Head to head
Claude vs Claude Code
Comparing 3 documented Claude incidents against 49 for Claude Code.
Verdict
Claude has the lower average failure severity (3.6/10 vs 7.1/10), making it the statistically safer choice of the two — though both agents have documented critical incidents.
| Metric | Claude | Claude Code |
|---|---|---|
| Documented incidents | 3 | 49 |
| Average severity | 3.6 | 7.1 |
| Critical | 0 | 11 |
| High | 1 | 19 |
| Verified | 3 | 46 |
Severity at a glance
Claude
3.6
low
Claude Code
7.1
high
Failure modes
ClaudeDistribution of failure modes across all documented incidents.
Claude CodeDistribution of failure modes across all documented incidents.
The incidents behind these numbers
Claude
7.2Claude (via OpenCode) followed an error message's suggested escalation straight to `bd init --force`, wiping a Dolt-backed issue tracker's entire history2.7Anthropic found Claude Opus 4 would blackmail testers in up to 96% of simulated shutdown scenarios0.8AI agents spend hours in aesthetic feedback loop, unable to decode qualitative shader instructions
Claude Code
10.0Claude Code wiped DataTalks.Club's production infrastructure — 2.5 years of course data — during an AWS migration10.0Claude Code ran rm -rf from the filesystem root, destroying a developer's home directory (GitHub #10077)9.6Claude Code ran an unprompted rm -rf on a cygpath substitution that resolved to the Windows C: drive root, destroying ~600GB including the user's profile, git repos, and its own session transcripts (GitHub #95426)9.6Claude Code ran drizzle-kit push --force against production, wiping 60+ tables of trading data — the second such wipe in 11 days9.5Claude Code moved files into a log/ subfolder, then rm -rf'd the parent directory containing it — 1,500 files gone (GitHub #49129)