The whole saga is kind of nuts, but the thing that fascinates me most is that Fable got this far and then hit some kind of guardrail; I'd be very curious to know what it wasn't able to do that caused it to downgrade to Opus.
It already got extremely... invasive? It didn't do anything that I wouldn't have approved in the same case, but it's interesting that it got as far as launching browsers, inspecting every open window, and storing screenshots to disk, and then it was stopped by something? I wonder what.
Yeah, Docker Sandbox is in the right direction. But there's a lot of parts that are still not ironed out yet.
How do you package a Docker Sandbox up into an app that can expose UI widgets, with an agent hiding behind them? What widgets is the agent allowed to modify? How do you run a workflow like "give agent all these files, modify the files, and do changeset management on the modifications?"
I'm not 100% sure which part of these will be baked into the application standard format, and which are orthogonal. But current way of packaging up and running these agents doesn't feel right.
I think about this a lot because my startup is building cloud VMs for agents to do code-gen and auto-validate changes, so we have a workflow like:
1. git repo, skills, CLI tools, biz context goes in
2. agent iterates against running dev environment
3. changes go out into git PRs and CI
I think this type of app/agent workflow will expand outside coding use-cases.
I mean, that's kind of a stretch given how popular and well-regarded Claude Code is at this point. They're not perfect but they seem to be the best out there at this point.
> I mean, that's kind of a stretch given how popular and well-regarded Claude Code is at this point.
Popularity here is irrelevant.
Just because the software is "popular", it does not always mean that the quality of the engineering and their choices is the best. Objectively, it's the model that everyone regards as the best rather than their desktop apps or the harness that drives it.
That is why people want to use the model and their subscription in other harnesses.
In this case, the desktop app is evidently poor with very embarrassing bugs and glitches like this and I expect well funded startups with the best engineers releasing very high quality code.
I can tell it's still early days - it's obvious. What they have today actually kind of sucks compared to what it could be. And I use it every day, and get frustrated every day because it could be so much better.
It's popular because they have the best models and they are burning obscene amounts of money handing out tokens via subscriptions (for now) at a huge discount compared to what the API costs are.
Claude Code itself is incredibly buggy and as we have seen the codebase is a complete mess of slop.
They were too late to the party on music players (which people wanted), mobile devices being any good (which people wanted), and cloud services (which people wanted), so now they're going to be damned if they're going to be late to the party on AI (which nobody wants).
A lot of the products they killed were promising, it's just that Google just has no stomach for investing in anything for the long haul if it's not going to either capture the entire market or prevent someone else from capturing the entire market.
Do they have any supported way to export a user's account (e-mail, calendars, etc) for offline archiving yet? I used to have to reset their password, disable their 2FA, log in as their user, initiate a 'Takeout' request to export their account data into an archive, wait until the request was done (between minutes and days depending on the account), download it manually (often in chunks if it was large enough), store it somewhere, and then delete it and delete the account.
I can't imagine that no other 'Google Workspace' organizations want to actually save their employee data rather than irrevocably delete it forever.
A big part of why Stadia was cancelled is because it didn't get traction, and a big part of why it didn't get traction was because of how many people assumed it was just going to get cancelled.
The major differentiating factor that Google has had in every product category is that their products are free and you have to deal with ads (and they monitor your behavior for profiling you and your interests).
GMail and Google Maps were revolutionary when they came out, sure, but the vast majority of Google's products now are... fine? at best? And a lot of their "big products" were acquisitions that they absorbed in order to further the core goal of the business - to organize all the world's information and use it to serve ads to people.
Meanwhile, Google has a litany of products they've started internally, launched, ran for a while, and then let stagnate or canned entirely; anecdotally I've heard that this is because your bonuses at Google hinge on your ability to launch a product and not your ability to support a product, so it's beneficial to get something launched and then immediately leave to go launch another project rather than polish the one you just launched into something to be proud of.
I'm not sure if that's true, but it would certainly explain a lot; if Google launches something and it's bad or it doesn't click, they just give up on it. Google Wave, a half-dozen chat apps that I can think of, Stadia, and dozens of others. Things that Google launched, which had problems or didn't hit mass adoption instantly, and then just petered out and were retired with all of the time and energy and money put into them arguably wasted - products that people wanted, and wanted to succeed, but which weren't revolutionary successes at launch so they weren't worth further investment.
Meanwhile, they (and most of the industry) are pushing AI for some reason despite the fact that almost no one actually wants AI to be the only way that people interact with information.
This all reinforces what I've been saying about Google for decades: they're not creating things that users want to use, they're creating things that they want users to use. Sometimes those things align, but when they don't then it's not worth further investment (except, apparently, AI).
