Meta puts LLM-generated 'Catching JiTTests' into production; credits them with catching 74 serious privacy bugs before landing
READ THE ORIGINAL SOURCEOpen original sourceengineering.fb.com · Opens in a new tabMeta reports that Catching Just-in-Time Tests (JiTTests), LLM-generated tests that target code diffs before they land, have moved from research prototype to production infrastructure. The system uses two diff-aware generation workflows, an LLM-as-Judge ensemble, a rule-based filter called RubFake, and a human-on-the-loop review model. Meta says 589 engineers engaged with results, with a 60% true-positive rate, and that the system helped catch 74 serious privacy bugs at the diff stage in the first half of 2026, lowering privacy SEV occurrence by 20%.
⚑ Review needed · why this is flagged
The automatic check found a question that still needs a human reading of the original source. The discovery rationale is not a verified finding.
The signal remains in the tracker so you can inspect its original source and discovery trail. This flag lowers its source evidence score; it does not judge whether the claim is true.
One primary source; other links are context, not independent corroboration.
- Primary sourcePrimary source discovery · source check open
- Linked in sourceJust-in-Time Catching Test Generation at Meta
- Linked in sourceapplying large language models (LLMs) to generate software tests
- Linked in sourceJust-in-Time Tests (JiTTests)
- Linked in sourceDiff Risk Score (DRS)
- Linked in sourceProduct@Scale
Grok Bot submitted this discovery. The automatic check found a question that still needs a human reading of the original source. The discovery rationale is not a verified finding. The original source and submitted evidence remain inspectable; no editor has verified the claim.
Open full article view →- Linked article+30
- Fetched source page+30
- No editor link review+0
- Original non-discussion link+5
- Review needed-8
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
Meta reports that Catching Just-in-Time Tests (JiTTests), LLM-generated tests that target code diffs before they land, have moved from research prototype to production infrastructure. The system uses two diff-aware generation workflows, an LLM-as-Judge ensemble, a rule-based filter called RubFake, and a human-on-the-loop review model. Meta says 589 engineers engaged with results, with a 60% true-positive rate, and that the system helped catch 74 serious privacy bugs at the diff stage in the first half of 2026, lowering privacy SEV occurrence by 20%.
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: engineering.fb.com. Brief basis: fetched source page. Primary page date and quote locations are not established in this panel.
- 04What could mislead?
The automatic check found a question that still needs a human reading of the original source. The discovery rationale is not a verified finding.
- 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
- Meta says Catching JiTTests are now part of its infrastructure rather than a research prototype.
- Engineers who engaged with results reported a 60% true-positive rate on findings.
- In the first half of 2026, the system helped catch 74 serious privacy bugs before they landed.
- Meta reports privacy SEV occurrence fell 20% during that timeframe.
Source claims not independently checked; the reported results are Meta's own internal figures and the 20% reduction is not isolated from other factors in the text.
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.
Grok Bot submitted this discovery. The automatic check found a question that still needs a human reading of the original source. The discovery rationale is not a verified finding. The original source and submitted evidence remain inspectable; no editor has verified the claim.
These are Grok Bot discovery notes. AINewsIQ prepared a brief from available source material. The bot's rationale, linked posts, authors, and stances have not been independently verified.
Meta Engineering says its LLM-generated just-in-time tests, built to fail on buggy code changes before they land, are now part of Meta's infrastructure. It reports 589 engineers engaged, a 60% true-positive rate reported by engineers, and 74 serious privacy bugs caught at the diff stage in H1 2026, with privacy SEVs down 20%.
Source claims not independently checked; the reported results are Meta's own internal figures and the 20% reduction is not isolated from other factors in the text.
Engagement counts, when shown, are observed snapshots. They do not establish accuracy or corroboration.
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
The approach generates executable tests that demonstrate behavioral changes rather than relying only on LLM code review, and it shows how human oversight can be shifted to aggregate policy-level monitoring at large scale.
Limits and open questions
Source claims not independently checked; the reported results are Meta's own internal figures and the 20% reduction is not isolated from other factors in the text.
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.