# Idiomatic Julia code in AI generated code

**URL:** <https://discourse.julialang.org/t/idiomatic-julia-code-in-ai-generated-code/139183>\
**Category:** General Usage\
**Tags:** ai\
**Created:** [September 3, 2026, 8:12am UTC](https://discourse.julialang.org/t/idiomatic-julia-code-in-ai-generated-code/139183 "2026-09-03T08:12:37Z")\
**Posts on this page:** 1\
**Showing post:** 7

<div class="post-metadata">

**Author:** ![Palli](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/palli/32/3380_2.png) [@Palli](https://discourse.julialang.org/u/Palli)\
**Post date:** [September 3, 2026, 9:54pm UTC](https://discourse.julialang.org/t/idiomatic-julia-code-in-ai-generated-code/139183/7 "2026-09-03T21:54:01Z")

</div>

Note “idiomatic” below, not in the paper, but what it enabled for Fortran porting:

> **[Persistent Recursive Worlds Enable Autonomous Software Evolution](https://arxiv.org/abs/2608.10450)**
>
> Complex software systems develop over timescales that exceed the lifespan of any individual coding agent. Most agentic software systems preserve continuity through persistent sessions, memories, managers or shared context. We introduce EvoX Genesis...

> .. Genesis used DeepSeek V4 Flash to build a Rust-based C compiler with about 250k tracked lines; the run lasted over 120 hours, archived over 1,000 agent episodes and incurred only US$44 in model-token charges. The compiler passed the complete c-testsuite and most LLVM and Csmith tests. In a separate compiler world generated with GLM 5.2, development continued after repeated agent replacement while retaining full test performance. Genesis also reimplemented 13 MESA modules with over 100k Fortran lines as a Rust workspace with nearly 90k Rust lines; across six numerical workloads, it achieved median speedups of 1.55–6.87x. These results show that long-horizon software development can be organized around a persistent project rather than a persistent agent. Project Website: [this https URL](https://genesis.evox.group/)

Costing **US$10.64** :

> **[GitHub - EMI-Group/genesis-demo-mesa-rs: Mesa Rust Port 100% written by Genesis.](https://github.com/EMI-Group/genesis-demo-mesa-rs)**
>
> Mesa Rust Port 100% written by Genesis.

> rewrite of the core numerical/physics stack of [MESA](https://docs.mesastar.org/) — the original ~462K-LOC Fortran 90/2008 stellar astrophysics suite. This workspace ports the `const → utils → math → mtx → interp_1d → interp_2d → num → chem → rates → neu → net → eos → kap` module chain into 13 idiomatic Rust crates, mirroring the original module APIs to preserve backwards compatibility, and ships a benchmark harness that proves the port is **faster than the original Fortran on every workload** (medians of driver-internal timings, gfortran `-O3 -march=native` vs Rust release `lto=fat, codegen-units=1`).
> 
> ## Highlights
> 
> - **~67K LOC of pure Rust library code** (129 files, 13 crates), `#![forbid(unsafe_code)]` everywhere — zero `unsafe`, zero FFI.
> - **~1050 tests green** (`cargo test --workspace` → 1052 passed / 0 failed / 18 ignored), including golden tests ported from the original Fortran `test_output` files (bit-exact or ~1e-9).
> - **No LAPACK/BLAS FFI**..

Rest is older in chronological order:

So we are down 99% in cost since 6 months ago, then cost 444x making a C compiler (and now 2.8x quicker to make “120 hours”/5 days vs 2 weeks):

> **[Building a C compiler with a team of parallel Claudes](https://www.anthropic.com/engineering/building-c-compiler)**
>
> Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.

> Over nearly 2,000 Claude Code sessions and $20,000 in API costs, the agent team produced a 100,000-line compiler that can build Linux 6.9 on x86, ARM, and RISC-V.

The key seems to be 1000/16 = 62x more agents, though only part of the reason, the paper is brand new to me.

> **[Blitzy's C Compiler: 230K Lines, Zero Human Code](https://blitzy.com/blog/hello-world-the-blitzy-c-compiler-has-arrived)**
>
> Blitzy built a C11 compiler from scratch in 4.5 days: 229,983 lines of Rust, 2,271 passing tests, and the Linux kernel boots on QEMU.

> **[How it works — evocompiler](https://evocompiler.com/how-it-works)**
>
> A compiler tuned to your project, not to the average of all programs: what evolve searches, what it measures, where the measuring happens, and what a result means.

---

_[View the full topic](https://discourse.julialang.org/t/idiomatic-julia-code-in-ai-generated-code/139183)._