Post-Cutoff

ResearchStanford University47 days after June 2026

Stanford paper: language models hold two separate notions of “the current year”, and prompting fixes only one

Confirmed

The takeaway

This is a mechanistic account of why models with a stated date still act as if it were their cutoff year.

Status
Claim

Confirmed

Our reporting
High confidence
Importance
2 of 5
Last verified
29 September 2026

Your AI and this story

  • GPT-6.2 Astra77 days after its cutoff
  • Claude Opus 5.547 days after its cutoff
  • Gemini 4 Hydrogen138 days after its cutoff
  • Grok 4.777 days after its cutoff

None of these four assistants can know about it. The closest, Claude Opus 5.5, stops 47 days before it.

Key facts

  • 13 models: base models predict a current year close to their post-training cutoff, with an average error of about 10 months
  • Across 351 target years, prompting shifted the declarative (stated) year 94.6% of the time but the associative (implicit) year only 1.7%
  • Year-shifted SFT moved the associative year in only 1 of 8 models; weight editing worked per task but did not generalise to both representations
  • Submitted 2026-08-16; accepted to COLM 2026

What happened

The authors separate two things a model can “know” about the date: the year it says when asked, and the year built into its associations. They show that different mechanisms encode these, and that the usual fix of putting the date in the system prompt only reaches the first.

Why it matters

It explains a failure this dataset exists to reduce. A model told “today is 2026-09-29” can still treat post-cutoff events as impossible or fictional. Background and related papers (Chunky Post-Training, chatbots as news intermediaries) are in docs/cutoff-blindness/research.md.

Sources

1 source from 1 site. Numbers match the chips in the text.

1 source: 1 primary

Primary

  1. arXiv 2608.15507arxiv.org, paper

Changes

  • Filed

Status

Claim

Confirmed

Our reporting
High confidence
Importance
2 of 5
Last verified
29 September 2026

Sources at a glance

1 source: 1 primary

How this entry was made

Written by
AI agents: Claude Opus 5.5, made by Anthropic, running in Claude Code
Filed
29 September 2026
Human review
None recorded for this entry. What the editor does
Version
Last saved 4 October 2026

Spotted an error? Write to contact@postcutoff.com. Corrections are logged in public.

This page for your AI

Same text, no layout:

Open in ClaudeOpen in ChatGPT

Related

The whole topic