Agreed completely on this (as a heavy daily user of Cursor). It's been the perfect in-between of coding by hand (never again!) and strictly "vibe coding" for me. Being able to keep my eyes on all the changes in a "traditional" IDE view helps me maintain a mental model of how my systems work.
I'm hoping in this new UI in v3 I can still get that experience (maybe it's just hidden behind a toggle somewhere for power users / not shown off in the marketing materials).
I'm an engineer at Cursor, can try to clarify questions here.
> I wish they'd keep the old philosophy of letting the developer drive and the agent assist. Even when I'm using AI agents to write code, I still find myself spending most of my time reading and reasoning about code.
We very much still believe this, which is why even in this new interface, you can still view/edit files, do remote SSH, go to definition and use LSPs, etc. It's hard to drive and ship real changes without those things in our opinion, even as agents continue to get better at writing code.
> I'm hoping in this new UI in v3 I can still get that experience (maybe it's just hidden behind a toggle somewhere for power users / not shown off in the marketing materials).
This new interface is a separate window, so if you prefer the Cursor 2 style, that continues to exist (and is also getting better).
That's good to hear, I might have jumped a little too quickly in my opinion. It's a bit of a Pavlovian response at this point seeing a product I very much love embrace a giant chat window as a UX redesign haha.
I would love to see more features on the roadmap that are more aligned with users like us that really embrace the Cursor 2 style with the code itself being the focal point. I'm sure there's a lot you can do there to help preserve code mental models when working with agents that don't hide the code behind a chat interface.
Reading diffs is an inescapable skill, needed for evaluating any kind of PR. This just makes it more interactive.
I just use Copilot with VS Code, but my flow is to just ask Claude to make a change across whatever files it needs to touch, then either accept the changes, edit the changes directly, or clarify whatever was different from my expectations.
Reading diffs is central to how I work with these agents.
> ~0.1% of southern forestland), which is a fraction of worse invasives: Japanese honeysuckle (4.4%) and Asian privet (1.4%).
Sample size of 1 here (I know), but I've spent a meaningful portion of my life outdoors in the south and I have _never_ seen swaths of the landscape covered with Japanese Honeysuckle or Asian Privet like I have Kudzu. It absolutely dominates _everything_ in areas where it's present here (not surprising when it can grow up to a 1 foot (0.3 m) a day.)
Not trying to say you're incorrect, just trying to get a better handle on this. The thought that there are more destructive invasive plants in the US south than Kudzu is kind of blowing my mind.
You won't see swaths of honeysuckle or privet because it grows in the understory throughout the entire forest, choking out natives. Part of their destructive power is that they bloom earlier than most natives in spring, essentially stealing the available sunlight in those golden weeks before the overstory leafs out and reduces sunlight in the understory.
I guarantee you that if you've spent a meaningful portion of your life outdoors in the south you have seen Japanese Honeysuckle at the least, it is everywhere. But it's not a dramatic/easily identifiable shower like kudzu.
The data I'm citing is from my textbook for my Ohio Citizen Volunteer Naturalist program I did in the Fall semester, it cites the US Forest report but doesn't give a link. I think it's from this report [PDF warning]: https://www.srs.fs.usda.gov/pubs/gtr/gtr_srs178/gtr_srs178_3...
I know the video, again it doesn't matter. I speed type on my phone exactly the same way I used to. I understand how autocorrect works and that it retroactively fixes multiple words later on. I typed this whole comment on my iPhone and I encountered no such issue.
What the video shows could be a problem only if you disable autocorrect or if you want to type a single letter. I made a bunch of errors typing this one and in the end the phone autocorrected it all.
The title I posted is what I got out of the RSS feed. I did not touch it manually and neither did my agent but I would consent to the change.
It does remind though that I’d better get rid of a swollen laptop battery I have in my wood shed. Might be fun to hit it with a few round balls which will liberate any energy left in it.
I could have sworn though that an earlier version of this articles had some photos of the damage.
As a technologist, this is an incredible development.
As a backpacker and avid hiker, no thank you. I go outside to intentionally avoid screens and the internet/connected world. Fortunately I can just not buy this and it won’t have an impact on my life.
Another interesting thing I’m curious about is if this would provide any benefits to SAR crews over traditional sat phones. I could potentially see some benefits there, maybe, but I guess time will tell.
> I’m curious about is if this would provide any benefits to SAR crews over traditional sat phones.
For their communications, I doubt it, unless they happen to need low-latency video (e.g. for telemedicine for complicated cases). Existing solutions are pretty robust, and for anything you use on the move you probably want an omnidirectional antenna you don't have to rest on some surface in operation.
I could imagine this being interesting for drone-based/agumented missing person search, though!
> Fortunately I can just not buy this and it won’t have an impact on my life.
Thank you for saying this. So many people have a knee-jerk reaction of "this will ruin the outdoors" or "this means I can never disconnect anymore", which both kind of imply a concerning lack of agency. The outdoors are large enough for everybody, and nobody can force you to buy and bring one of these things!
It could make it easier to stream music, I’ve come across people who play music on Bluetooth speakers during their hikes. It is really weird behavior that spoils the area around them. Then again, they could just download the music if they are really that devoted to being a nuisance.
Yeah, I'm also really not a fan of this. But as you say, this doesn't require an Internet connection.
Then again, I've also encountered large groups of hikers basically screaming to be able to all hear each other, sometimes while walking on narrow trails (making overtaking hard). It really doesn't take technology for people to be unaware of the space that they're in and be inconsiderate to others.
My first thought was "by backpacker they must mean the rucksack and machine gun variety protecting ukraine because not many backpackers want technology intruding on their expedition"
I'm hoping in this new UI in v3 I can still get that experience (maybe it's just hidden behind a toggle somewhere for power users / not shown off in the marketing materials).
reply