Safeguards changedclaude-science/safeguards
Nearest release: v2.1.292, published 11 hours before upstream edited the page. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.
Upstream edited this page at 7 Oct 2026 04:51 UTC, give or take a minute or two: the time comes from Anthropic’s own sitemap rather than from a commit. This site recorded the change at 7 Oct 2026 05:07 UTC.
Upstream edited
Recorded here
Lines+1added
Lines−1removed
From line
12
where the diff opens
First seen
17 Sep 2026
this site's first read of the page
Recorded edits3to this page, all time
The whole hunk
from line 12, old and new numbered
/
from line 12
1212
1313When safeguards flag a message for content related to life sciences research, Claude Science can retry it right away on another model instead of stopping at the [**Chat paused** card](#when-safeguards-flag-a-message). It does this only when a model is available for automatic switching, and at most once per message. A notice names the model it switched to, and the session stays on that model until you choose a different one in the composer.
1414
15Automatic switching is on by default and applies to every session on this computer. To turn it off, go to **Settings > General > Model** and turn off the **Switch models when a message is flagged** toggle. The **Chat paused** card shows the same toggle when it offers **Retry with `<model>`**. Turning the toggle on from the card can also retry the paused message right away.
15Automatic switching is on by default. To turn it off, go to **Settings > General > Model** and turn off the **Switch models when a message is flagged** toggle. The **Chat paused** card shows the same toggle when it offers **Retry with `<model>`**. Turning the toggle on from the card can also retry the paused message right away.
1616
1717## Life Sciences Verification Program (beta)
1818
No line in this hunk matches that.