- My understanding is that the reasoning behind all this is:
- In 1985 there were a ton of different hardware floating-point implementations with incompatible instructions, making it a nightmare to write floating-point code once that worked on multiple machines
- To address the compatibility problem, IEEE came up with a hardware standard that could do error handling using only CPU registers (no software, since it's a hardware standard) - With that design constraint, they (reasonably imo) chose to handle errors by making them "poisonous" - once you have a NaN, all operations on it fail, including equality, so the error state propagates rather than potentially accidentally "un-erroring" if you do another operation, leading you into undefined behavior territory
- The standard solved the problem when hardware manufacturers adopted it
- The upstream consequence on software is that if your programming language does anything other than these exact floating-point semantics, the cost is losing hardware acceleration, which makes your floating-point operations way slower
- > I’ve tried all the popular alternatives (Copilot, Claude Code, Codex, Gemini CLI, Cline)
Can't help but notice you haven't tried Zed!
- As of August 2025, Zed had 150K monthly active users. That was before it supported Windows; the number is much higher now (although not publicly reported).
I'd be very surprised to learn that any other Rust UI crate has more real-world usage than GPUI!
Source:
https://sequoiacap.com/article/partnering-with-zed-the-ai-po...
- You don't have to use Codex in its terminal UI - e.g. you can use it in the Zed IDE out-the-box:
- When I wrote Elm in Action for Manning, I talked with them explicitly about the language being pre-1.0 and what would happen if there were breaking changes. The short answer was that it was something they dealt with all the time; if there were small changes, we could issue errata online, and if there were sufficiently large changes, we could do a second edition.
I did get an advance but I don't remember a clause about having to return any of it if I didn't earn it out. (I did earn it out, but I don't remember any expectation that I'd have to give them money back if I hadn't.) Also my memory was that it was more than $2k but it was about 10 years ago so I might be misremembering!
- > I get it, pausing some work to ship AI integration plumbing is a good strategy to keep momentum up with competition.
By every metric - lines of code shipped, hours per week spent on it, number of people assigned to it, etc. - AI is a minority part of what Zed does. It's a priority, but it's not the priority.
I know there's a disproportionate amount of blogging about AI, but that's a decision about what prose gets written, not what code gets written!
- It's actively being worked on - there have been 8 font rendering PRs in the past 3 weeks, most recently yesterday: https://github.com/zed-industries/zed/pulls?q=is%3Apr+is%3Ac...
A downside that comes with the territory of building the rendering pipeline from scratch is needing to work through the long tail of complex and tradeoff-heavy font rendering issues on different displays, operating systems, drivers, etc.
I know it's taking awhile to get through, but I agree it's important!
- A quick glance at Zed's changelog is all it takes to see that AI has been a minority of what Zed has shipped since it was rolled out over a year ago. :)
https://zed.dev/releases/stable
(And that's even with almost none of the work on the massive Windows project being included in the changelog!)
- We just pushed a fix! Here's how to get it:
- Start a new Claude Code Thread, which will kick off the background download of the new Claude Code ACP adapter.
- Wait a few seconds, then start another Claude Code Thread. The new thread will use the updated one.
We're working on a nicer UX for getting updated versions, which we'll definitely ship before Claude Code support leaves beta!
- Zed is open-source under GPLv3 - https://github.com/zed-industries/zed
That doesn't guarantee it will have paid contributors indefinitely, but the same is true of the other editors you listed. It does, however, guarantee that if Zed (the company) were to disappear, community members would be free to continue using the Zed editor (and developing it) in perpetuity!
- We're working on it! :)
You can pay for Zed today if you'd like - https://zed.dev/pricing - and also the editor itself is open-source under the GPLv3 license. So if at any point in the future Zed changes direction in a way you don't like, you are perpetually free to build the version you liked from source (or make a community fork and take it in a different direction).
- Yes, Opus is very noticeably better at programming in both Rust and Zig in my experience. I wish it were cheaper!
- > Given Rust's numerous benefits, is having subpar compilation time really that big of a deal?
As someone who uses Rust as a daily driver at work at zed.dev (about 600K LoC of Rust), and Zig outside of work on roc-lang.org (which was about 300K LoC of Rust before we decided to rewrite it in Zig, in significant part because of Rust's compilation speed), yes - it is an absolutely huge deal.
I like a lot of things about Rust, but its build times are my biggest pain point.
- A better argument against vector embeddings for AI code agents is that model performance degrades with number of tokens used (even when well below the context window limit), and vector chunks are more prone to bloating the context window with unhelpful noise than more targeted search techniques.
Claude Code doesn't do vector indexing, and neither does Zed. There aren't any rigorous studies comparing these tools, but you can find plenty of anecdotes of people preferring the output of Claude Code and/or Zed to Cursor's, and search technique is certainly a factor there!
- Not to worry! When VS Code launched, it had a tiny ecosystem compared to Atom. When Atom launched, it had a tiny ecosystem compared to Sublime Text.
Starting out with a much smaller ecosystem than already-popular alternatives is a totally normal part of the road to success. :)
- Zed employee here - there are no limits if you bring your own API keys!
- > Maybe I'm wrong but when I looked at zed last (about 2 months ago) the AI workflow was surprisingly clunky
I'm curious what you think of this launch! :D
We've overhauled the entire workflow - the OP link describes how it works now.
- > I don't want "agentic" tools, I just want to back and forth with an LLM to get a better idea.
Ah! So you can get that experience with the agent panel (despite "agent" being in the name).
If you click the dropdown next to the model (it will say "Write" by default) and change it from "Write" to "Minimal" then it disables all the agentic tool use and becomes an ordinary back-and-forth chat with an LLM where you can add context manually if you like.
Also, you can press the three-dots menu in the upper-right and choose New Text Thread if you want something more customizable but still not agentic.
- The debugger is now in beta!
You can sign up for the beta here - https://zed.dev/debugger - or build from source right now.
https://gist.github.com/rtfeldman/f46bcbfe5132d62c4095dfa687...