
building dev tools. ml data/training pipelines @syntiantcorp
Irvine, California
Joined July 2021
- Tweets5.9K
- Following245
- Followers335
- Likes25.9K
i wanted to test the astra 6.2 release on something id use, so we built seek, a native linux media center in zig.
it browses movies and shows with stremio add-ons, streams episodes over bittorrent, and plays them straight from a multipart rar.
1
42
is the google arc beginning
Introducing Gemini 4 Neon! Pushing the frontier across domains and punching above its model class in a meaningful way. To me, Neon feels like the right balance of intelligence, speed, and usability. Available now across @GoogleAIStudio, the API, and more!
16
how many ppl do you think he got w/ this
i deleted all the tests in my repo and banned them in AGENTS.md
tests were always just a second, worse copy of your logic. a leaky imitation humans wrote because we couldn't hold every invariant in our head (staying green half the time the real bug happened anyway)
opus 5.5+ is good enough at raw logic now to read the intended invariants straight from the codebase
maintaining that duplicate copy is just economic waste. plus it makes tasks take way longer while agents burn compute running tests when they almost certainly got it right anyway
48
the guy makes me want to obsess & build absolutely beautiful dev tools.
Rex demo time: magical and automatic remote copy/paste, drag/drop, and port forwarding (e.g. open web servers running on remote machines in your local browser). Plus, showcasing some of the internal plumbing that powers this and how you can hook into it with Lua scripting.
Our goal with Superlogical and Rex is for everything to feel local. I've said before: the moment any UI shows a selector between "local" and "cloud", the product has failed. The lines should blur, and we should build the foundational technology that makes it happen performantly, securely, and beautifully.
2
63
when do you think we'll see the "higher quality" from LLMs being better/faster at writing code than SWEs?
1
1
35
agree
虽然我写了快 9 年的 Rust 了, 但是在 AI 时代我反而强烈推荐性能和内存占用在同一水平线的 Zig
以前大家吹 Rust 吹得最狠的就是它那套严苛的内存和借用检查,觉得能帮人类程序员兜底,但到了现在这个已经不需要人类写代码的时代,这反而成了拖后腿的累赘
AI 生成代码追求一个快速迭代和秒级试错,特别是在 0.17 版本之后, 增量编译几乎都是写完1秒钟后就能编译好跑测试看结果
对比 Rust, AI 为了战胜编译器往往得反复读编译错误甚至强行绕弯路,各自 struct trait 生命周期满天飞, 增量编译一次要十多秒, 改动一次硬生生被拖慢几十倍
再加上 Zig 内存分配全靠显式传参,边界极其清晰,还能直接无缝调现成的 C 库, 在 AI 已经能帮我们把关基础逻辑, 拼的是迭代效率和底层掌控力情况下, Zig 这种轻量透明不需要 AI 和编译器较劲的语言设计反而有巨大的优势
22

















