---
title: 'In the News: August 16, 2026, Evening'
description: "A Hacker News thread on Anthropic's system-prompt diffs shows what's baked into Claude's harness, and Simon Willison's case for why it stays closed to users."
canonical_url: 'https://darkfactory.dev/news/2026-08-16-evening'
markdown_url: 'https://darkfactory.dev/news/2026-08-16-evening.md'
collection: news
date_published: '2026-08-16T20:20:00-04:00'
date_modified: '2026-08-16T20:20:00-04:00'
---

# In the News: August 16, 2026, Evening


Anthropic has kept a public changelog of the system prompts running on claude.ai and the
mobile apps for two years, updated with every model release. In a five-hour-old Hacker News
thread that was still climbing, the harness-engineering crowd read it line by line, and Simon
Willison showed up to explain why the thing they wanted, a customizable system prompt, isn't
coming.

## 1. Anthropic's public system-prompt diffs get read closely for the first time, and Simon Willison explains why harnesses don't let you edit them

**[System Prompts](https://platform.claude.com/docs/en/release-notes/system-prompts)** · Anthropic · Claude Platform Docs, ongoing changelog, discussed on Hacker News August 16, 2026

Anthropic's release-notes page lists the system prompt shipped with every Claude model since
Claude Haiku 3, with diffs bolded where a prompt changed between dated versions for the same
model. A submission by user tosh reached 331 points and 144 comments within about five hours
on Hacker News, comments outpacing the site's usual ratio because commenters started pasting
excerpts and reacting to specific lines rather than discussing the page in the abstract. One
excerpt posted in the thread, from the current Opus 5 prompt, instructs the model on how to
handle a session that was meant for Claude Fable 5 but got silently redirected: Anthropic's
own account is that the redirect is a safeguards mechanism that "trigger[s], on average, in
less than 5% of sessions," put in place after Fable 5 launched with cybersecurity capabilities
Anthropic judged needed gating. Simon Willison, who keeps a git commit history of the prompt
diffs at github.com/simonw/research, called that routing language the most interesting change
between the Opus 4.8 and Opus 5 prompts, and gave the design rationale for why the prompt
itself stays closed to users: "harnesses don't make core system prompts customizable out of
the box because the system prompt is one of the defining features of the agent... Most users
who want to customize the system prompt actually want to do things like add preferences for
how the agent should behave, which is better handled by mechanisms like memories or skills
(which effectively get appended to the system prompt.)" Willison also confirmed, with another
commenter, that the published prompts are prefix-cached, so reading them costs nothing extra
per query.

**Why it matters:** The changelog shows what a frontier lab already puts in the one prompt block
it controls end to end. Willison draws a useful design split: put durable, vendor-level behavior in the system
prompt, and put user preference in memories or skills instead of fighting for space in a prompt
you don't own.