Porting code with ai is a measurable engineering problem now. akka's spec-driven experiment across…
porting code with ai is a measurable engineering problem now. akka's spec-driven experiment across 65 open-source projects, out oct 5, tracked time, tokens and test parity across models and effort levels.
the question stopped being 'can ai port code' and became 'which spec shape makes it cheaper'.
Context
Akka's blog post says it built a self-improving, spec-driven delivery harness to test whether frontier models can port complete systems. Its summary says unattended rewrites of existing systems that pass the original's unit and integration tests are possible, that low effort models were more efficient than high effort models, and that the delivery harness and its structure had a bigger effect than the model.
InfoQ reports on October 5, 2026 that Akka used 65 open source projects to test a spec-driven workflow, measuring specification structure, context, model and effort selection, automated validation, token consumption and runtime performance. It says the initial tranche took 99.3 hours and consumed 9.41 billion tokens, with Akka reporting a lines-of-code or performance improvement in 57 of the 65 ports.
The 65 projects, time, tokens and test parity match the sources. The note says out oct 5. Akka's own post is dated September 3, 2026, and the October 5 date is InfoQ's coverage, so the experiment was published earlier than the note implies. This is a vendor experiment, run with Akka's own harness and specification format, with no independent replication in the pages read.
'Which spec shape makes it cheaper' is the author's framing. Akka's summary says harness structure mattered more than the model, and that low effort models were more efficient, which is consistent with the cost question. 'A measurable engineering problem' is the author's line.
Related work
- We Ported 65 OSS Projects With AI (Akka, September 3, 2026) ↗Primary source for the harness, the 65 projects and the summary findings.
- Akka Tests Spec-Driven AI Delivery across 65 Open Source Projects (InfoQ, October 5, 2026) ↗Independent coverage with the hours, tokens and 57 of 65 figures.
- Akka reports AI porting results across 65 open source projects (Trusence, October 5, 2026) ↗Short report on the findings from October 5, 2026.
Watch next
- Read Akka's post for how test parity was measured. Look for a replication on a different specification format.
Sources
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 9 October 2026 at 07:51 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 →