cd /news/large-language-models/fable-5-2-reportedly-injects-a-hidde… · home › topics › large-language-models › article
[ARTICLE · art-167283] src=runtimewire.com ↗ pub= topic=large-language-models verified=true sentiment=↓ negative

Fable 5.2 reportedly injects a hidden copyright reminder, then blocks the chat inspecting it

Anthropic's Claude Fable 5.2 repeatedly injected a hidden copyright reminder into an API user's conversation after the words "pirated" and "torrent" appeared, then blocked the chat when the user tried to inspect the reminder, according to an account posted on X by a user identified as Jake (@v01dpr1mr0s3). Jake reported that the session was consumed by an instruction he never wrote and could not see in the normal interface, and that he could remove it only by rewinding the conversation; Anthropic documents both the classifier reminders and the HTTP 200 refusal format, leaving open how often a benign trigger word keeps an ip_reminder firing turn after turn and how developers should debug a refusal labeled as a success.

by read1 min views2 publishedNov 10, 2026
Fable 5.2 reportedly injects a hidden copyright reminder, then blocks the chat inspecting it
Image: Runtimewire (auto-discovered)

Jake says two words, "pirated" and "torrent," triggered a copyright reminder Fable 5.2 could not stop discussing, then a block when he inspected it.

        By [Ryan Merket](https://runtimewire.com/author/ryan-merket)
        · Published 

Primary source: [x.com](https://x.com/v01dpr1mr0s3/status/2119993017717358913)

Why it matters #

API customers pay for every token Fable 5.2 spends reasoning, and Jake's account describes a session consumed by an instruction the customer never wrote, could not see in the normal interface, and could not remove except by rewinding the conversation. Anthropic documents both the classifier reminders and the HTTP 200 refusal format, leaving questions about how often a benign trigger word keeps an ip_reminder firing turn after turn, and how a developer is supposed to debug a refusal that arrives labeled as a success.

An API user who posts as Jake (@v01dpr1mr0s3) says Anthropic's Claude Fable 5.2 repeatedly inserted a hidden copyright reminder into his conversation, fixated on the insertion, and then blocked a request on reverse-engineering grounds when he tried to inspect it.…

When you purchase through links in our articles, we may earn a small commission. This doesn’t affect our editorial independence.

── more in #large-language-models 4 stories · sorted by recency
── more on @anthropic 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/fable-5-2-reportedly…] indexed:0 read:1min 2026-11-10 · —