Cursor is my favorite of the VS forks. Agree that it delivers better plans than others. I prefer using Claude in Cursor over CC CLI when I am heads down going through bugs. I am disappointed in how "little value" in token use Cursor provides compared to others.
On API use, I am noticing verbose output across the board. When I task it with plans it now creates more detailed task counts and tasks descriptions. It is more constrained to its directions than 4.6.
It is the rush of "wow it solved this." I should take a break and work on something else, but in the back of my mind "what else can it solve?" Then I come up with extra work and sometimes lose at the LLM casino.
It feels like every other convenience in modern life. We trade off some value for lack of human ability. Should you drive or walk or bike? In the US, most people drive and sit all day. Now we have fenced off part of our week for dedicated physical exercise to counteract physical atrophy.
> It feels like every other convenience in modern life. We trade off some value for lack of human ability. Should you drive or walk or bike? In the US, most people drive and sit all day. Now we have fenced off part of our week for dedicated physical exercise to counteract physical atrophy.
And arguably, our society has made a lot of bad choices about many "convenience[s] in modern life." For instance, cities should probably be designed to make you walk more by default, so healthy physical activity isn't turned into a chore you then have to have the discipline to do consistently.
Basically, collectively, we're stupid and unwise, picking short term convenience and neglecting the medium and long term, and we need to get better at that.
Funny you should mention that. There was a HN post about the prompt similar to this: "I want to wash my car. The car wash is 100m away. Should I drive or walk?" - Was quite difficult for even frontier models. Surely they now do better, but it was quite entertaining reading the answers.
I agree in principle, although I personally consider mental atrophy to be far more serious than physical atrophy (and I value physical fitness very high already!).
As you suggest, it's clearly to curtail free speech further; but in a way that their supporters can claim isn't fascist because 'it's the companies doing it not the government'.
We do really need non-USA based social media, stat.
It represents a general purpose computer on your network which will accumulate vulnerabilities and never be patched or otherwise secured, making it a persistent insider threat as a launchpad for attacks on your network
The issue isn't really Android, it's the touchscreen and the way the UX is a regression from many analog single-purpose devices.
If you gonna have a single-purpose device - make it analog (or close to analog)!
Don't give it a perceptible boot-time and all the other flaws that come with general-purpose computing. Don't make the user have to "wake up the device", let alone have to visually confirm that it is woken-up, before they can switch to the next song.
It's controversial in education schools to "track" students, i.e. sort them into ability-categories and tailor each category's experience to its needs. For example, activist groups in New York City have been trying to kill gifted-and-talented schools and programs (e.g. Bronx Science high school) for years. It's painful to watch.
People can and do create rigorous private schools, but they're not accessible to the masses and often embody the same anti-talent mentality public ones do.
Nothing, based on the existence of thousands of exactly such schools within the US alone.
On the other hand: a disagreement about the actual definition of gifted, based on the existence of thousands of such schools in the US alone. "Gifted" in some jurisdictions simply means something anodyne like "top 10%" which obviously doesn't get close to creating an actually targeted school environment for your Mozarts.
reply