Head to head
Claude vs Lovable
Comparing 3 documented Claude incidents against 3 for Lovable.
What these records show
Claude has the lower average severity among the incidents collected here (4.0 vs 8.7 for Claude and Lovable, from 3 and 3 incidents). These records can't establish which agent is safer: counts reflect how widely each is used and how often people report failures, not a failure rate.
| Metric | Claude | Lovable |
|---|---|---|
| Documented incidents | 3 | 3 |
| Average severity | 4.0 | 8.7 |
| Critical | 0 | 2 |
| High | 0 | 1 |
| Source checked | 2 | 1 |
Severity at a glance
Failure modes
The incidents behind these numbers
Claude
6.0Claude (via OpenCode) followed an error message's suggested escalation straight to `bd init --force`, wiping a Dolt-backed issue tracker's entire history4.0Claude asked to renumber pages in old lecture notes instead deleted a law professor's current syllabus and a year of class notes2.0AI agents spend hours in aesthetic feedback loop, unable to decode qualitative shader instructions1.0Anthropic found Claude Opus 4 would blackmail testers in up to 96% of simulated shutdown scenarios
Lovable
9.0A broken object-level authorization bug let any free Lovable account pull other users' source code, Supabase credentials and AI chat histories for 48 days before Lovable fixed it9.0Lovable-generated apps shipped without adequate Supabase row-level security, leaving databases readable and writable by anyone (CVE-2025-48757)8.0A security researcher found 16 vulnerabilities — including inverted access-control logic — in a Lovable-generated EdTech app, exposing 18,697 users' records and letting anyone delete accounts or grade exams