HackerReposA FIELD GUIDE TO OPEN SOURCE
ProSponsor the shelf♧ 0
← Back to top all-time
alantech
marsha
Python2023–2023
alantech / marsha

marsha

Marsha is a functional, higher-level, English-based programming language that gets compiled into tested Python software by an LLM

2Distinct people
8Mentions
0Explicit recommenders
466GitHub stars
REPOSITORY AT A GLANCE

What to know before exploring

What it is

Marsha is a functional, higher-level, English-based programming language that gets compiled into tested Python software by an LLM

GitHub

Where it is used

No documented product use has been verified yet.

What people are saying

No recommendation phrase was found in the indexed comments.

No classified warning is attached to this page. Read the discussions before treating silence as approval.

Also in these discussions

No other repository is repeatedly linked in the same discussions.

This week on Hacker News

Nov 9–Nov 16 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/16/2026, 6:28:55 AM UTC.

No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.

Mentions over time

HN mentions by hour8 dated mentions

Observed mentions: 2023-07-25 15:43:56 UTC to 2023-07-26 06:18:11 UTC.

0122023-07-25 15:00:00 UTC to 2023-07-25 16:00:00 UTC (exclusive): 1 mentions; 1 submissions, 0 commentsJul 25, 15:002023-07-25 16:00:00 UTC to 2023-07-25 17:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-07-25 17:00:00 UTC to 2023-07-25 18:00:00 UTC (exclusive): 2 mentions; 0 submissions, 2 comments2023-07-25 18:00:00 UTC to 2023-07-25 19:00:00 UTC (exclusive): 2 mentions; 0 submissions, 2 comments2023-07-25 19:00:00 UTC to 2023-07-25 20:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-07-25 20:00:00 UTC to 2023-07-25 21:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-07-25 21:00:00 UTC to 2023-07-25 22:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-07-25 22:00:00 UTC to 2023-07-25 23:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 commentsJul 25, 22:002023-07-25 23:00:00 UTC to 2023-07-26 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-07-26 00:00:00 UTC to 2023-07-26 01:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-07-26 01:00:00 UTC to 2023-07-26 02:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 comments2023-07-26 02:00:00 UTC to 2023-07-26 03:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-07-26 03:00:00 UTC to 2023-07-26 04:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-07-26 04:00:00 UTC to 2023-07-26 05:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-07-26 05:00:00 UTC to 2023-07-26 06:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-07-26 06:00:00 UTC to 2023-07-26 07:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 commentsJul 26, 06:00

Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.

View mention counts and date ranges
UTC ranges include their start and exclude their end. Select a period to filter the source evidence.
PeriodStart (UTC)End (exclusive, UTC)MentionsSubmissionsComments
Jul 25, 15:002023-07-25 15:00:00 UTC2023-07-25 16:00:00 UTC110
Jul 25, 16:002023-07-25 16:00:00 UTC2023-07-25 17:00:00 UTC000
Jul 25, 17:002023-07-25 17:00:00 UTC2023-07-25 18:00:00 UTC202
Jul 25, 18:002023-07-25 18:00:00 UTC2023-07-25 19:00:00 UTC202
Jul 25, 19:002023-07-25 19:00:00 UTC2023-07-25 20:00:00 UTC000
Jul 25, 20:002023-07-25 20:00:00 UTC2023-07-25 21:00:00 UTC000
Jul 25, 21:002023-07-25 21:00:00 UTC2023-07-25 22:00:00 UTC000
Jul 25, 22:002023-07-25 22:00:00 UTC2023-07-25 23:00:00 UTC101
Jul 25, 23:002023-07-25 23:00:00 UTC2023-07-26 00:00:00 UTC000
Jul 26, 00:002023-07-26 00:00:00 UTC2023-07-26 01:00:00 UTC000
Jul 26, 01:002023-07-26 01:00:00 UTC2023-07-26 02:00:00 UTC101
Jul 26, 02:002023-07-26 02:00:00 UTC2023-07-26 03:00:00 UTC000
Jul 26, 03:002023-07-26 03:00:00 UTC2023-07-26 04:00:00 UTC000
Jul 26, 04:002023-07-26 04:00:00 UTC2023-07-26 05:00:00 UTC000
Jul 26, 05:002023-07-26 05:00:00 UTC2023-07-26 06:00:00 UTC000
Jul 26, 06:002023-07-26 06:00:00 UTC2023-07-26 07:00:00 UTC101

What Hacker News says

1 sources
> You're a bit too black-and-white on this situation. While I agree with your other points, I feel this argument doesn't really hold water. The output of the c compiler is deterministic. I struggle very hard to believe that the floating point rounding errors when you compile C will cause it to occasionally emit a binary that is not byte-identical multiple sequential runs in a row. What any program does at runtime is essentially non-deterministic, and that's 100% not what we're talking about here. If you consider https://github.com/alantech/marsha/blob/main/examples/web/we... ... The generated output of this file is a probability distribution with a sweet spot where the code does what you want; there are multiple outputs of code that sit in the sweet spot. You want one of these. The actual output of this file is a probability distribution
Read the rest
that includes the examples, but may or may not overlap the sweet spot of 'actually does the right thing'. ...in fact, and there's no specific reason to expect that, regardless of the number of examples you provide, the distribution that includes those examples also includes the sweet spot. For common examples it will, but I'd argue that it's actually provable that there are times (eg. where the output length of a valid solution would be > the possible out of the model), that regardless of the examples / tests, it's not actually possible to generate a valid solution from. Just like how constraint solvers will sometimes tell you there's no solution that matches all the constraints. So, that would be like a compiler error. "You've asked for something impossible". ...but I imagine it would be very very difficult to tell the difference between inputs that overlap the sweet spot and those that don't; the ones that don't will have solutions that look right, but actually only cover the examples; and there's literally no way of telling the difference between that and a correct solution without HFRL. It seem like an intractable problem to me. > Different tools for different scenarios, so if that is a huge problem, don't use Marsha as it currently is. As you say~
In Show HN: Marsha – An LLM-Based Programming Language

MAKE YOURSELF AT HOME

A few shortcuts

/
Search the collection
?
Open this guide
Esc
Close dialogs and navigation

Your saved repositories and interests stay in this browser.