"Available on Pro plans. Maybe. The only thing I can tell you for sure is that Terms and Conditions will change tomorrow. Still can't differentiate tabs and spaces[1]."
Is it a bit ironic that, while I certainly believe the author did not use gen AI to create this post, it reads like the most mindlessly AI generated post ever?
What I find ironic is that "this reads like an AI" is a phrase that is rapidly losing its meaning, partly due to advances in AI, but also because it's being worn out, just like every other generic phrase used to dismiss someone's work out of hand without providing any additional context.
Some of that, sure. But realistically, a lot people are just don't want to pay for every frontier model provider out there as they're released. Not just money, but also time trying them out. (Recommend people at least try out their multimodal model.)
It doesn't help that Google offers a bunch of confusing plans in multiple places. I ended up just pasting all their AI plan URLs, at least that I could find, into Claude so I didn't have to figure it out.
I pay for Google Workspace, so pretty much the Gemini Pro included with that suffices my use case. I can't say it will work for everyone, but I do use it for random tasks - all the way from wood working to building complex software projects, and so far I've rarely hit the limit too.
I guess it's access to Gemini, because that's the plan I'm on and you can access Gemini using gemini.google.com or their phone app (Android/iOS). I couldn't find information on the API, maybe it's on that page, but I couldn't find it from my phone browser. Anyway, I use OpenRouter pretty much, so I have no idea if the API is part of my plan.
I think Antigravity w/Gemini is a great product; it's been super useful on a bunch of my hobby projects. It's especially wonderful when writing firmware and needing to add support for a new chip. I can point it at a PDF datasheet and it'll do a much better job of reading it and parsing out all of the register fields than anything else. Saves me enormous amounts of time.
Thanks, been meaning to try it. I heard the limits on that is an issue and people are supposedly blowing the limits off way too easily? How has your experience been so far in this regard?
Yeah, in most threads you will see anyone recommending Gemini be downvoted. Ironically, Gemini (with Workspace subscription) is the only model that explicitly states it doesn't use your inputs to train their models right under the chat box. AFAIK no other provider does that explicitly - usually there is a hidden toggle in settings you will need to turn off.
TIL. That's cool. I mostly use Gemini 3 Flash for some background jobs because of the price/perf, but rooting for their models to improve. Competition is good.
I've finished (as in: it's done, it works, and I may never need to change it again) entire projects with ChatGPT and Codex. Sometimes it takes a lot of hand-holding to get there, but it does get there and (with the exception of 4o) it's been improving since the beginning.
In contrast: I can't even get Gemini Pro to give me any answers to the most primitive questions that aren't caked in prima facie lies without at least 4 interactions, in any context, ever. The output is consistently and ridiculously garish with its insessant self-contradictions. It seems to be impossible to actually get anywhere with it.
From the repo, it signs natively on macOS and falls back to a cloud signing server (shortcut-signing-server). That fallback matters -- without macOS you would have to reverse-engineer Apple signing format yourself, and it changes across iOS versions. The hosted signing server is really what makes the whole cross-platform toolchain viable.
I’m not familiar with 2 of these 3 stories so I’m mostly just impressed by the RL turnaround (4 hours!?) and sharing knowledge on the fly off using fine tuned models at scale.
For the gossipy part, I love Kimi, but find it hard to get worked up about them not labelling their model Kimi when Kimi was the base. Especially because Kimi…has had…some issues…being able to distinguish itself from Claude…
I don't though it works and these guys are raking in the money.
The wider audience of devs or people paying up for Cursor don't care about the morals old school OSS devs hold.
It’s one of those slick apps designed to superficially look nice without actually being well-thought-out. That’s not what design is or should mean; that’s just aesthetics.
Case in point: one of the most important pieces of data for a flight, its duration, is displayed in the tiniest type size on the flight info display pane, in light grey text on a slightly darker grey background. It’s bordering on illegible.
It also doesn’t surface boarding time (or countdown to same), which is the single most important piece of data a flight tracker can give you.
> one of the most important pieces of data for a flight, its duration
Flighty is all about getting you to the airport in time for your flight, so the most important pieces of information are things like departure times, connection times, delay information, terminal and boarding gate. These are prioritised in the interface.
