When Modernization Breaks Working Code: A Study of LLMs on Legacy PHP
READ THE ORIGINAL SOURCEOpen original sourcearxiv.org · Opens in a new tabThe paper studies single-file LLM modernization of 100 WordPress 4.0 PHP files to PHP 8.3, with five LLMs, no project context, and no execution feedback. Outputs were checked with 630 hidden behavioral checks and 511 Rector-detected modernization findings, and compared against unchanged originals and the rule-based tool Rector. Untouched files passed 83 checks, while the best LLM passed only 59. Each LLM broke 32-51 working files, versus 7 for Rector. Most damage occurred in files needing no change.
One primary source; other links are context, not independent corroboration.
- Primary sourceHacker News · LLM
- Discovery linkHacker News
- Linked in sourceView PDF
- Linked in sourcearXiv:2610.40269v1
- Linked in sourceLearn more about arXivLabs
A community post points to the original link. Discussion and upvotes do not establish accuracy.
Open full article view →- Community discussion+5
- Fetched source page+30
- No editor link review+0
- Community link+0
This measures the stored source trail and editorial steps. It does not certify accuracy, peer review, or independent corroboration. Popularity adds no points.
View full scoring →Read the scoring rubric →What the source says
The paper studies single-file LLM modernization of 100 WordPress 4.0 PHP files to PHP 8.3, with five LLMs, no project context, and no execution feedback. Outputs were checked with 630 hidden behavioral checks and 511 Rector-detected modernization findings, and compared against unchanged originals and the rule-based tool Rector. Untouched files passed 83 checks, while the best LLM passed only 59. Each LLM broke 32-51 working files, versus 7 for Rector. Most damage occurred in files needing no change.
A READER'S EVIDENCE CHECKHow to read this signalSix questions about claims, sources, risks, and open checks
This is a signal-level guide until claim-level evidence is available. “Not recorded” means the evidence has not been assessed here; it does not mean a result is false. How we check AI news →
- 01Who is making each claim?
The claimant and whether each claim was measured or asserted are not recorded in this public brief.
- 02What was actually tested?
Not recorded per claim. Check the source for sample size, tasks, model and benchmark versions, and reproducibility.
- 03Where are the sources?
Original link: arxiv.org. Brief basis: fetched source page. Primary page date and quote locations are not established in this panel.
- 04What could mislead?
Source claims not independently checked; results are limited to single-file tasks on WordPress 4.0 PHP files without project context.
- 05What is at risk if wrong?
Not assessed per claim. Consider safety, privacy, cost, and adoption decisions before relying on the result.
- 06What would change the view?
No claim-specific check is recorded. An inspectable primary method or independent replication could change the assessment.
Key findings from the stored brief
- Untouched originals pass every check on 83 files; the best LLM leaves only 59 passing.
- Each LLM breaks 32-51 working files while repairing at most 10; Rector breaks 7 and repairs 6.
- Only 37 findings (7 percent) require a change under PHP 8.3, yet LLMs break 36-60 percent of compatible files.
- Many regressions come from files that no longer load, often due to type declarations PHP rejects.
Source claims not independently checked; results are limited to single-file tasks on WordPress 4.0 PHP files without project context.
This is a source-based abstract, not independent validation of the source's claims.
Evidence & sources
These links show where the signal came from and what the source page linked to. A linked page is context, not independent corroboration.
Related archive coverage
These relationships record a citation or topic overlap, not confirmation of the finding.
A community post points to the original link. Discussion and upvotes do not establish accuracy.
Timeline & updates
- Signal dated by source or discovery feed
This timestamp places the signal in the radar. It may be the discovery post date rather than the primary page's first publication date.
- Shared brief stored
AINewsIQ prepared one abstract from fetched source page.
A publication revision history is not stored for this signal. New engagement snapshots do not mean the source itself changed.
Why this may matter
It suggests LLM-based code modernization can silently break working legacy code, and that evaluations should compare against a no-change baseline and report modernization and behavior preservation separately.
Limits and open questions
Source claims not independently checked; results are limited to single-file tasks on WordPress 4.0 PHP files without project context.
Organization-specific financial, security, and operational effects require the organization's own context and review.
Discussion
Comments are reviewed before publication. Discuss the evidence, not the person.
No published comments yet.
Reader discussion opens with accounts. You can read the original source and published comments now.