Post-Cutoff

ResearchAnthropic and AE Studio8 days after June 2026

Modular pretraining lets dangerous capabilities be switched off per module

Confirmed

The takeaway

On July 8, 2026 researchers from AE Studio and Anthropic published “Modular Pretraining Enables Access Control”.

Status
Claim

Confirmed

Our reporting
High confidence
Importance
2 of 5
Last verified
1 October 2026

Your AI and this story

  • GPT-6.2 Astra38 days after its cutoff
  • Claude Opus 5.58 days after its cutoff
  • Gemini 4 Hydrogen99 days after its cutoff
  • Grok 4.738 days after its cutoff

None of these four assistants can know about it. The closest, Claude Opus 5.5, stops 8 days before it.

Key facts

  • 800M-parameter model with four dual-use domains: GRAM and LoRA matched data filtering at capability removal and beat it on retained domains
  • Capability removal improved with scale across 50M–5B parameters
  • Four modules give 16 configurations from one training run, vs one run per configuration for data filtering
  • With only 50% of data labelled, GRAM isolated capabilities better than filtering or LoRA
  • Authors include Cem Anil and Alex Cloud (Anthropic) and Judd Rosenblatt (AE Studio)

What happened

An extension of gradient routing. Dangerous knowledge is placed in removable modules during pretraining instead of being filtered out of the data.

Why it matters

It points to tiered access, where vetted users get a model with, say, the virology module and the public does not, without training separate models. This bears on how labs might ship open or differentiated weights safely.

Sources

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

1 source: 1 primary

Primary

  1. Anthropic Alignment Science blog: Modular Pretraining Enables Access Controlalignment.anthropic.com, paper

Changes

  • Filed

Status

Claim

Confirmed

Our reporting
High confidence
Importance
2 of 5
Last verified
1 October 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
1 October 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

On “Should we be worried?”

  • Response Researchers showed dual-use knowledge can be put in switchable modules during pretraining; DeepMind published watermarks for AI-designed proteins and DNA.In Biology, chemistry and weapons

The whole topic