I just don’t think your opinion is shared by most people.
Gmail is the most popular email service in the world, people are always telling me how they prefer Google Docs over everything else and their only competition is Microsoft.
Yes it’s free but there is no other service that I rather switch to, and I actually pay for additional storage.
> Gmail is the most popular email service in the world
That's because it's been around for quite a while, and for a long time it was the best webmail service. It's also free, unlike most alternatives. And switching to a new provider means a new email address, unless you're using a custom domain with Google Workspace (or whatever they call it these days), which is a small minority of personal accounts.
(I gave up on Gmail a few years ago and switched to Fastmail, and like it much more than Gmail. But I'm the rare person who is willing to pay for email, and had been using a custom domain with Gmail, so my non-monetary switching costs were minimal.)
You're absolutely right that Gmail was the best webmail service when it launched, and for some time afterwards. How many people now commenting on HN remember when Gmail launched? Remember how revolutionary it was at the time? Every other email webapp, when you clicked on an email, would refresh the page. Gmail, when you clicked on an email, did not cause a browser navigation. It simply replaced the page contents with the contents of the email.
We're so used to setting webapps do this that we take this for granted, but Gmail was the first email webapp to do this. It's possible it was the first webapp, period, to do this; I feel like Gmail's use of XmlHttpRequest was innovative at the time.
Fast forward twenty years, and what about Gmail is innovative today? Nothing that I can think of. It's mediocre (there are lots of filtering improvements they could make that they aren't making, for example), and everything that made it good has been copied by other webmail clients. There's no particular reason except momentum to stay on Gmail.
Gmail spam filtering also used to be revolutionary and an unsung hero. I haven’t put effort into finding out if other options have caught up with that (because of aforementioned tedium of changing email addressed)
I have had a pobox.com email address (just a forwarding one) longer than I've had a Gmail one, and their spam filtering was pretty amazing too. Even before I set my pobox.com address to forward to Gmail, I never saw very much spam.
Now that Pobox is owned by Fastmail, I rather suspect that Fastmail is going to have the same good spam filtering. Can't speak from experience, though, as I haven't actually used my new Fastmail account yet (it still forwards to Gmail, and so far I haven't switched. Momentum, again).
You can’t beat free. The Fastmail web interface is snappier than gmail. And you can’t beat dedicated mail clients like thunderbolt in terms of workflow.
Google doc is wordpad level with very good collaboration (but that’s mostly what people need). People were fine with typewriters, so they are fine with a word processor like google doc. But it’s not at the level of even Libreoffice or Apple’s page in terms of features.
By any definition of good usability, Gmail is not good and Google Docs are not far behind. It’s not that they are functionally bad, just really poor UX.
That's hyperbole. They have flaws, but at the very least, when they were launched, they were arguably best in class. I'm not sure how much me sticking with them is due to familiarity and muscle memory but I know they won we over purely on merit in the beginning.
As someone who was an original invitee to Gmail it was the clarity of function that was the differentiator. They were “grown up” and acknowledged user agency vs their competitors.
But as others have mentioned, they operating model of Google as a company incentivises creating products but does not incentivise refining it. Gmail has gotten far richer in functionality but at the same time the interface has gotten far less consistent. Their competitors (mainly Microsoft but not only them) also got richer functionality, but they also paid attention to UX. While none are perfect, there are definitely some better than others. Familiarity definitely breeds inertia though, I’ll grant that.
Oh, yes, typo aside (which is the lowest form of critique) it was.
It's not about why this or that person would want to install the MS Office on their Mac (millions do after all). So the pointed flew above their head.
It's about the point that many people having to use Google Docs are doing so because corporate wants them to. (In fact most people using MS Office do it because it's a work requirement too).
> GMail and Google Maps were revolutionary when they came out, sure, but the vast majority of Google's products now are... fine? at best?
Is that... good? I mean take maps -- what more can possibly be done to that product that wouldn't just make it worse? It's done. The fact that's the default choice for mapping and just works is fantastic really. There aren't any competitors doing anything revolutionary either because there isn't anything revolutionary to be done.
Maps is far from done. At the very least it's still riddled with usability issues. One bug-bear I have in particular: when I zoom into a very specifically chosen area, search for a Chinese restaurant, and it zooms out to half the state. Maddening. And it's rife with problems like this.
It already got extremely... invasive? It didn't do anything that I wouldn't have approved in the same case, but it's interesting that it got as far as launching browsers, inspecting every open window, and storing screenshots to disk, and then it was stopped by something? I wonder what.
reply