joshka

I've reimplemented ghostty in Rust and it performed on par with ghostty.

I've also given various models access to the tools necessary to measure performance and instructions to make things faster and they do pretty well. Hill climbing on a validatable measure is reasonably easy these days.

My direct experience here directly contradicts pretty much everything you've said can't be done. I.e. the human out of the loop stuff.

I really want to give this a try for a backup to my main email (hosted on fastmail), but a couple of those enterprise features are things I'd want to really try out as a solo hoster (AI Sieve and masked addresses). I can't justify paying $50/year for those though. :|

It's great. Much stronger on the UX side for things that devs need than Claude / Codex. Feels like the issue tracker isn't a black hole. Release notes aren't "Fixes and unicorns", but real links to PRs. I use both Codex and Claude models in it, often interchangably - sub agents from one to the other as needed.

(Bias, I'm more familiar with Codex than Claude as I worked on Codex when I was at OpenAI, but mainly on the TUI not the app - take my better than Claude with a grain of salt perhaps).

> what currently is stopping Anthropic, OpenAI et al. from internally building (and maybe buying) datasets of good and bad architecture, and RL'ing that?

I think to do this well, you have to have all the comms, code for various projects over time and do large scale analysis with tooling to get the various outcomes. A lot of "good and bad architecture" is really post-hoc rationalization of decisions that worked, and it's likely super noisy.

I'd love to see this done, regardless of how difficult it is.

> Corporations can’t use code from GPL projects without contributing to them in some way. Once the license is changed to MIT through a Rust rewrite, the project is free to be used for whatever purpose benefits corporations the most.

Counterpoint: people at corporations who want to contribute to OSS that is GPL licensed often cannot because the legal risks of doing so is too high for many corporations to bear. MIT / Apache licensed software doesn't have this problem. Yes, you might have that software internally forked and used and see that as a net loss, but more often you'll likely find that a company does not want to own their own fork of an open source product and actually contributes back. GPL is friction there, and its supposed benefits seem (at least in my limited experience in 20 something years in the industry) don't seem to outpace this downside. (I put my money where my mouth is on this and release all my OSS as MIT/Apache generally).

Obviously big things like the Linux kernel or other fundamental tooling this doesn't apply, but for anything smaller the GPL is bad.

Love your work on this and the previous site. Thanks!!!

One comment I had (I think I may have posted something like this on a github issue too) is that the site has that feel a bit of the sort of UI from the early 2000s - like helm, or cold fusion dashboards. There's something about it that screams developer generated UI rather than designer influenced. The light mode looks ok, but the greys on the dark mode don't feel particularly scream well suited to a theme website. (Obv. just my purely subjective opinion here).

The swatches preview on the search results pages probably should be much smaller swatches - similar to the copy embed perhaps. And the background of the top part of the card should match the background of the theme.

> We’d love to hear your thoughts on the new dashboard experience. Drop a comment with any questions or feedback in the Community discussion.

Please someone at github, hear this. Discussions are useless for feedback as you cannot subscribe to just the single thread you posted, only the entire discussion. That means I have a a binary choice of drinking the firehose or ignoring all future comments on some feedback I care about.

Please fix this.

My bugbears are narration - where the page tells me how to use it, or is labelling things in a way that a human would not use. "Choose a ..." where ... would be better as a heading.

I'd put it more generously (albeit biased), that they do take it seriously. But even serious people can be misguided in what things they pay attention to. Security is something that you have to get right 100% of the time and have people whose job it is to say no a lot. Research is the opposite. There's a clash of cultures in those two extremes and OpenAI was born from the wrong side of it. It's worth reminding that ChatGPT was launched as a "low key research preview".

I'd say the narrative that AI agents are a looming danger to the world is probably undersold rather than overhyped. I'm not particularly a doomer on this, but I have an infosec background too, so have a fair idea of what the combination of agentic harnesses + a malicious mindset could do to people/companies/nations/politics/world if wielded incorrectly. I think the good guys will win on this, but there will be plenty of interesting things that happen in that journey.

A good thought process might be to think back to the various large internet worms of the 2000s (Code red, Nimda, SQL Slammer, ...) which were mostly monoculture 0-days (not technically but close enough). Now consider if you no longer have monoculture / single bug as the limitation plus an ability for the hosts to take part not just as attack surface, but also cognition and planning. There's lots of variants of this and they're not particularly far fetched scenarios.