### Preflight Checklist - [x] I have searched [existing issues](https://github.com/anthropics/claude-code/issues?q=is%3Aissue%20state%3Aopen%20label%3Abug) and this hasn't been reported yet - [x] This is a single bug report (please file separate reports for different bugs) - [x] I am using the latest version of Claude Code ### What's Wrong? Good afternoon, I am reporting major restriction in using Claude Code to develop any biologic, cheminformatics or ML-related hypothesis for therapeutics.

[BUG] Excessive safety flags when dealing with biology/cheminformatic/ML research (models - Sonnet, Opus)

Status Open

Reported on v2.1.229

Maintainer reply None cached

Activity 0 comments · opened Aug 13, 2026

Preflight Checklist

[x] I have searched existing issues and this hasn't been reported yet
[x] This is a single bug report (please file separate reports for different bugs)
[x] I am using the latest version of Claude Code

What's Wrong?

Good afternoon,
I am reporting major restriction in using Claude Code to develop any biologic, cheminformatics or ML-related hypothesis for therapeutics.

Claude's restrictions make it unusable for any drug discovery or cheminformatic research.

What Should Happen?

Claude should not flag genuine research on therapeutics or new modalities or machine learning work for drug discovery.

Error Messages/Logs

Steps to Reproduce

Simply ask to work to an architecture for antibody mutation to improve the affinity and selectivity or to collaborate on a DTi architecture. It will flag the content as dangerous and stop functioning.

Claude Model

Not sure / Multiple models

Is this a regression?

Yes, this worked in a previous version

Last Working Version

_No response_

Claude Code Version

2.1.229 (Claude Code)

Platform

Other

Operating System

Ubuntu/Debian Linux

Terminal/Shell