---
title: 'In the News: November 7, 2026 (Morning)'
description: 'Anthropic reports that telling Claude what memory is for beat fixed write rules, and that a wiki built over 128 sessions lifted a corpus-question score from 13% to 48%.'
canonical_url: 'https://darkfactory.dev/news/2026-11-07-morning'
markdown_url: 'https://darkfactory.dev/news/2026-11-07-morning.md'
collection: news
date_published: '2026-11-07T07:06:00-05:00'
date_modified: '2026-11-07T07:06:00-05:00'
---

# In the News: November 7, 2026 (Morning)


One item this morning, and it is a first-party write-up with numbers: Anthropic's account of how it gives Claude agent memory, including what happened when it told the model what to write down and when it did not.

## 1. Anthropic: fixed memory-write rules cost strong models most of their memory gain

**[The components of agent memory](https://www.anthropic.com/research/components-of-agent-memory)** · Anthropic · November 6, 2026

Anthropic describes memory as notes Claude keeps between sessions, and reports several of its own evaluations. On Continual Learning Bench (CL-Bench) 1.0, telling Claude only that a memory folder existed was enough guidance for Claude Opus 4.7 and Opus 5 to improve. When Anthropic added the rule "record only failures", both models lost much of that gain. Claude Sonnet 4.6 behaved differently: prompting it to read its memory files before answering and to test its own theories nearly doubled its score, and Anthropic says Sonnet 5 reads memory before answering 9 times out of 10 without being asked.

The post also covers "dreaming", background passes in which Claude checks its notes against session transcripts and reorganizes them. Anthropic reports that scaling a wiki-building run over a corpus of about 350,000 internal files (roughly 420M tokens) from 2 sessions to 128 sessions raised the score on 25 questions from 13% to 48% of graded criteria. The wiki alone topped out at 48%. Search plus the wiki rose from 54% to 61% as the wiki grew, against 53% for search alone, and saved about 20,000 tokens per question. On a contract-terms task, one shared table written by several agents kept 41 of 57 graded facts; one page per contract, quoting terms word for word, kept 57 of 57.

Two cautions come from Anthropic's own text. The wiki showed no clear gain on a task where criteria could be met from a single document, and on another it grew larger than the source files. In the Pokémon Red comparison, a Sonnet 3.7 run wrote 413 memory files and earned one badge while a Claude Fable 5 run wrote nine files plus a single global.md and earned four; that is one run per model, as Anthropic describes it. The figures are Anthropic's own and the evaluation setups were not independently checked.

**Why it matters:** If you write memory instructions into a harness, this is evidence against prescribing what the agent may record, at least for current frontier models. It also points to two checks worth testing: a periodic pass that tests notes against transcripts, and a small always-loaded index. Anthropic's own phrasing is that "the top layer of the memory hierarchy has to stay relatively small."