The flight duration is set when you book the flight and it's not going to change, there is no reason to prioritise this.
> It also doesn’t surface boarding time
I think this would be useful but difficult data to get. Airlines sometimes will push boarding announcements to their own apps but I doubt they would agree to feed Flighty.
My guess is that's because boarding a plane is a little bit like being an extra for a film, it's a hurry up and wait situation. If they printed the exact time boarding starts and people showed up then (and later), no flight would ever board on time. Better for the airline to print an earlier time and have people wait longer, so they can board as quickly as possible. Every minute behind schedule costs the airline money.
AA displays the boarding time in the app instead of the departure time once the flight gets close enough (like same day)
>If they printed the exact time boarding starts and people showed up then (and later), no flight would ever board on time
I don't understand the logic. If everyone is there at the stated boarding time and the airline has correctly allocated enough time for boarding, aren't they winning?
200 people can't board at the same second. Reality is you want orderly boarding over the course of ~ 10-15mins depending on passenger makeup. Crew also need to account for passenger with additional needs, catering recharge, etc
Just don't try this on Ryan Air. A good friend got stuck at the airport on a Sunday night after being denied boarding because he waited out the standing line sitting on a bench right by the gate.
As soon as the last person standing walked through the checkpoint the gate crew closed the gate -- and completely ignored my friend when he showed up 10 seconds later.
How did his actual boarding time match up with the contractually agreed boarding close time?
Most budget airlines pull this crap but I've started pushing back especially when it's poor weather outside and they expect us to wait in the rain just to improve their metrics
They need some EU261 denied boarding threats/claims to sort them out
Why is duration important? Surely you already knew what it was when you booked and it's not like it changes. I can't say that I've ever wanted to double check the duration of my flight.
Knowing when I land, especially if there are any disturbances, is probably THE most important piece of information with regards to a flight. I have already planned my airport arrival, at least for the first leg, and the worst scenario is I have to stare at a screen/book for a bit longer. If the landing is delayed I might need to make amendments to the plans for the rest of the day.
The complaint is about the visibility of the flight duration (e.g. "this flight will take 1h 50m"), not the landing time (e.g. "this flight will land at 11:25am"). The landing time is prominently displayed in the flight info pane. Knowing your flight duration (gate-to-gate time) is not impacted whatsoever by flight delays, so I think you're conflating these two things inappropriately.
I think the design is great; my only gripe is it's awful on the iPad mini. But so are Apple apps. They think it makes sense for the side drawer (in portrait mode) to cover half the screen. Which is especially insane in apps with maps where the drawer COVERS THE "YOU ARE HERE" DOT.
I regularly fly all over the world, and it's nice to know how long my flights are going to be? I'm not always flying direct, and seeing the lengths of the legs and the lengths of the layovers allows me to plan my day and my sleep schedule.
You do have landing time for all of the legs? That’s more useful than duration. For your sleep, you care about landing says, at midnight, as oppose to a 10 hr flight from Paris that may or may not arrive during day time at the destination.
No, duration is far more useful than landing time when my basic desire is to know how long I’m going to be on the plane. A 2h flight vs a 6h flight is a huge difference in experience. Also, landing time is given in the destination timezone, which does me no good. The part of the day that it lands is basically irrelevant to me.
Totally agree that AI coding makes this even more important. We are working on a coding agent-first cloud and a large part of that is ensuring everything runs locally so folks can let their coding agents define the infra and test it all
It's a fair point but iff you neglect that the overwhelming revenue drivers for these services are large corps who are already locked-in.
Devx doesn't matter at all once you're there.
The myopathy among us "online people" is assuming number of voices here and elsewhere correlate to revenue.
Just fyi, myopathy is a general term for diseases that affect some types of muscles, while myopia is short-sightedness -- assuming the latter is what you were going for!
Without the infrastructure behind it to make it make sense, cloud platforms just seem like convoluted ways of storing data and launching applications/VMs to me.
The only functional use of a tool like this to me would be to learn how to use AWS so that I can work for people who want me to use AWS. Would that not be to Amazon's benefit?
[1] https://github.com/anthropics/claude-code/issues/11447#issue...
reply