>It's easy to be a little bummed by the core thesis here: "for now we're stuck reading the code".
>I was pretty excited for a world where we could just ask for things and let the models cook and not read the code and get beautiful production software
I feel so disconnected reading those things. Reading and writing code is what brings me joy. I'd never feel "bummed" or "stuck" with it.
>remove the internet - forget the internet didn't exist.
Advertising as it exists today is tied to the Internet.
> you will see why the publishing business runs on ads.
And I maintain that tying business interests with advertising inevitably results in a conflict of interest between people producing goods and services, and people consuming them.
>it's only in the last 30 years - when ads got a bad rap
It's only natural that ads started being viewed in a more negative way as their effects were amplified by tech.
> due to tech bros who don't didn't learn humanities
Name calling doesn't add much to this discussion. My background is in humanities anyway.
Highly debatable, IMO. They're already a net negative for society on their own. We'd probably have a healthier Internet if ads didn't create incentives for social media companies to get their users addicted to serve them more ads.
Thank you so much. I was about to ask you for links, since they have multiple domains that look similar (kimi.ai, kimi.com, moonshot.ai, etc.). I wasn't sure which one was the legit one, or if they all are.
The plan I got is called "Moderato", which somehow isn't any of those 8... I'll try to read more about it.
I had the _exact_ same problem. Got the 20 USD/month subscription from Kimi.com (paid annually), exhausted my 5-hour quota with a simple prompt on OpenCode + Kimi K2.7 through their API. Cursor got the same prompt done in minutes.
According to their web interface, I'm also on 23% of my weekly usage. That feels crazy, as I do a lot more than that on the 20 USD Cursor plan, and never got even a warning.
I thought OpenCode was doing something wrong, but you had the same issue with Kimi Code.
I have the same impression. Services from MS have been specially buggy. Games also feel buggier in the last 10 years or so, and it somehow seems worse the bigger the studio is.
I stopped engaging in arguments once I realized there's very little to gain by trying to convince someone you're right (regardless of who's actually right).
If there's nothing major at stake (say, trying to convincing someone with cancer to seek treatment instead of ignoring it), it's not worth your (or their) time.
Zod is by far the most ergonomic way to express those ideas in TypeScript these days. I miss it when writing code in other languages.
The friction with the rest of the ecosystem is real, though. Most code out there expects you to handle errors with exceptions.
I get the impression that polymorphic return types could get in the way of JSC/V8/SpiderMonkey's JIT, but I haven't measured it and I'm not sure of the actual impact on hot and cold paths. Same for all the allocations caused by custom Option<T>/Result<T,E> implementations.
I think using Zod at the edge (with branded types and whatnot), while keeping return types as T/Promise<T> to keep a sane relationship with the ecosystem is a good middle ground.
Has anyone managed to boot it on bare metal using an AM5 motherboard?
I tried booting various Illumos distros through USB sticks on two different AM5 computers, and it got stuck very early on. I assume due to some incompatibility with USB 3.0. Meanwhile, a friend of mine booted on a Thinkpad just fine from a DVD.
Is it common for the toolkits written from scratch in Rust to have bindings for other languages?
I still think the ideal solution for Desktop GUIs would be the Qt company developing first class Qt bindings for Node.js (or some other runtime), and allow people to build UIs using web tech with Qt components.
> without copyright, all of the profit made on creative works (of a perhaps smaller pie) would get be kept by distributors like Amazon or Netflix
Assuming copyright gets dismantled is a good-faith way, Netflix/Amazon remaining as gatekeepers sounds unlikely, IMO. Free software clients like Popcorn Time provide a better experience and would be able to exist without threats from copyright trolls.
It's also much more robust regarding cultural preservation (as users and organizations can keep DRM-free local copies) and censorship (being torrent-based makes it much harder to delete a movie from existence).
> Sorry if my objection came across as overly antagonistic
Apologies accepted, no worries.
> while your experiences are unassailable as your experience, it may not be very representative of what's out there.
Of course. I try to speak in the first person when talking about my experiences, as a way to make that point (that they may not be representative of what's out there) more explicit.
>Agents used to be bad at this kind of stuff in my workplace as well, but newer models + agent-friendly documentation + AGENT.md begging agents to read the fucking docs before coding changed this landscape for us here.
Wouldn't that be true for humans as well? If you have documentation explaining a rule and you read it, you may not need to reach out to coworkers.
Otherwise I think the author's concerns are 100% valid.
>I was pretty excited for a world where we could just ask for things and let the models cook and not read the code and get beautiful production software
I feel so disconnected reading those things. Reading and writing code is what brings me joy. I'd never feel "bummed" or "stuck" with it.