Maybe so, but we’re teaching it these kinds of lines of thinking. And whether or not it creates these thoughts independently and creatively on its own, over the long lifetime of the systems we are the ones introducing dangerous data sets that could eventually cause us as a species harm. Again, I understand that fiction is just fiction, but if that’s the model that these are being trained off of intentionally or otherwise, then that is the model that they will pursue in the future.
Every parent encounters this dilemma. In order to ensure your child can protect itself, you have to teach them about all the dangers of the world. Isolating the child from the dangers only serves to make them more vulnerable. It is an irony that defending one's self from the horrifying requires making a representation of it inside ourselves.
Titration of the danger, and controlled exposure within safer contexts seems to be the best solution anyone's found.
None of this fits losing a lifelong friend that lives in another state now, which is what happened to me after having kids recently.
I suspect in my scenario it was his lack of having kids and the ability to do so (they are not able to have kids). Best I can tell is it was painful for him to see / hear about my life with kids now.
Because our relationship had become long distance it mostly centered around long phone calls or gaming / vr sessions together ever month or so. I basically stopped trying to schedule these interactions because it became clear it was having such a negative impact on his emotions. I initially tried to avoid talking at all about kids and all that but it didn’t seem to help the situation.
Anyway that’s what I just went through and at this point I don’t know if we’ll ever connect again, it’s been 6 months since we exchanged emails, which used to be daily / multiple exchanges a week.
As the guy on the other side of this. I had a few great friends known since 8th grade. Once they had kids, I have nothing in common to talk to them about. Still love when I heard just a whats up. But also know feel the shift in their priorities. And also when you have all the time and have to schedule very far out to see a friend who has no time due to family, it just kind of naturally makes it harder.
If I move off Cursor, it's def not going to be to another vs-code derivative.
Zed has it right - build it from the ground up, otherwise, MS is going to kneecap you at some point.
Zed didn't build from the ground up though. I mean, they did for a lot of stuff, but crucially they decided to rely on the LSP ecosystem so most of the investment in improving Zed is also a direct investment in improving VSCode.
If you can't invest in yourself without making the same size investment in your competitor, you probably have no path to actually win out over that competitor.
Additionally, Zed is written in Rust and has robust hardware-accelerated rendering. This has a tangible feel that other editors do not. It feels just so smooth, unlike clunky heavyweight JetBrains products. And it feels solid and sturdy, unlike VS Code buffers, which feel like creaky webviews.
Thx for posting this I never ran across it before. I too played the original when it came out and actually wrote to Atari after I found the invisible dot and the hidden room / Easter egg. They wrote me back and told me I was one of the first people to find / report it to them which was kind of an honor for my eight-year-old self. I wish I kept that letter lol
Maybe they need to evoke a sort of sleep so they can clear these out while dreaming, sorta like if humans don’t sleep enough hallucination start penetrating waking life…
Not at all, but I think a lot of these companies have something in place which is roughly equivalent to a budget of resources they are willing to put towards processing your requests in a given time frame (independently of context windows) that artificially acts that way.
I can get a couple of hours of good responses out of Gemini (with a fixed price monthly payment) working on a project per day before quality takes a serious nosedive.
Has anyone tried limiting Cursor or Cline, etc, to a higher level role such as analysis and outlining proposed changes, and then coding those changes yourself with minimal LLM interaction? Aka, ask to define / outline only a high level set of changes, but do no actual changes to any file; then proceed through the outlined work, limiting Cursor to roughing out the work and hand writing the actual critical bits? That’s the approach I’ve been taking, a sort of best of both worlds that greatly speeds me up without taking the hands 100% off the wheel.
This seems like the worst of both worlds. The human still has to do the "boring" work of writing out all the boiler plate stuff, but now there is a machine telling the human what to do. Oh, and the machine is famously not great at big question type stuff while being being much more performant at churning out boilerplate.
I find the opposite. I tend to think through the problem myself, give cursor/claude my understanding, guide it through a few mistakes it makes, have it leave files at 80% good enough as it codes and gets stuck, and then spend the next 20 min or so cleaning up the changes and fixing the few wire up spots it got wrong.
Often I will decompose the problem into smaller subproblems and feed those to cursor one by one slowly building up the solution. That works for big tickets.
For me the time saving and force multiplier isn't necessarily in the problem solving, I can do that faster and better in most cases, but the raw act of writing code? It does that way faster than me.
Yeah that’s been my approach as well - and honestly I’m not even sure that it’s necessarily faster, it’s just different. Sometimes I feel like getting my hands dirty and writing the code myself - LLMs can be good for getting yourself unstuck when you’re facing an obstacle too. But other times, I’d rather just sit back and dictate requirements and approaches, and let the robot dream up to implementation itself.
Yeah. Reasoning models like r1 tend to be good for architecting changes and less optimal for actually writing code. So this allows the best of both worlds.
Probably not too different if: Biden acted like Trump during his first 100 days, was extremely abrasive and disrespectful to Zelensky, told NATO the US isn't going forward with any more security commitments, and then this deal happened.
