Source Intelligence
Follow Discord

DisclaimerUnofficial, and not affiliated with Anthropic. Nearly all of this is read straight out of what ships: npm bundles, captured prompts, published docs. Anthropic's own notes go in verbatim, marked as theirs. The rest is my reading, and every entry carries the strings behind it. If one looks wrong, vote it down and say why.

← All of v2.1.238 Home All releases ←olderv2.1.237 v2.1.239newer→
Claude Code v2.1.238

Feedback screen drops the "never used to train models" line

You'll notice
Useful2 Signal3
Feedback

The feedback confirmation no longer tells you your feedback is never used to train models.

What

The confirmation shown after sending feedback lost its two-line footer, which stated that Claude Code feedback is never used to train models. It now shows only "Any key to continue".

Details
  • A separate error string for an over-large feedback payload was replaced by a shared constant.
Evidence

Claude Code feedback is never used to train models.

Strings lifted out of the shipped bundle, so the claim above can be checked against them.

Related

Other releases about the same thing. Found by shared names or similar wording; neither means one caused the other.

See this entry in the whole of v2.1.238 →