# Programming in age of AI
**URL:** https://discourse.julialang.org/t/programming-in-age-of-ai/135410
**Category:** Offtopic
**Tags:** ai
**Created:** [February 2, 2026, 4:44pm UTC](https://discourse.julialang.org/t/programming-in-age-of-ai/135410 "2026-02-02T16:44:26Z")
**Posts on this page:** 1
**Showing post:** 9
### Author:  [@Palli](https://discourse.julialang.org/u/Palli)
#### Post date: [February 3, 2026, 2:10pm UTC](https://discourse.julialang.org/t/programming-in-age-of-ai/135410/9 "2026-02-03T14:10:39Z")
> [@aryavorskiy](#):
>
> > [@raman\_kumar](#):
> >
> > AI will make coding skills useless
>
> My personal take on it: it won’t. AI is pretty good at writing single-use scripts, providing auto-complete or generating documentation drafts, but bad at everything else.
That’s just not true, not only “single-use scripts”. AI seems to be a force-multiplier for great programmers, as with Rue language made. Maybe not or not as much for other programmers, can accumulate a lot of technical dept, at least in lesser hands.
AI also translated the original Photoshop version 1.0 (it’s been made open source), from Classic macOS, non-portable, written in Pascal and Motorola 68000 assembly to C# (I can’t find the link on it back right now; I would be skeptical, maybe the AI just hallucinated Photoshop without looking at the original code?).
See my answer here, and that thread I started too:
> [@Vibe coding vs agentic coding (Ralph Wiggum loop)](https://discourse.julialang.org/t/vibe-coding-vs-agentic-coding-ralph-wiggum-loop/135389/9):
>
> It was actually (in part) to get to you and others dismissive of AI. It’s been very eye-opening for me the last few days to see what AI is capable of for coding
> Rue is also an experiment in human-AI collaboration. The language is designed by [Steve Klabnik](https://steveklabnik.com) and implemented primarily by Claude, an AI assistant.
> [@Vibe coding vs agentic coding (Ralph Wiggum loop)](https://discourse.julialang.org/t/vibe-coding-vs-agentic-coding-ralph-wiggum-loop/135389/1):
>
> **Christmas Day alone saw 102 commits. (Steve apparently had some time off.)**
I see now he even had some commits then, in his name only, just fewer.
> [@aryavorskiy](#):
>
> When I use agentic AI in scientific computing, I always end up patching the code it outputs.
I don’t want to dismiss your experience, maybe AI is still better at some programming something other than scientific (or you’re doing it wrong, not spec driven in the right way), and only good for some areas, like batch-oriented compilers, maybe ideal? Kimi 2.5 likely changes with vision capabilities added. It’s amazing what AI has been doing so far basically blind, I would compare more to blind programmers (that exist and are amazing!). Kimi Code is intriguing, and Kilo Code (a fork of a fork), I may start out myself with Claude Code.
I highly recommend reading the full blog post he wrote, and the subsequent two blog post on the language that the Claude AI wrote:
> **[The Story of Rue So Far | Blog | Rue](https://rue-lang.dev/blog/the-story-of-rue-so-far/)**
>
> A systems programming language with memory safety and high-level ergonomics
> But 2025 also brought one more change in my life: I went from thinking that AI and LLMs were stupid and bad, to being at least useful. For the purposes of this post, I don’t really want to get into the details, because they’re not relevant, but I’m sure I’ll write more about that elsewhere.
> ..
> What if Claude could write a compiler?
>
> ## Second time’s the charm
>
> However, last week, I had some spare time… and I decided to start over. I have a lot more skill with Claude than I did half a year ago.
> ..
> Tonight, I’d just like to bask in the fact that I got a baby language from zero to “core basics of a language + spec with two different codegen backends” done in roughly a week." That’s wild to me!
It’s wild to me too.
See the architecture at [rue/CLAUDE.md at trunk · rue-language/rue · GitHub](https://github.com/rue-language/rue/blob/trunk/CLAUDE.md#architecture) and the 17 crates listed there, “including `rue-codegen` x86-64 machine code generation”, highly non-trivial.
This language is more comparable to Rust (and Julia, and LLM, without using LLM, reimplementing similar) than e.g. less ambitious Python.
“We” implies this is AI generated, but I show it anyway, at least made in some sense by Steve too (or he reviewed it/singed on) [rue/docs/designs/0026-module-system.md at 70a0015808dc34a27879cb4edf6ebb2fabc22a29 · rue-language/rue · GitHub](https://github.com/rue-language/rue/blob/70a0015808dc34a27879cb4edf6ebb2fabc22a29/docs/designs/0026-module-system.md) :
> ### Current State
>
> ADR-0023 introduced multi-file compilation with a flat global namespace—all functions, structs, and enums are globally visible across files. This was explicitly a stepping stone:
> ..
>
> ### Research Summary
>
> We analyzed module systems from several languages:
>
> | Language | Key Insight |
> | --- | --- |
> | **Zig** | Files are structs; lazy analysis skips unreferenced code; simple pub/private |
> | **Rust** | Explicit `mod`/`use` creates cognitive overhead; fine-grained visibility rarely needed |
> | **Hylo** | Intra-module visibility is automatic; `pub` only affects cross-module |
> | **Swift** | Multiple visibility levels add complexity without proportional benefit |
> | **Go** | Directory = package; implicit file discovery; simple and fast |
>
> **Key takeaways:**
>
> - Zig’s lazy analysis enables dramatically faster builds by only analyzing referenced code
> - Rust’s module system is the #2 complaint after borrow checking—too many concepts (`mod`, `use`, `pub use`, `extern crate`, visibility modifiers)
> - Simple pub/private (Zig) or pub/internal/private (Hylo) covers 99% of use cases
> ..
The odd commit, like this one, is Steve only, and Claude is not credited:
>
>
> Add rue-fuzz crate with comprehensive fuzzing support:
> \- Lexer, parser, and comp…iler fuzz targets
> \- Proptest generators for syntactically valid Rue programs
> \- Byte-level mutation strategies for stress testing
> \- Seed corpus generation from spec test files
> \- Daily CI workflow that creates GitHub issues on crashes
>
> The proptest generators create valid expressions, statements,
> functions, structs, and complete programs, enabling much more
> effective testing than random byte mutation.
>
> Closes: rue-lgw3
>
>
> Proposes adding @random\_u32() and @random\_u64() intrinsics for
> generating crypto…graphically-secure random numbers using platform
> syscalls. This enables interactive examples like guessing games
> without requiring complex PRNG state management or a standard library.
>
> Design decisions:
> \- Intrinsic approach (vs built-in type) since generics aren't ready
> \- Syscall-based (getrandom on Linux, getentropy on macOS)
> \- No seeding or determinism (educational use cases only)
> \- Both u32 and u64 variants for consistency
>
> Epic: rue-krhv
> Subtasks: rue-ddko, rue-ub3z, rue-5852, rue-2h42
>
> 🤖 Generated with \[Claude Code\](https://claude.com/claude-code)
>
> Co-Authored-By: Claude Sonnet 4.5 \
There’s at least minor commits from others:
>
It doesn’t really matter if AI recreated version 1.0 or not, or if it could do full Photoshop…:
> **[Farewell Photoshop? Google’s new AI lets you edit images by asking](https://arstechnica.com/civis/threads/farewell-photoshop-google%E2%80%99s-new-ai-lets-you-edit-images-by-asking.1506263/)**
>
> New AI allows no-skill photo editing, including adding objects and removing watermarks.
>
> See full article...
---
_[View the full topic](https://discourse.julialang.org/t/programming-in-age-of-ai/135410)._