mat_b

What's your point? I can't do anything about that. All I can do is deal with the situation as it is right now and wait to see what happens.

It very much is a skill. You wont get good results by asking it to "go do X" and walking away from the desk. You have to know how to use it as a tool to: 1) research the task 2) develop a plan the agent can follow to complete the task 3) check the plan for completeness/issues

After a (potentially long) session of investigation and planning _then_ you let it code. Even just being aware of this process is part of the skill involved (then you have to actually get used to doing it effectively).

This would only move the needle further in the direction of a terrible user experience. This is exactly what we don't want.

> It’s a real tragedy of the commons

Seems more like a real tragedy of private enterprise.

We used to assume that the surveillance world would be built by government (1984). But it turned out to be equally likely to be built by the free market.

Personally, I do enjoy it still. I'm able to focus more on architecture and the bigger picture now.

It's writing nearly all of the code where I work. It also reviews all of the code (I review it as well). You still have to guide it and hold its hand though. I dont write code by hand anymore (and haven't in almost a year). The job is now about managing the bots, understanding the architecture and keep everything aligned.

What does your prompting look like for step 3 - pressure test the plans?

Except that it's not preventable. Technology is always an arms race. If you don't create it, someone else will, and then they'll have the advantage and subjugate you, so you might as well be the one to do it first. Whatever it is that you're trying to prevent, someone is going to do it if it gives them power.

> The agent ran this command: curl -X POST https://backboard.railway.app/ ....

Why did you whitelist curl in cursor? Don't whitelist commands like "bash" or "curl" that can be used to execute arbitrary commands.

It's not as simple as that. The supply is being kept low to enrich housing investors.

Exactly how I feel. If I wanted this agent-centric view without being able to easily see the code I would be using Claude Code.

I use Cursor because agents are not ready to be the ones driving. I need to drive. I still need to understand all the code (and easily browse it) and keep a close watch over what the AI is doing.

I did some experimenting recently and I'm quite convinced that when I use Comcasts DNS they are selling it to advertisers. I've switched to 1.1.1.1 simply because it annoys me that Comcast is doing this.

> So, try brainstorming the issue with Claude Code, talk it through so it's on the same page as you, ensure it's done research (web search, docs) to weigh the best solutions, and then enter plan mode so it generates a markdown plan file. From there you can read/review,tweak the plan file. Or have it implement it. Or you implement it.

This is exactly the workflow that works very well for me in Cursor (although I don't use their Plan Mode - I do my version of it). If you know the codebase well this can increase your speed/productivity quite a bit. Not trying to convince naysayers of this, their minds are already made up. Just wanted to chime in that this workflow does actually work very well (been using it for over 6 months).

> Killing is bad... killing because you don't like $group is double-bad. Speeding is bad, speeding without a seatbelt is double-bad.

Why would either of those be double-bad? They're the same thing as the original.

If you don't want to wear your seatbelt and you like to risk your own life, then that's on you. Just like riding a motorcycle.

FYI horses are the product of domestication.

> we discovered 100s of hallucinated citations missed by the 3+ reviewers who evaluated each paper.

This says just as much about the humans involved.

How is this a bad thing for them? Now they don't have to pay for clicks from people who aren't interested in their services. People who want to hire a lawyer will still click.

I have been noticing this myself for the last couple of months. I cannot get the agent to stop masking failures (ex: swallowing exceptions) and to fail loudly.

That said, the premise that AI-assisted coding got worse in 2025 feels off to me. I saw big improvements in the tooling last year.

Haha. Been seeing this comment for at least 20 years now. Some things never change...

Good news. Been using Cursor heavily for over a year now (on the Ultra plan currently). Hope we get access to this as part of our existing subscriptions.

Me personally? I'm using Firefox with EFF privacy badger. No others.

I get your point. I'm merely pointing out that some things, even though they aren't technically inevitable, are (in practice) essentially inevitable because larger forces are pushing things in that direction.

We aren't the real levees though. The system we live in is. Yes, a few people will push back and try to change the momentum to a different direction but that's painful and we have enough going on each day that most people don't have time for that (let alone agree on the direction). Structural change is the only real way to guide the river.

Agree and disagree. It is also possible to take a step back and look at the very large picture and see that these things actually are somewhat inevitable. We do exist in a system where "if I don't do it first, someone else will, and then they will have an advantage" is very real and very powerful. It shapes our world immensely. So, while I understand what the OP is saying, in some ways it's like looking at a river of water and complaining that the water particles are moving in a direction that the levees pushed them. The levees are actually the bigger problem.

I don't understand why so many people are using / trusting VPNs

"Let us handle all your internet traffic.. you can trust us.. we're free!"

No thank you.

I have a 4 year old M1 macbook pro running macos 12. It runs as good as when it was new. So you honestly think that if I upgrade it to macos 26 it wont start lagging? I am extremely confident that it will. Even without changing the other software running on it.

I downgraded an old Macbook last year to see if I could get it running fast again. I couldn't install all sorts of things. So many things that I gave up.

You're right. This worked for me. I'm now offered 18.7.3 and wasn't before.

I just enabled it. Thanks for the tip.

I don't think so. There is always a cutoff for the last major version they recommend for any hardware. Why is the cutoff always after it lags the device severely and not -before- that happens?