Mass attempted replication of old findings of LLMs with new models
READ THE ORIGINAL SOURCEOpen original sourcezou-group.github.io · Opens in a new tabExternal source links are regularly re-checked for safety, and checked again before opening using a recent cached result when available. How link checks work →
The source reports a revisit of 50 widely cited LLM findings across 20 models released July 2024 to September 2026. Within 15 months of publication, most tested claims either no longer held or showed substantially diminished effects. The authors classify claims as expired, weakened, persists, or strengthened. Results: 44% expired, 34% weakened, 16% persist, and 6% strengthened. Expired claims were mostly capability failures, while persisting claims tended to concern preferences and judgment.
One primary source; other links are context, not independent corroboration.
- Primary sourceHacker News · LLM
- Discovery linkHacker News
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 source reports a revisit of 50 widely cited LLM findings across 20 models released July 2024 to September 2026. Within 15 months of publication, most tested claims either no longer held or showed substantially diminished effects. The authors classify claims as expired, weakened, persists, or strengthened. Results: 44% expired, 34% weakened, 16% persist, and 6% strengthened. Expired claims were mostly capability failures, while persisting claims tended to concern preferences and judgment.
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: zou-group.github.io. 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; expiration dates are model-fitted estimates from a 20-model panel and do not propagate their uncertainty.
- 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
- 44% of 50 tested LLM claims are classified as expired in September 2026 models.
- Expired claims are mostly capability failures such as letter counting and fabricated citations.
- Claims about flattery, self-preference by judges, and abstention persist or strengthen.
- Among 22 claims with dated expirations, time to expiration averaged 15.7 months.
Source claims not independently checked; expiration dates are model-fitted estimates from a 20-model panel and do not propagate their uncertainty.
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
Practitioners citing LLM findings may rely on results that no longer hold for newer models. The study suggests claims about capabilities age faster than claims about preferences and judgment, which bears on how long benchmark results should be trusted.
Limits and open questions
Source claims not independently checked; expiration dates are model-fitted estimates from a 20-model panel and do not propagate their uncertainty.
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.