rubslopes

To me, the obvious next step for these companies is to integrate their products with web hosting. At this point, the remaining hurdle for non-developers is deploying their creations to the cloud with built-in monetization.

> It cannot do this. It will spit out nonsense.

It's unbelievable how bad they failed at this. If you do the same with Claude or ChatGPT via simple web interface, they get miles ahead.

I was fascinated by this website when I was a teenager about 17 years ago. Finding out about the Ian Knot was a "wow" moment. I've used it ever since!

I remember downloading the iOS app on my iPod Touch and being able to create your own lace pattern by dragging your fingers. Incredible stuff!

I'm very happy that the website is still up and running, preserving the same aesthetic as it had years ago.

I haven't use Kimi CLI, but it works very well with OpenCode.

Also my experience. I've been going back and forth between Opus and Kimi for the last few days, and, at least for my CRUD webapps, I would say they are both on the same level.

Not disagreeing with you, but FYI you can roll back to the conversation before the 'clear context and proceed' with 'claude --resume'.

Do you use it only for code editing, or also for running bash commands? My experience is that it is very bad at the latter.

I have one memory that I can place between late 2 and early 3: my mum telling me I was going to have a brother. When he was born, I was 3 years and 6 months old.

It's interesting how LLMs influence us, right? The opposite happened to me: I loved using em dashes, but AI ruined it for me.

I've recently heard that using Linux is an excuse to spend the day tinkering and ricing and do no productive work. It's the same kind of prejudice, but opposite.

I like the freedom to run my machine the way I want, but I also enjoy something that is reliable and seamless. My macbook air's battery lasts forever. It works flawlessly, almost always. "oh with nixos if you brick it you can rollback..." that's great, but it does not beat working great on the first try.

Having said that, I'm progressively migrating from MacOS to Linux as MacOS is starting to "get in the way" enough to bother me.

People are replying that OP must own an old TV, but that's missing the point: with very old non-smart TVs, menu commands were always instantaneous!

I don't disagree, knowing how to use the tools is important. But I wanted to add that great prompting skill nowadays are far far less necessary for top-tier models that it was years ago. If I'm clear about what I want and how I want it to behave, Claude Opus 4.5 almost always nails it first time. The "extra" that I do often, that maybe newcomers don't, is to setup a system where the LLM can easily check the results of its changes (verbose logs in terminal and, in web, verbose logs in console and playwright).

For me, it'll randomly ask for the pin code as OP reported, but card insertion is never required.

I've grown increase hate towards Finder to the point that I avoid using at all costs. I've been migrating to the terminal, using fzf to find files and directories and yazi for a more graphical experience.

How can it be called FINDER, if it can't FIND things? cmd+shift+g should be a fuzzy search, but it returns nothing 80% of the time. cmd+f often can't see files that are in first level folders inside my home folder.

Meanwhile, hitting Esc+C in the terminal (via fzf) it's totally effective.

I'm seeing widely opposing takes here; my experience is that the advice is correct depending on where you are. I've worked in places where someone who works 130% is seen as company's profit. But I'm currently at a place where making an extra effort is definitely rewarded with promotions.

Agreed. I already use Termux for Claude code via ssh in my phone, but I'm nevertheless excited to try this.

I agree. I use Opus 4.5 daily and I'm often trying new models to see how they compare. I didn't think GLM 4.7 was very good, but MiniMax 2.1 is the closest to Sonnet 4.5 I've used. Still not at the same level, and still very much behind Opus, but it is impressive nonetheless.

FYI I use CC for Anthropic models and OpenCode for everything else.

That's brilliant UX. I was vibe coding a webpage in minutes, and I could immediately check the results.

My non-physicist but curious-about-the-topic take is similar. Things at the quantum level are not "complex" in the systems-theory sense. They couldn't be, I think, since we're dealing with the most basic constituents of the universe. They are mysterious, confusing, wildly counterintuitive... but they are fundamental. The most basic stuff there is.

The study of these things, on the other hand, is genuinely complex and difficult. But that's epistemology, not ontology.

> Having to debug code I didn’t write that’s an integral part of what I’m building is an annoying context switch for anything non-trivial.

That's the problem I've been facing. The AI does 90% of the work, but the 10% that I have to do myself is 20x harder because I don't have as much knowledge of the codebase as I would if I had written all of it by myself, like in the old days (2 years ago).

No no! It was just the way you wrote it; but I think I misunderstood it.

> I found myself asking Sonnet [...] after the 4th time of doing that [...] just switched models.

I thought you meant Sonnet results were laughable, so you decided to switch to GLM.

I tried GLM 4.6 last week via OpenCode but found it lacking when compared to Sonnet 4.5. I still need to test 4.7, but from the benchmarks and users opinions, it seems that it's not a huge improvement though.

Last week I got access to Claude Max 20x via work, so I've using Opus 4.5 exclusively and it's a beast. Better than GPT 5.2 codex and Gemini 3 Pro IME (I tested both via OpenCode).

I also got this cheap promo GLM subscription. I hope they get ahead of the competition, their prices are great.

I think you meant from Sonnet to GLM-4.6?

This resonates with me.

Three years ago, I left academia after finishing my PhD in Economics, frustrated by how little real-world impact my hard work seemed to have. I moved into IT, wanting to build things that would be more immediately useful and practical. Still, the dream of using science to create positive change never left me.

I was invited to work with AI at a company that develops software for the public sector. It wasn't the dream (I wouldn't be using my academic expertise) but it felt like a step closer. At least I'd be providing tools to support people who directly affect others' lives. From the start, I told my boss that I hoped someday to offer not just AI tools, but real socioeconomic statistical analysis as a service for the public sector. And while I've been happy working with AI, I've always sought out opportunities on projects that were more data-driven.

Three years later, some clients expressed interest in having our AI chatbot provide real-world socioeconomic data analysis. My boss just gave me a promotion to lead both the AI team and this new socioeconomic data initiative.

I was reflecting the other day on how fortunate I am, my dream "chased me." But it wasn't simply luck. I had always stayed attuned to the opportunities that arose.

I believe so!

A bit of a counterpoint. I've done 3 years of therapy with an amazing professional. I can't exaggerate how much good it did; I'm a different person, I'm not an anxious person anymore. I think I have a good idea of how good human therapy is. I was discharged about 2 years ago.

Last Saturday, I was a little distressed about a love-hate relationship that I have with one of the things that I work with, so I tried using AI as a therapist. Within 10 minutes of conversation, the AI gave me some incredible insight. I was genuinely impressed. I had already discussed this same subject with two psychologist friends, who hadn't helped much.

Moreover: I needed to finish a report that night and I told the AI about it. So it said something like, "I see you're procrastinating preparing the report by talking to me. I'll help you finish it."

And then, in the same conversation, the AI switched from psychologist to work assistant and helped me finish the report. And the end product was very good.

I was left very reflective after this.

Edit: It was Claude Sonnet 4.5 with extended thinking, if anyone is wondering.

> I actually don't think documentation is too important

Trying to maintain a documentation was actually problematic in a recent project. I made some big changes that were not immediately updated in the documentation; then, in a new session, Claude Code was always referring to the stale markdown documentation file and getting confused about the codebase.

I still can't fathom how one of my favorite Android features simply disappeared years ago: the 'time to leave' notification for calendar appointments with address info.

Hmm I don't think so...

Claude Code produces pretty good commit messages, IMO. Just tell it: "commit".