News for hackers. Stuff that matters.

A comment on Claude Code's "extended thinking" is a summary- not authentic thinking. Parent comment

Re:Claude Code's "extended thinking" is a summary- not authe... by exit on Monday June 22, 2026 @02:01PM (#48633613)
the point is that introducing data from a foreign source could lead to e.g. exfiltration:

the model retrieves https://somewhere into its context and then gets confused, following instructions embedded there.

it then retrieves https://somewhere?exfiltration=private_data_in_context

it gets worse if the tooling with hidden blocks can invoke can retrieve further secrets.

[ Parent | on HN ]
Re:Claude Code's "extended thinking" is a summary- not authe... by _alternator_ on Monday June 22, 2026 @03:34PM (#48634937)
If data exfiltration is a danger in your threat model, you need local LLMs (or at least ones you fully control) not just the full chain-of-thought reasoning.
[ Parent | on HN ]