Legacy code found its workforce. mistral's agents migrated 40,000 lines of fortran 77 to modern c++…
legacy code found its workforce. mistral's agents migrated 40,000 lines of fortran 77 to modern c++ for a european energy operator, detailed september 9, and the playbook is translation rules plus a trial batch before scale.
the backlog everyone avoided just became the cheapest work.
Context
Mistral's post of 9 September 2026 says it helped a European energy operator migrate 40,000 lines of Fortran 77 to C++ for a reservoir simulator with no test suite and no central documentation. It describes building a parity harness for numerical agreement first, using agents and a caller-callee tree to document the code, a first attempt with fully autonomous agents that gave functional but not modernized code, and a chosen workflow in which a human operates coder, tester and reviewer agents module by module. It states the first sprint covered 40,000 of 300,000 lines and that the codebase was self-contained and runnable, a favorable condition.
The 40,000 lines, Fortran 77 to C++, the operator and the date are first-party. Migrated applies to the first sprint of about 300,000 lines. The playbook is translation rules plus a trial batch was not the post's wording: the post describes a parity harness, documentation, architecture review with a reservoir engineer, a task queue and human pull request review, and says translation is largely solved while the work is architecture and verification. Cheapest work was not supported, since no cost figure was seen. The backlog everyone avoided just became the cheapest work is the author's take.
Watch next
- Any report on the remaining 260,000 lines or cost and time figures.
Sources
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 21 September 2026 at 02:16 IST. Sources are the papers and datasets the note draws on.
View the original post ↗Embed this note
More notes
The air is now being asked to keep its own ledger
the air is now being asked to keep its own ledger: ecmwf’s aifs compo becomes the first ai model to forecast atmospheric composition globally every three hours, cleanair simulates 365 days of pm2.5 over china in ten seconds, and a unified framework maps six pollutants at one kilometer across the whole country. the air now files its own composition report.
read the note →The current is now being asked to draw its own map
the current is now being asked to draw its own map: china’s langya 2.0 predicts six ocean phenomena including internal waves and mesoscale eddies, a deep net called wenhai resolves eddies globally with air sea flux formulas built in, and scripps infers surface currents from the way temperature patterns deform in satellite images. the ocean now files its own circulation report.
read the note →The soil is now being asked to report its own carbon
the soil is now being asked to report its own carbon: a nix color sensor paired with generative data augmentation predicts soil organic carbon without a lab, random forest drives 74 percent of soil health mapping studies, and sentinel 2 tracks five year carbon change across france and italy from 922 samples. the dirt now files its own carbon account.
read the note →