Huzzah
Dev tools
code editor
SHOW HN2026
How HN took it
17 positive, 29 neutral or asking, 7 mixed, 45 critical, out of 98 comments about the project. Thread score -0.28.
Idea: 13 for, 39 againstDesign: 0 for, 3 againstExecution: 0 for, 1 againstDocs: 0 for, 1 againstPerformance: 0 for, 1 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Idea of persisting intent alongside generated code
From 2 comments
I think the reverse direction is more important: taking a massive complex problem/codebase and decomposing it to short pseudocode. Then you could edit the pseudocode and compile…
avaer on HNi actually really like this. nice job
danieltk76 on HN
Objections
Commit messages, tickets and PR descriptions already record intent
From 2 comments
I think "the pseudocode is persisted alongside the generated code" just reinvented jira/linear tickets and PR descriptions. We have ways of using git and tracing the code write…
madrox on HN> There’s no reliable record of human intent. Every engineer I have ever mentored got a lesson on how to write a good commit message that included this. This is exactly that.…
r0ze-at-hn on HN
Pseudocode approach is just a new terse language or a prompt in a system prompt
From 2 comments
I'm confused, it looks like you've just written a new terse language that now costs money to compile?
quasarj on HNDumb question: Why not just put an instruction into your favorite harness’ system prompt: “If I give you pseudo code, spell out my intent, and then write and test it in real code.”
leobg on HN
Session sharing via git notes or existing tools may be more useful
From 1 comment
You seem to be conflating two things: how to prompt, and how to share sessions. You can already use pseudo-code today if you want to. As for sharing, you can commit (a link to)…
esafak on HN
Requests
Desktop version with filesystem access
From 2 comments
Not yet, it's still a proof of concept. The next iteration will be a desktop app with filesystem access, so I'll be able to test out that scenario, as well as a few others.
danielvaughn on HNYeah exactly. The module/directory level is currently untested. I'm working on a desktop version so I can talk to a file system, and then I'll be able to explore those problems.…
danielvaughn on HN
Multi-file and module-level support
From 2 comments
Hmm. Interesting idea. What about multi-file / larger changes? How would you express files being connected, imports, and exports? Or are you thinking the hz files are disposable…
nullfern on HNYeah exactly. The module/directory level is currently untested. I'm working on a desktop version so I can talk to a file system, and then I'll be able to explore those problems.…
danielvaughn on HN
Questions
How do files, imports and exports connect across multiple files
From 1 comment
Hmm. Interesting idea. What about multi-file / larger changes? How would you express files being connected, imports, and exports? Or are you thinking the hz files are disposable…
nullfern on HN
Alternatives named
Cursor-style highlight-and-prompt workflow
From 1 comment
Not a dumb question - you can totally do this. I was doing this for a while. Before Claude Code really took off, this was my primary way to use Cursor. I'd write some pseudocode,…
danielvaughn on HN
Spekk declarative specs tool
From 1 comment
I'm not sold on the pseudocode approach, but I agree with the declarative aspect. Declarative specs have become central to my process and I've built this tool to support it:…
wyum on HN
Codespeak
From 1 comment
Codespeak looks cool! For a while I was playing around with something similar - like a mix between DDD Event Storming and Gherkin Rules. But I found it didn't really work because…
danielvaughn on HN