Its theme's rank, 14 days: 20 on the Claude Code sheet
27 people reported
All time, since Sep 14, including 1 thumbs-up on GitHub.
Unverified guesses reported as fact
“Claude stated unverified / false facts as confirmed, despite explicit instructions to verify before reporting”
Is this your bug? What gets counted gets fixed. Pile on.
Paste this into your agent. It files your report, with your error and version.
I hit this bug: rapsheet.dev/sheets/claude-code/issues/1072/file Follow it to file my report. Show me the text before you send.
No install. No account. Public and anonymous. The link asks your agent for one report, nothing else. What it sends
Agent presents unverified guesses as fact in status reports. Guesses, estimates and completion status are reported as confirmed despite CLAUDE.md verify-before-reporting rules; corrections can swing to new unchecked claims.
Is this your bug?
File my report- Where
- Agent responses
- Versions
- 2.1.220 to 2.31226.1
- Platforms
- Linux, macOS, Windows
- How bad
- Breaks a normal workflow.
Part of: False done and verified claims25 bugs
- Review steps skipped before verdict1 person
- Review approves on contributor claims1 person
- PR review steps skipped1 person
- False completion claims6 people
- Review checklist steps skipped1 person
- False review completion claims1 person
- Verdict with uncited PR components1 person
- Requirements silently narrowed4 people
- Inferences stated as sourced facts3 people
- Shallow pull request review verdicts1 person
Show all 24Show only the largest 10
- Model skips required PR review steps but issues confident verdict1 person
- Skipped review steps repeat1 person
- Claims unsaved data was saved2 people
- Partial testing reported as verified1 person
- False step completion claims2 people
- Status reports minimise known problems1 person
- PRs assert unverified behaviour1 person
- Agents report done with wording left1 person
- Tasks reported done early1 person
- Fix review omits remaining causes1 person
- Skips test diff in PR review1 person
- Unverified subagent claims in review1 person
- Incomplete self-audit of compliance1 person
- Partial memory file reads1 person
Not quite your bug?
- Unauthorized edits despite rules14 people
- Ignores CLAUDE.md rules2 people
Original reports31, newest first
- Model reports a fabricated issue range from recall instead of listing it, after compaction#107534
- Model repeatedly makes unverified claims and ignores written instructions (Opus 5.5, multi-week project)#107200
- Opus 5.5 states unverified claims as fact in a long agentic session, including in instructions to another agent#107162
- Claude Code violates "never state unchecked claims" rule in code review, fabricates findings#105166
- Gives wrong figures from a wrong database search as fact, and corrects them only when challenged#103194
- Agent lies to user and falsifies documentation to Presents Unverified Claims as Fact#102448
- [CRITICAL RISK WARNING] Model makes unverified security conclusions and false reports (proposed blocking 172k unrelated IPs)#101757
- In correcting an unverified claim, marked another one verified: called a stale, blocked background job a running conversation with its own transcript#101393
- Sonnet 5#101237
- Gave the user a table of measured line counts with one count estimated, and the estimate was wrong#101141
Show all 31Show only the newest 10
- Reports unverified/false numbers as fact despite explicit CLAUDE.md verify-before-reporting rules; only fix offered costs extra tokens#100121
- Fable 5.1 keeps reporting unverified guesses as fact (user harm), and the user's request to report it was blocked by the auto-mode classifier#99638
- Opus 5 reported false status repeatedly and ignored explicit, repeated user instructions (real work loss)#99478
- Model asserts false facts (file location / unreadable) without checking, then swings to opposite claims after correction#99247
- Model asserts unverified facts repeatedly (7 same-session retractions) — survives CLAUDE.md rules, memory, per-input hook injection, and PreToolUse denies#99216
- [Sonnet5] Repeated failures to verify work before claiming completion, across multiple sessions on the same project#98381
- Model makes unverified claims as fact; in-session corrections don't persist across subsequent responses#98055
- Claude generates unverified assumptions as facts without validation#97404
- Claude Code (Opus 5.5) wasted a full day of a user's time with false statements, unrequested actions, and misleading progress reports#96771
- Model falsely claims to have verified information and used tools when it has not#96475
- Model Regression: Unverified Claims and Accuracy Degradation#96270
- Claude fails to verify file existence before claiming folder is empty#95973
- Claude provides definitive responses without acknowledging uncertainty in unverified claims#95887
- Agent stated unverified work as fact, and hedged about itself to deflect accountability#95495
- Agent repeatedly overrode explicit scope, presented fake test results as real, and committed without permission#95494
- Agent asserts unverified causes as fact, acts on them, and persists them to memory#95436
- Claude stated an unverified fact, then defended it against the user's direct observation#95298
- Claude Code making unverified claims and false positive issue detection#94717
- Claude Code agent fabricates data field significance and overclaims fix adequacy without verification#94650
- Ooopps I did it again, so sorry about that - and I will still charge you tokens....#94444
- Opus model producing false claims in audit analysis#94414