for me the number is like <10%. Just typing code on a phone is a chore. Having browsers open on another screen, splitting terminals, ssh tunnels and so many other things make any form of using mobile phones for what I use my pc for is a literal mental pain and thus I don't do it. I'd be better off doing additional 5 minutes on my PC instead of doing 50 minutes on my phone (and I have a foldable one lol).

I know everyone is different thus my curiosity about other peoples experience!

Custom AI tools like these have an uphill battle to fight. Automaker[0] from webdevcody is an example of that. He, together with some other folks created an open source Agentic Coding tool (for the lack of a better term), which gained popularity on github. He was advertising/showcasing it on streams etc. A few weeks in, he posted a video[1] where he speaks about why he's not using it himself anymore and went back to Claude Code, which over time receives tools/skills/mcps/whatnot and is in the terminal which we're all familiar with.

I made similar experience. Downloaded all sorts of tools, IDE's for the new era of development. Other than claude code in cli and occasional uses of codex (because have free tokens), nothing else stuck. I can just split my terminal effortlessly how many times I want, write/speak to the terminal with any custom request etc. And once someone comes up with a clever idea on top of what claude has today, I reckon they'll add it one way or another within the next weeks.

bayesian curve meme fits here rather well:

- claude code for everything, custom IDE's/tools, claude code for everything.

[0] https://github.com/AutoMaker-Org/automaker [1] https://www.youtube.com/watch?v=3H_t78QcueA&t=382s

Of course its not near as good, but that's not the point - it's meant to supplement normal development, not compete with it. The idea that one can be nearly as productive on a mobile phone as on a pc is a fairy tale. Best example is the github app which functionally might be ok, but is unusable for e.g. looking at the source code of a repo in any meaningful way (IMO).

There's plenty of situations where one doesn't want to stay at the PC for AI to finish its thing. Now we can just go about our life and check in from the phone. IMO great feature. Would've used it many times in the past but didn't want to be bothered with some wrapper around CC that perhaps did it already.