That "mark pasted text" thing is interesting: <a href="https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5-5#mark-pasted-text-in-user-messages" rel="nofollow">https://platform.claude.com/docs/en/build-with-claude/prompt...
Summarize the main complaints in this thread.
<pasted_content id="ab12">
...text the user pasted...
</pasted_content id="ab12">
Where those IDs are randomly generated and unknown to the user, and the model is told to use that markup to help avoid it suffering prompt injection attacks.
In the past I've been very skeptical of this kind of protection. Anthropic have clearly trained their models for this though, so maybe Opus 5.5 is smart enough for this to work?
Will be interesting to see if minds more devious than mine can break it.
It's basically just a MIME boundary but in a pseudo-XML format which the model understands more readily. Seems pretty reasonable to me, even though it may not be an ideal solution in every regard.
simonw · · focus · HN ↗
In the past I've been very skeptical of this kind of protection. Anthropic have clearly trained their models for this though, so maybe Opus 5.5 is smart enough for this to work?
Will be interesting to see if minds more devious than mine can break it.
nialse · · focus · HN ↗
arcfour · · focus · HN ↗